{"slug":"llm-api-provider-prices","name":"LLM API provider price database: every price with its source, date and quote","snapshot":"2026-11-15","oldestCheck":"2026-11-14","url":"https://broadrouter.com/data/llm-api-provider-prices/","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/","covers":"Our compilation (the selection, normalised fields, model matching, notes, tables and method): CC BY 4.0.","notCovered":"Each price is a fact published by the provider named in its row, at the source URL given per row, and each quote is a short excerpt from that page; we do not license those pages to you. Credit the provider as the source of each price."},"unit":"USD per 1M tokens","source":"Each price read from the named provider's own pricing page; source URL, date checked and verbatim quote per row. Not BroadNet traffic data; BroadNet's own prices are not included.","method":["Source: each provider's own pricing page or price documentation, read with AI assistance and a page renderer between 2026-11-14 and 2026-11-15. Every row stores the source URL, the date checked and a verbatim quote from the page. No router, reseller or aggregator feed is used.","Scope: 41 providers (16 of them model makers with their own API), text and chat models only. Image, audio and embedding models are out of scope. Where a provider shows no public per-token price (for example \"contact sales\"), the model is left out and the provider file's notes say why.","Prices are USD per 1M tokens as the page shows them, at the lowest prompt-size tier in the provider's default region. Batch, flex or spot, priority, fast and ultrafast prices are separate rows with their tier. Promotional prices are kept as published, with the condition in notes. DeepSeek rows carry the peak-hour price; the off-peak price is in notes.","Model slugs join rows for the same model across providers. A dated snapshot that a maker serves under a base name keeps its own slug.","Re-checks: every Monday a script re-fetches each source URL and flags rows whose quote or price it can no longer find. It never edits data; flagged pages are re-read with AI assistance, and the value, quote and date are updated. Each row keeps its own check date.","BroadNet Inference, which publishes this site, is not in the database; its prices are in its own machine-readable file, pricing.json."],"columns":[{"name":"provider","desc":"Provider ID (one source file per provider: src/data/own-prices/<provider>.json)."},{"name":"provider_name","desc":"Provider's product name, as the file records it."},{"name":"provider_kind","desc":"\"maker\" if the provider trains models and sells them on its own API, else \"host\"."},{"name":"maker_api","desc":"true when this row is the model's maker selling it on its own API (a maker that hosts another lab's model is a host for that row)."},{"name":"model","desc":"Model slug, as in the /llm-api-pricing/<model>/ page address. Rows with the same slug are the same model."},{"name":"name","desc":"Model name as this provider lists it."},{"name":"maker","desc":"Lab that trained the model."},{"name":"provider_model_id","desc":"The provider's own model ID for API calls, where its page or docs give one; empty if not stated."},{"name":"tier","desc":"Service tier: standard (standard), batch (batch), flex (flex / spot), priority (priority), fast (fast), ultrafast (ultrafast). Only standard rows are ranked on the site."},{"name":"input_per_m","desc":"Input price, USD per 1M tokens, at the lowest prompt-size tier in the default region."},{"name":"cached_input_per_m","desc":"Cache-read input price, USD per 1M tokens; empty if the page shows none."},{"name":"output_per_m","desc":"Output price, USD per 1M tokens (reasoning tokens bill as output)."},{"name":"context","desc":"Context window in tokens as this provider states it; empty if not stated."},{"name":"precision","desc":"Numeric precision served (for example fp8), only where the provider states it; empty means not stated, not full precision."},{"name":"source_url","desc":"The provider page the price was read from."},{"name":"checked","desc":"Date the price was read from that page (YYYY-MM-DD)."},{"name":"quote","desc":"Verbatim text from the source page that shows the price, so anyone can re-check it."},{"name":"notes","desc":"Region, promotion, peak or off-peak, batch or other conditions that apply to this row."}],"summary":{"rows":1671,"providers":41,"makers":16,"models":430,"modelsWithPage":428,"modelsIndexed":198,"standardRows":1218,"tierRows":[{"tier":"standard","rows":1218},{"tier":"batch","rows":157},{"tier":"flex","rows":117},{"tier":"priority","rows":106},{"tier":"fast","rows":70},{"tier":"ultrafast","rows":3}],"models2":198,"models3":155,"makerRows":328,"cachedShareStd":65.2,"precisionShare":24.1,"contextShare":47.6,"idShare":71.3,"quoted":1671,"sourceUrls":363,"freeStd":6,"checkDates":["2026-11-14","2026-11-15"],"singleModels":230,"mostProvidersModel":{"model":"glm-5.3","providers":24},"largestProvider":{"provider":"deepinfra","rows":183}},"providers":[{"id":"deepinfra","name":"DeepInfra","kind":"host","prices":183,"models":92,"tiers":["standard","flex","priority"],"checked":"2026-11-14","pricingUrl":"https://deepinfra.com/pricing"},{"id":"amazon-bedrock","name":"Amazon Bedrock","kind":"host","prices":146,"models":110,"tiers":["standard","batch","flex","priority","fast"],"checked":"2026-11-15","pricingUrl":"https://aws.amazon.com/bedrock/pricing/"},{"id":"azure","name":"Microsoft Azure","kind":"host","prices":124,"models":97,"tiers":["standard","batch","flex","priority","fast"],"checked":"2026-11-14","pricingUrl":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/"},{"id":"google-vertex","name":"Google Vertex AI","kind":"host","prices":118,"models":63,"tiers":["standard","batch","priority"],"checked":"2026-11-14","pricingUrl":"https://cloud.google.com/model-garden/pricing"},{"id":"openai","name":"OpenAI","kind":"maker","prices":107,"models":37,"tiers":["standard","batch","flex","fast","ultrafast"],"checked":"2026-11-14","pricingUrl":"https://developers.openai.com/api/docs/pricing"},{"id":"gmi-cloud","name":"GMI Cloud","kind":"host","prices":97,"models":97,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://www.gmicloud.ai/en/models/maas"},{"id":"digitalocean","name":"DigitalOcean","kind":"host","prices":95,"models":59,"tiers":["standard","flex","fast"],"checked":"2026-11-14","pricingUrl":"https://docs.digitalocean.com/products/inference/details/pricing/"},{"id":"featherless","name":"Featherless","kind":"host","prices":87,"models":87,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://featherless.ai/pricing"},{"id":"novita","name":"Novita AI","kind":"host","prices":68,"models":67,"tiers":["standard","fast"],"checked":"2026-11-14","pricingUrl":"https://novita.ai/pricing"},{"id":"venice","name":"Venice","kind":"host","prices":60,"models":57,"tiers":["standard","fast","ultrafast"],"checked":"2026-11-15","pricingUrl":"https://docs.venice.ai/pricing"},{"id":"siliconflow","name":"SiliconFlow","kind":"host","prices":56,"models":56,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://www.siliconflow.com/pricing"},{"id":"google","name":"Google Gemini API","kind":"maker","prices":48,"models":12,"tiers":["standard","batch","flex","priority"],"checked":"2026-11-14","pricingUrl":"https://aistudio.google.com/docs/pricing"},{"id":"alibaba","name":"Alibaba Cloud","kind":"maker","prices":44,"models":43,"tiers":["standard","fast"],"checked":"2026-11-14","pricingUrl":"https://www.alibabacloud.com/help/en/model-studio/model-pricing"},{"id":"anthropic","name":"Anthropic","kind":"maker","prices":41,"models":18,"tiers":["standard","batch","fast"],"checked":"2026-11-14","pricingUrl":"https://platform.claude.com/docs/en/about-claude/pricing"},{"id":"cloudflare","name":"Cloudflare Workers AI","kind":"host","prices":40,"models":40,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://developers.cloudflare.com/workers-ai/platform/pricing/"},{"id":"parasail","name":"Parasail","kind":"host","prices":40,"models":39,"tiers":["standard","fast"],"checked":"2026-11-14","pricingUrl":"https://www.parasail.io/pricing"},{"id":"fireworks","name":"Fireworks AI","kind":"host","prices":36,"models":15,"tiers":["standard","flex","priority","fast"],"checked":"2026-11-14","pricingUrl":"https://fireworks.ai/pricing"},{"id":"mistral","name":"Mistral AI","kind":"maker","prices":27,"models":9,"tiers":["standard","batch","priority"],"checked":"2026-11-15","pricingUrl":"https://docs.mistral.ai/inference/pricing"},{"id":"amazon-nova","name":"Amazon (Bedrock)","kind":"maker","prices":25,"models":7,"tiers":["standard","batch","flex","priority","fast"],"checked":"2026-11-15","pricingUrl":"https://aws.amazon.com/bedrock/pricing/"},{"id":"together","name":"Together AI","kind":"host","prices":25,"models":25,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://www.together.ai/pricing"},{"id":"perplexity","name":"Perplexity","kind":"maker","prices":24,"models":24,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://docs.perplexity.ai/docs/getting-started/pricing"},{"id":"z-ai","name":"Z.ai","kind":"maker","prices":21,"models":21,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://docs.z.ai/guides/overview/pricing"},{"id":"coreweave","name":"CoreWeave Forge","kind":"host","prices":20,"models":20,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://coreweave.com/forge-pricing/inference-agents"},{"id":"chutes","name":"Chutes","kind":"host","prices":19,"models":18,"tiers":["standard","fast"],"checked":"2026-11-15","pricingUrl":"https://chutes.ai/pricing"},{"id":"baseten","name":"Baseten","kind":"host","prices":18,"models":14,"tiers":["standard","fast"],"checked":"2026-11-14","pricingUrl":"https://www.baseten.co/pricing/"},{"id":"baidu","name":"Baidu","kind":"maker","prices":15,"models":14,"tiers":["standard","fast"],"checked":"2026-11-15","pricingUrl":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en"},{"id":"hyperbolic","name":"Hyperbolic","kind":"host","prices":11,"models":11,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://www.hyperbolic.ai/inference"},{"id":"moonshot","name":"Moonshot AI","kind":"maker","prices":10,"models":4,"tiers":["standard","batch","fast"],"checked":"2026-11-14","pricingUrl":"https://platform.kimi.ai/docs/pricing/chat"},{"id":"crusoe","name":"Crusoe Cloud","kind":"host","prices":9,"models":9,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://www.crusoe.ai/cloud/pricing#Serverless-Inference"},{"id":"ibm-watsonx","name":"IBM watsonx.ai","kind":"maker","prices":9,"models":9,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://www.ibm.com/products/watsonx-ai/pricing"},{"id":"xai","name":"xAI","kind":"maker","prices":8,"models":8,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://docs.x.ai/developers/pricing"},{"id":"akashml","name":"AkashML","kind":"host","prices":7,"models":7,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://akashml.com/#pricing"},{"id":"cohere","name":"Cohere","kind":"maker","prices":6,"models":6,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://cohere.com/pricing"},{"id":"friendli","name":"FriendliAI","kind":"host","prices":5,"models":5,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://friendli.ai/pricing"},{"id":"sambanova","name":"SambaNova","kind":"host","prices":5,"models":5,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://cloud.sambanova.ai/plans/pricing"},{"id":"groq","name":"Groq","kind":"host","prices":4,"models":4,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://console.groq.com/docs/models"},{"id":"nscale","name":"Nscale","kind":"host","prices":4,"models":4,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://docs.nscale.com/docs/ai-services/models"},{"id":"minimax","name":"MiniMax","kind":"maker","prices":3,"models":2,"tiers":["standard","priority"],"checked":"2026-11-14","pricingUrl":"https://platform.minimax.io/docs/pricing/overview"},{"id":"ai21","name":"AI21 Labs","kind":"maker","prices":2,"models":2,"tiers":["standard"],"checked":"2026-11-15","pricingUrl":"https://www.ai21.com/pricing/"},{"id":"cerebras","name":"Cerebras","kind":"host","prices":2,"models":2,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://www.cerebras.ai/pricing"},{"id":"deepseek","name":"DeepSeek","kind":"maker","prices":2,"models":2,"tiers":["standard"],"checked":"2026-11-14","pricingUrl":"https://api-docs.deepseek.com/quick_start/pricing"}],"rows":[{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"apodex-1.1-mini","name":"Apodex 1.1 Mini","maker":"Apodex","provider_model_id":"apodex/apodex-1.1-mini","tier":"standard","input_per_m":0,"cached_input_per_m":null,"output_per_m":0,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Apodex 1.1 Mini 256K Free Free","notes":"Listed as Free on the pricing page."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"autoglm-phone-9b-multilingual","name":"AutoGLM Phone 9B Multilingual","maker":"Z.ai","provider_model_id":"zai-org/autoglm-phone-9b-multilingual","tier":"standard","input_per_m":0.035,"cached_input_per_m":null,"output_per_m":0.138,"context":65536,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"AutoGLM Phone 9B Multilingual 64K $0.035 /Mt $0.138 /Mt","notes":""},{"provider":"cohere","provider_name":"Cohere","provider_kind":"maker","maker_api":true,"model":"aya-expanse-32b","name":"Aya Expanse 32B","maker":"Cohere","provider_model_id":"c4ai-aya-expanse-32b","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://cohere.com/pricing","checked":"2026-11-14","quote":"Aya Expanse models (8B and 32B) on the API are charged at $0.50/1M tokens for input and $1.50/1M tokens for output","notes":"Research model (Cohere Labs). Price from the pricing FAQ. API model ID is not on the pricing page; c4ai-aya-expanse-32b is the ID Cohere publishes for this model."},{"provider":"cohere","provider_name":"Cohere","provider_kind":"maker","maker_api":true,"model":"aya-expanse-8b","name":"Aya Expanse 8B","maker":"Cohere","provider_model_id":"c4ai-aya-expanse-8b","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://cohere.com/pricing","checked":"2026-11-14","quote":"Aya Expanse models (8B and 32B) on the API are charged at $0.50/1M tokens for input and $1.50/1M tokens for output","notes":"Research model (Cohere Labs). Price from the pricing FAQ. API model ID is not on the pricing page; c4ai-aya-expanse-8b is the ID Cohere publishes for this model."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"beam-1.0-501b-a23b","name":"Beam","maker":"Reflection AI","provider_model_id":null,"tier":"standard","input_per_m":0.4,"cached_input_per_m":0.04,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"Beam $0.40 $0.04 $1.20","notes":"Listed as \"Beam\"; mapped to Beam 1.0 501B A23B."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"beam-1.0-501b-a23b","name":"Beam","maker":"Reflection AI","provider_model_id":null,"tier":"standard","input_per_m":0.4,"cached_input_per_m":0.04,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Beam — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.40$1.20$0.04","notes":"DigitalOcean-hosted. Listed as \"Beam\"; mapped to Beam 1.0 501B A23B."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"beam-1.0-501b-a23b","name":"Beam 1.0 501B A23B","maker":"Reflection AI","provider_model_id":null,"tier":"standard","input_per_m":0.4,"cached_input_per_m":0.04,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Beam 1.0 501B A23B $0.40 $0.04 (cached) $1.20","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-2","name":"Claude 2.0","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":8,"cached_input_per_m":null,"output_per_m":24,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 2.0 $8.00 $24.00 N/A N/A N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-2.1","name":"Claude 2.1","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":8,"cached_input_per_m":null,"output_per_m":24,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 2.1 $8.00 $24.00 N/A N/A N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3-haiku","name":"Claude 3 Haiku","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Claude 3 Haiku $0.25 $1.25 $0.125 $0.625 N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3-haiku","name":"Claude 3 Haiku","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.625,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3 Haiku $0.25 $1.25 $0.125 $0.625 N/A N/A N/A","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3-opus","name":"Claude 3 Opus","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":15,"cached_input_per_m":null,"output_per_m":75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3 Opus $15.00 $75.00 $7.50 $37.50 N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3-opus","name":"Claude 3 Opus","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":7.5,"cached_input_per_m":null,"output_per_m":37.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Claude 3 Opus $15.00 $75.00 $7.50 $37.50 N/A N/A N/A","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3-sonnet","name":"Claude 3 Sonnet","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3 Sonnet $3.00 $15.00 $1.50 $7.50 N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3-sonnet","name":"Claude 3 Sonnet","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3 Sonnet $3.00 $15.00 $1.50 $7.50 N/A N/A N/A","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.5-haiku","name":"Claude 3.5 Haiku","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":0.8,"cached_input_per_m":0.08,"output_per_m":4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.5 Haiku $0.80 $4.00 $0.40 $2.00 $1.00 N/A $0.08","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.5-haiku","name":"Claude 3.5 Haiku","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.5 Haiku $0.80 $4.00 $0.40 $2.00 $1.00 N/A $0.08","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.5-sonnet","name":"Claude 3.5 Sonnet","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.5 Sonnet $3.00 $15.00 $1.50 $7.50 N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.5-sonnet","name":"Claude 3.5 Sonnet","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.5 Sonnet $3.00 $15.00 $1.50 $7.50 N/A N/A N/A","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.5-sonnet-v2","name":"Claude 3.5 Sonnet v2","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.5 Sonnet v2 $3.00 $15.00 $1.50 $7.50 $3.75 N/A $0.30","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.5-sonnet-v2","name":"Claude 3.5 Sonnet v2","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.5 Sonnet v2 $3.00 $15.00 $1.50 $7.50 $3.75 N/A $0.30","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.7-sonnet","name":"Claude 3.7 Sonnet","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.7 Sonnet $3.00 $15.00 $1.50 $7.50 $3.75 N/A $0.30","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-3.7-sonnet","name":"Claude 3.7 Sonnet","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 3.7 Sonnet $3.00 $15.00 $1.50 $7.50 $3.75 N/A $0.30","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-fable-5","name":"Claude Fable 5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":11,"cached_input_per_m":1.1,"output_per_m":55,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Fable 5 $11.00 $55.00 N/A N/A $13.75 $22.00 $1.10","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $10.00, output $50.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5","name":"Claude Fable 5","maker":"Anthropic","provider_model_id":"Claude Fable 5","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5 | $10 / MTok | $12.50 / MTok | $20 / MTok | $1 / MTok | $50 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-fable-5","name":"claude-fable-5","maker":"Anthropic","provider_model_id":"anthropic/claude-fable-5","tier":"standard","input_per_m":10,"cached_input_per_m":null,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-fable-5","checked":"2026-11-14","quote":"$10.00 in $50.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-fable-5","name":"Claude Fable 5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Fable 5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$10.00$50.00$12.50$20.00$1.00","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-fable-5","name":"Claude Fable 5","maker":"Anthropic","provider_model_id":"claude-fable-5","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Fable 5 Input $10.00 … Output $50.00 … Cache Hit $1.00","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5","name":"Claude Fable 5","maker":"Anthropic","provider_model_id":"Claude Fable 5","tier":"batch","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5 | $5 / MTok | $25 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-fable-5","name":"Claude Fable 5","maker":"Anthropic","provider_model_id":"claude-fable-5","tier":"batch","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Fable 5 Batch Input $5.00 … Batch Output $25.00 … Batch Cache Hit $0.50","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-fable-5.1","name":"Claude Fable 5.1","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":11,"cached_input_per_m":0.275,"output_per_m":55,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Fable 5.1 $11.00 $55.00 N/A N/A $13.75 $22.00 $0.275","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $10.00, output $50.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5.1","name":"Claude Fable 5.1","maker":"Anthropic","provider_model_id":"Claude Fable 5.1","tier":"standard","input_per_m":10,"cached_input_per_m":0.25,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5.1 | $10 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok | $50 / MTok |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-fable-5.1","name":"Claude Fable 5.1","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":10,"cached_input_per_m":0.25,"output_per_m":50,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Fable 5.1 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$10.00$50.00$12.50$20.00$0.25","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-fable-5.1","name":"Claude Fable 5.1","maker":"Anthropic","provider_model_id":"claude-fable-5.1","tier":"standard","input_per_m":10,"cached_input_per_m":0.25,"output_per_m":50,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Fable 5.1 Input $10.00 … Output $50.00 … Cache Hit $0.25","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5.1","name":"Claude Fable 5.1","maker":"Anthropic","provider_model_id":"Claude Fable 5.1","tier":"batch","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5.1 | $5 / MTok | $25 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-fable-5.1","name":"Claude Fable 5.1","maker":"Anthropic","provider_model_id":"claude-fable-5.1","tier":"batch","input_per_m":5,"cached_input_per_m":0.125,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Fable 5.1 Batch Input $5.00 … Batch Output $25.00 … Batch Cache Hit $0.125","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":"Claude Fable 5.2","tier":"standard","input_per_m":8,"cached_input_per_m":0.2,"output_per_m":40,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5.2 | $8 / MTok | $10 / MTok | $16 / MTok | $0.20 / MTok | $40 / MTok |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":8,"cached_input_per_m":0.2,"output_per_m":40,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Fable 5.2 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$8.00$40.00$10.00$16.00$0.20","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":"claude-fable-5.2","tier":"standard","input_per_m":8,"cached_input_per_m":0.2,"output_per_m":40,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Fable 5.2 Input $8.00 … Output $40.00 … Cache Hit $0.20","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":"anthropic/claude-fable-5-2","tier":"standard","input_per_m":8,"cached_input_per_m":0.2,"output_per_m":40,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`anthropic/claude-fable-5-2` | 8.00 | 40.00 | 0.20","notes":"Third-party model resold through the Perplexity Agent API. Requires non-ZDR model access on request."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":"Claude Fable 5.2","tier":"batch","input_per_m":4,"cached_input_per_m":null,"output_per_m":20,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5.2 | $4 / MTok | $20 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":"claude-fable-5.2","tier":"batch","input_per_m":4,"cached_input_per_m":0.1,"output_per_m":20,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Fable 5.2 Batch Input $4.00 … Batch Output $20.00 … Batch Cache Hit $0.10","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":"Claude Fable 5.2","tier":"fast","input_per_m":16,"cached_input_per_m":null,"output_per_m":80,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Fable 5.2 | $16 USD / MTok | $80 USD / MTok |","notes":"Fast mode. Prompt caching multipliers apply on top; not available with the Batch API."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-fable-5.2","name":"Claude Fable 5.2","maker":"Anthropic","provider_model_id":null,"tier":"fast","input_per_m":16,"cached_input_per_m":0.4,"output_per_m":80,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Fable 5.2 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Fast Mode All prompts$16.00$80.00$20.00$32.00$0.40","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":1.1,"cached_input_per_m":0.11,"output_per_m":5.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 4.5 Haiku $1.10 $5.50 $0.55 $2.75 $1.375 $2.20 $0.11","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $1.00, output $5.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":"Claude Haiku 4.5","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":5,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Haiku 4.5 | $1 / MTok | $1.25 / MTok | $2 / MTok | $0.10 / MTok | $5 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-haiku-4.5","name":"claude-haiku-4-5","maker":"Anthropic","provider_model_id":"anthropic/claude-haiku-4-5","tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":5,"context":200000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-haiku-4-5","checked":"2026-11-14","quote":"$1.00 in $5.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Haiku 4.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$1.00$5.00$1.25$2.00$0.10","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":"claude-haiku-4.5","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Haiku 4.5 Input $1.00 … Output $5.00 … Cache Hit $0.10","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":0.55,"cached_input_per_m":null,"output_per_m":2.75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude 4.5 Haiku $1.10 $5.50 $0.55 $2.75 $1.375 $2.20 $0.11","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":"Claude Haiku 4.5","tier":"batch","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Haiku 4.5 | $0.50 / MTok | $2.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-haiku-4.5","name":"Claude Haiku 4.5","maker":"Anthropic","provider_model_id":"claude-haiku-4.5","tier":"batch","input_per_m":0.5,"cached_input_per_m":0.05,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Haiku 4.5 Batch Input $0.50 … Batch Output $2.50 … Batch Cache Hit $0.05","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-haiku-5.5","name":"Claude Haiku 5.5","maker":"Anthropic","provider_model_id":"Claude Haiku 5.5","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.10 / MTok | $0.125 / MTok | $0.20 / MTok | $0.01 / MTok | $0.50 / MTok |","notes":"For prompts up to 100,000 tokens; longer prompts bill at 5 times these rates."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-haiku-5.5","name":"Claude Haiku 5.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Haiku 5.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard ≤ 100K tokens$0.10$0.50$0.125$0.20$0.01","notes":"Prompts ≤ 100K tokens; > 100K tokens: input $0.50, output $2.50."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-haiku-5.5","name":"Claude Haiku 5.5","maker":"Anthropic","provider_model_id":"claude-haiku-5.5","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Haiku 5.5 Input $0.10 … Output $0.50 … Cache Hit $0.01","notes":"Global endpoint, prompts under 100K tokens; at 100K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"claude-haiku-5.5","name":"Claude Haiku 5.5","maker":"Anthropic","provider_model_id":"anthropic/claude-haiku-5-5","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`anthropic/claude-haiku-5-5` | 0.10 (≤100k) 0.50 (>100k) | 0.50 (≤100k) 2.50 (>100k) | 0.01 (≤100k) 0.05 (>100k)","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 100k tokens: 0.50 input, 0.05 cached, 2.50 output."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-haiku-5.5","name":"Claude Haiku 5.5","maker":"Anthropic","provider_model_id":"Claude Haiku 5.5","tier":"batch","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.25,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.05 / MTok | $0.25 / MTok |","notes":"Message Batches API. For prompts up to 100,000 tokens; longer prompts bill at 5 times these rates."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-haiku-5.5","name":"Claude Haiku 5.5","maker":"Anthropic","provider_model_id":"claude-haiku-5.5","tier":"batch","input_per_m":0.05,"cached_input_per_m":0.005,"output_per_m":0.25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Haiku 5.5 Batch Input $0.05 … Batch Output $0.25 … Batch Cache Hit $0.005","notes":"Global endpoint, prompts under 100K tokens; at 100K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-instant","name":"Claude Instant","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":0.8,"cached_input_per_m":null,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Instant $0.80 $2.40 N/A N/A N/A N/A N/A","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5","name":"Claude Mythos 5","maker":"Anthropic","provider_model_id":"Claude Mythos 5","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5 (limited availability) | $10 / MTok | $12.50 / MTok | $20 / MTok | $1 / MTok | $50 / MTok |","notes":"Limited availability: only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5","name":"Claude Mythos 5","maker":"Anthropic","provider_model_id":"Claude Mythos 5","tier":"batch","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5 (limited availability) | $5 / MTok | $25 / MTok |","notes":"Message Batches API. Limited availability: only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5.1","name":"Claude Mythos 5.1","maker":"Anthropic","provider_model_id":"Claude Mythos 5.1","tier":"standard","input_per_m":10,"cached_input_per_m":0.25,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5.1 (limited availability) | $10 / MTok | $12.50 / MTok | $20 / MTok | $0.25 / MTok | $50 / MTok |","notes":"Limited availability: only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5.1","name":"Claude Mythos 5.1","maker":"Anthropic","provider_model_id":"Claude Mythos 5.1","tier":"batch","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5.1 (limited availability) | $5 / MTok | $25 / MTok |","notes":"Message Batches API. Limited availability: only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5.2","name":"Claude Mythos 5.2","maker":"Anthropic","provider_model_id":"Claude Mythos 5.2","tier":"standard","input_per_m":8,"cached_input_per_m":0.2,"output_per_m":40,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5.2 (limited availability) | $8 / MTok | $10 / MTok | $16 / MTok | $0.20 / MTok | $40 / MTok |","notes":"Limited availability: only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5.2","name":"Claude Mythos 5.2","maker":"Anthropic","provider_model_id":"Claude Mythos 5.2","tier":"batch","input_per_m":4,"cached_input_per_m":null,"output_per_m":20,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5.2 (limited availability) | $4 / MTok | $20 / MTok |","notes":"Message Batches API. Limited availability: only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-mythos-5.2","name":"Claude Mythos 5.2","maker":"Anthropic","provider_model_id":"Claude Mythos 5.2","tier":"fast","input_per_m":16,"cached_input_per_m":null,"output_per_m":80,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Mythos 5.2 | $16 USD / MTok | $80 USD / MTok |","notes":"Fast mode. Prompt caching multipliers apply on top; not available with the Batch API. Limited availability."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4","name":"Claude Opus 4","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":15,"cached_input_per_m":1.5,"output_per_m":75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4 $15.00 $75.00 $7.50 $37.50 $18.75 N/A $1.50","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4","name":"Claude Opus 4","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":7.5,"cached_input_per_m":null,"output_per_m":37.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Claude Opus 4 $15.00 $75.00 $7.50 $37.50 $18.75 N/A $1.50","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.1","name":"Claude Opus 4.1","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":15,"cached_input_per_m":1.5,"output_per_m":75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.1 $15.00 $75.00 N/A N/A $18.75 N/A $1.50","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5.5,"cached_input_per_m":0.55,"output_per_m":27.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.5 $5.50 $27.50 $2.75 $13.75 $6.875 $11.00 $0.55","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $5.00, output $25.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":"Claude Opus 4.5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.5 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$5.00$25.00$6.25$10.00$0.50","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":"claude-opus-4.5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.5 Input $5.00 … Output $25.00 … Cache Hit $0.50","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":2.75,"cached_input_per_m":null,"output_per_m":13.75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.5 $5.50 $27.50 $2.75 $13.75 $6.875 $11.00 $0.55","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":"Claude Opus 4.5","tier":"batch","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.5 | $2.50 / MTok | $12.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.5","name":"Claude Opus 4.5","maker":"Anthropic","provider_model_id":"claude-opus-4.5","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.5 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.25","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5.5,"cached_input_per_m":0.55,"output_per_m":27.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.6 $5.50 $27.50 $2.75 $13.75 $6.875 $11.00 $0.55","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $5.00, output $25.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":"Claude Opus 4.6","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.6 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.6 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$5.00$25.00$6.25$10.00$0.50","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":"claude-opus-4.6","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.6 Input $5.00 … Output $25.00 … Cache Hit $0.50","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":2.75,"cached_input_per_m":null,"output_per_m":13.75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.6 $5.50 $27.50 $2.75 $13.75 $6.875 $11.00 $0.55","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":"Claude Opus 4.6","tier":"batch","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":12.5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.6 | $2.50 / MTok | $12.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.6","name":"Claude Opus 4.6","maker":"Anthropic","provider_model_id":"claude-opus-4.6","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.6 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.25","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.7","name":"Claude Opus 4.7","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5.5,"cached_input_per_m":0.55,"output_per_m":27.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.7 $5.50 $27.50 N/A N/A $6.875 $11.00 $0.55","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $5.00, output $25.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.7","name":"Claude Opus 4.7","maker":"Anthropic","provider_model_id":"Claude Opus 4.7","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.7 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-opus-4.7","name":"claude-opus-4-7","maker":"Anthropic","provider_model_id":"anthropic/claude-opus-4-7","tier":"standard","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-opus-4-7","checked":"2026-11-14","quote":"$5.00 in $25.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-4.7","name":"Claude Opus 4.7","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.7 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$5.00$25.00$6.25$10.00$0.50","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.7","name":"Claude Opus 4.7","maker":"Anthropic","provider_model_id":"claude-opus-4.7","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.7 Input $5.00 … Output $25.00 … Cache Hit $0.50","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.7","name":"Claude Opus 4.7","maker":"Anthropic","provider_model_id":"Claude Opus 4.7","tier":"batch","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":12.5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.7 | $2.50 / MTok | $12.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.7","name":"Claude Opus 4.7","maker":"Anthropic","provider_model_id":"claude-opus-4.7","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.7 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.25","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5.5,"cached_input_per_m":0.55,"output_per_m":27.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.8 $5.50 $27.50 N/A N/A $6.875 $11.00 $0.55","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $5.00, output $25.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":"Claude Opus 4.8","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.8 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-opus-4.8","name":"claude-opus-4-8","maker":"Anthropic","provider_model_id":"anthropic/claude-opus-4-8","tier":"standard","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-opus-4-8","checked":"2026-11-14","quote":"$5.00 in $25.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.8 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$5.00$25.00$6.25$10.00$0.50","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":"claude-opus-4.8","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.8 Input $5.00 … Output $25.00 … Cache Hit $0.50","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":"Claude Opus 4.8","tier":"batch","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":12.5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 4.8 | $2.50 / MTok | $12.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":"claude-opus-4.8","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Opus 4.8 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.25","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":"Claude Opus 4.8","tier":"fast","input_per_m":10,"cached_input_per_m":null,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5 / Claude Opus 4.8 | $10 USD / MTok | $50 USD / MTok |","notes":"Fast mode. Prompt caching multipliers apply on top; not available with the Batch API. Anthropic lists fast mode as deprecated for Claude Opus 4.8."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-4.8","name":"Claude Opus 4.8","maker":"Anthropic","provider_model_id":null,"tier":"fast","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 4.8 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Fast Mode All prompts$10.00$50.00$12.50$20.00$1.00","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5.5,"cached_input_per_m":0.55,"output_per_m":27.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 5 $5.50 $27.50 $2.75 $13.75 $6.875 $11.00 $0.55","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $5.00, output $25.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":"Claude Opus 5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5 | $5 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | $25 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"claude-opus-5","maker":"Anthropic","provider_model_id":"anthropic/claude-opus-5","tier":"standard","input_per_m":5,"cached_input_per_m":null,"output_per_m":25,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-opus-5","checked":"2026-11-14","quote":"$5.00 in $25.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$5.00$25.00$6.25$10.00$0.50","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":"claude-opus-5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Opus 5 Input $5.00 … Output $25.00 … Cache Hit $0.50","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":2.75,"cached_input_per_m":null,"output_per_m":13.75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 5 $5.50 $27.50 $2.75 $13.75 $6.875 $11.00 $0.55","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":"Claude Opus 5","tier":"batch","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":12.5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5 | $2.50 / MTok | $12.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":"claude-opus-5","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Opus 5 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.25","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":"Claude Opus 5","tier":"fast","input_per_m":10,"cached_input_per_m":null,"output_per_m":50,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5 / Claude Opus 4.8 | $10 USD / MTok | $50 USD / MTok |","notes":"Fast mode. Prompt caching multipliers apply on top; not available with the Batch API. Anthropic says fast mode is in research preview for Claude Opus 5."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-5","name":"Claude Opus 5","maker":"Anthropic","provider_model_id":null,"tier":"fast","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Fast Mode All prompts$10.00$50.00$12.50$20.00$1.00","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":4.4,"cached_input_per_m":0.22,"output_per_m":22,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Opus 5.5 $4.40 $22.00 N/A N/A $5.50 $8.80 $0.22","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $4.00, output $20.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":"Claude Opus 5.5","tier":"standard","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5.5 | $4 / MTok | $5 / MTok | $8 / MTok | $0.20 / MTok | $20 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-opus-5.5","name":"claude-opus-5-5","maker":"Anthropic","provider_model_id":"anthropic/claude-opus-5-5","tier":"standard","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-opus-5-5","checked":"2026-11-14","quote":"$4.00 in $20.00 out $0.20 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 5.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$4.00$20.00$5.00$8.00$0.20","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":"claude-opus-5.5","tier":"standard","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Opus 5.5 Input $4.00 … Output $20.00 … Cache Hit $0.20","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately. The batch input price on the page (2.50) is not half the standard input price (4.00); recorded as published."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":"anthropic/claude-opus-5-5","tier":"standard","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`anthropic/claude-opus-5-5` | 4.00 | 20.00 | 0.20","notes":"Third-party model resold through the Perplexity Agent API."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":"Claude Opus 5.5","tier":"batch","input_per_m":2,"cached_input_per_m":null,"output_per_m":10,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5.5 | $2 / MTok | $10 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":"claude-opus-5.5","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.1,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Opus 5.5 Batch Input $2.50 … Batch Output $12.50 … Batch Cache Hit $0.10","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately. The batch input price on the page (2.50) is not half the standard input price (4.00); recorded as published."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":"Claude Opus 5.5","tier":"fast","input_per_m":8,"cached_input_per_m":null,"output_per_m":40,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Opus 5.5 | $8 USD / MTok | $40 USD / MTok |","notes":"Fast mode. Prompt caching multipliers apply on top; not available with the Batch API."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-opus-5.5","name":"Claude Opus 5.5","maker":"Anthropic","provider_model_id":null,"tier":"fast","input_per_m":8,"cached_input_per_m":0.4,"output_per_m":40,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Opus 5.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Fast Mode All prompts$8.00$40.00$10.00$16.00$0.40","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4","name":"Claude Sonnet 4","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4 $3.00 $15.00 $1.50 $7.50 $3.75 N/A $0.30","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4","name":"Claude Sonnet 4","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4 $3.00 $15.00 $1.50 $7.50 $3.75 N/A $0.30","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3.3,"cached_input_per_m":0.33,"output_per_m":16.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4.5 $3.30 $16.50 $1.65 $8.25 $4.125 $6.60 $0.33","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $3.00, output $15.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":"Claude Sonnet 4.5","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 4.5 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard ≤ 200K tokens$3.00$15.00$3.75$6.00$0.30","notes":"Prompts ≤ 200K tokens; > 200K tokens: input $6.00, output $22.50."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":"claude-sonnet-4.5","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Sonnet 4.5 Input $3.00 … Output $15.00 … Cache Hit $0.30","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.65,"cached_input_per_m":null,"output_per_m":8.25,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4.5 $3.30 $16.50 $1.65 $8.25 $4.125 $6.60 $0.33","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":"Claude Sonnet 4.5","tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 4.5 | $1.50 / MTok | $7.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.5","name":"Claude Sonnet 4.5","maker":"Anthropic","provider_model_id":"claude-sonnet-4.5","tier":"batch","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Sonnet 4.5 Batch Input $1.50 … Batch Output $7.50 … Batch Cache Hit $0.15","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3.3,"cached_input_per_m":0.33,"output_per_m":16.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4.6 $3.30 $16.50 $1.65 $8.25 $4.125 $6.60 $0.33","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $3.00, output $15.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":"Claude Sonnet 4.6","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 4.6 | $3 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | $15 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.6","name":"claude-sonnet-4-6","maker":"Anthropic","provider_model_id":"anthropic/claude-sonnet-4-6","tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-sonnet-4-6","checked":"2026-11-14","quote":"$3.00 in $15.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4.6 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$3.00$15.00$3.75$6.00$0.30","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":"claude-sonnet-4.6","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Sonnet 4.6 Input $3.00 … Output $15.00 … Cache Hit $0.30","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":null,"tier":"batch","input_per_m":1.65,"cached_input_per_m":null,"output_per_m":8.25,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 4.6 $3.30 $16.50 $1.65 $8.25 $4.125 $6.60 $0.33","notes":"Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":"Claude Sonnet 4.6","tier":"batch","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 4.6 | $1.50 / MTok | $7.50 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-4.6","name":"Claude Sonnet 4.6","maker":"Anthropic","provider_model_id":"claude-sonnet-4.6","tier":"batch","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Sonnet 4.6 Batch Input $1.50 … Batch Output $7.50 … Batch Cache Hit $0.15","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5","name":"Claude Sonnet 5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":2.2,"cached_input_per_m":0.22,"output_per_m":11,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 5 $2.20 $11.00 N/A N/A $2.75 $4.40 $0.22","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $2.00, output $10.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-5","name":"Claude Sonnet 5","maker":"Anthropic","provider_model_id":"Claude Sonnet 5","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 5 | $2 / MTok | $2.50 / MTok | $4 / MTok | $0.20 / MTok | $10 / MTok |","notes":"Anthropic says the launch price of 2 input / 10 output is now the standard price; the planned September 1, 2026 increase will not occur."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5","name":"claude-sonnet-5","maker":"Anthropic","provider_model_id":"anthropic/claude-sonnet-5","tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-sonnet-5","checked":"2026-11-14","quote":"$3.00 in $15.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5","name":"Claude Sonnet 5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$2.00$10.00$2.50$4.00$0.20","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5","name":"Claude Sonnet 5","maker":"Anthropic","provider_model_id":"claude-sonnet-5","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Sonnet 5 Input $2.00 … Output $10.00 … Cache Hit $0.20","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-5","name":"Claude Sonnet 5","maker":"Anthropic","provider_model_id":"Claude Sonnet 5","tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 5 | $1 / MTok | $5 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5","name":"Claude Sonnet 5","maker":"Anthropic","provider_model_id":"claude-sonnet-5","tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Claude Sonnet 5 Batch Input $1.00 … Batch Output $5.00","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":2.2,"cached_input_per_m":0.11,"output_per_m":11,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 5.5 $2.20 $11.00 N/A N/A $2.75 $4.40 $0.11","notes":"Geo / in-region (US) on-demand price for us-east-1 from the \"Geo and In-region Cross-region Inference\" table. Global cross-region inference is cheaper: input $2.00, output $10.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":"Claude Sonnet 5.5","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 5.5 | $2 / MTok | $2.50 / MTok | $4 / MTok | $0.10 / MTok | $10 / MTok |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5.5","name":"claude-sonnet-5-5","maker":"Anthropic","provider_model_id":"anthropic/claude-sonnet-5-5","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":10,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/anthropic/claude-sonnet-5-5","checked":"2026-11-14","quote":"$2.00 in $10.00 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Claude Sonnet 5.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$2.00$10.00$2.50$4.00$0.20","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":"claude-sonnet-5.5","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Sonnet 5.5 Input $2.00 … Output $10.00 … Cache Hit $0.10","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":"anthropic/claude-sonnet-5-5","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`anthropic/claude-sonnet-5-5` | 2.00 | 10.00 | 0.10","notes":"Third-party model resold through the Perplexity Agent API."},{"provider":"anthropic","provider_name":"Anthropic","provider_kind":"maker","maker_api":true,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":"Claude Sonnet 5.5","tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":5,"context":1000000,"precision":null,"source_url":"https://platform.claude.com/docs/en/about-claude/pricing","checked":"2026-11-14","quote":"| Claude Sonnet 5.5 | $1 / MTok | $5 / MTok |","notes":"Message Batches API."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"claude-sonnet-5.5","name":"Claude Sonnet 5.5","maker":"Anthropic","provider_model_id":"claude-sonnet-5.5","tier":"batch","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Sonnet 5.5 Batch Input $1.00 … Batch Output $5.00 … Batch Cache Hit $0.05","notes":"Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"codestral-2","name":"Codestral 2","maker":"Mistral AI","provider_model_id":"codestral-2","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.9,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Codestral 2 Input $0.30 … Output $0.90","notes":""},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"codestral-2508","name":"Codestral 2508","maker":"Mistral AI","provider_model_id":"codestral-2508","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":0.9,"context":131072,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Codestral ↗\t$0.3\t$0.03\t$0.9","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"codestral-2508","name":"Codestral 2508","maker":"Mistral AI","provider_model_id":"codestral-2508","tier":"batch","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.45,"context":131072,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Codestral ↗\t$0.15\t$0.015\t$0.45 (Batch tab, \"Batch (-50%)\")","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"codestral-2508","name":"Codestral 2508","maker":"Mistral AI","provider_model_id":"codestral-2508","tier":"priority","input_per_m":0.525,"cached_input_per_m":0.0525,"output_per_m":1.575,"context":131072,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Codestral ↗\t$0.525\t$0.0525\t$1.575 (Priority tab, \"Priority (+75%)\")","notes":"Context from the docs model card."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"command","name":"Command","maker":"Cohere","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Command $1.00 $2.00 [NA:opt]","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"command-a","name":"Cohere Command A","maker":"Cohere","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/","checked":"2026-11-14","quote":"Cohere Command A Global Input: $2.50/1M Tokens | Output: $10/1M Tokens","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"command-a-plus","name":"Cohere Command A Plus","maker":"Cohere","provider_model_id":null,"tier":"standard","input_per_m":0.8,"cached_input_per_m":null,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/","checked":"2026-11-14","quote":"Cohere Command A Plus Global Input: $0.80/1M Tokens | Output: $3.20/1M Tokens","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"cohere","provider_name":"Cohere","provider_kind":"maker","maker_api":true,"model":"command-a-plus","name":"Command A+","maker":"Cohere","provider_model_id":"command-a-plus-05-2026","tier":"standard","input_per_m":0,"cached_input_per_m":null,"output_per_m":0,"context":null,"precision":null,"source_url":"https://cohere.com/pricing","checked":"2026-11-14","quote":"Command A+ ... API key $0 / Free","notes":"Cohere lists API-key access to Command A+ as free (and the weights as a free Apache 2.0 download). Price shown under the \"Generative models\" tab, rendered with Playwright. API model ID from docs.cohere.com/docs/models (context 128k there)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"command-light","name":"Command-Light","maker":"Cohere","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Command-Light $0.30 $0.60 [NA:opt]","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"command-r","name":"Command R","maker":"Cohere","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Command R $0.50 $1.50 N/A","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cohere","provider_name":"Cohere","provider_kind":"maker","maker_api":true,"model":"command-r","name":"Command R","maker":"Cohere","provider_model_id":"command-r-08-2024","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":128000,"precision":null,"source_url":"https://cohere.com/pricing","checked":"2026-11-14","quote":"Command R ... Input $0.15 / 1M tokens Output $0.60 / 1M tokens 128K token context window","notes":"The pricing card says only \"Command R\"; command-r-08-2024 is the live Command R model in Cohere's model list (command-r-03-2024 is deprecated)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"command-r-plus","name":"Command R+","maker":"Cohere","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Command R+ $3.00 $15.00 N/A","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cohere","provider_name":"Cohere","provider_kind":"maker","maker_api":true,"model":"command-r-plus-08-2024","name":"Command R+ (08-2024)","maker":"Cohere","provider_model_id":"command-r-plus-08-2024","tier":"standard","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":10,"context":null,"precision":null,"source_url":"https://cohere.com/pricing","checked":"2026-11-14","quote":"Command R+ 08-2024 pricing is $2.50/1M tokens for input and $10.00/1M tokens for output","notes":"Listed in the pricing FAQ under legacy models, \"For existing customers\". Still marked Live in Cohere's model list."},{"provider":"cohere","provider_name":"Cohere","provider_kind":"maker","maker_api":true,"model":"command-r7b-12-2024","name":"Command R7B (12-2024)","maker":"Cohere","provider_model_id":"command-r7b-12-2024","tier":"standard","input_per_m":0.0375,"cached_input_per_m":null,"output_per_m":0.15,"context":128000,"precision":null,"source_url":"https://cohere.com/pricing","checked":"2026-11-14","quote":"Command R7B ... Input $0.0375 / 1M tokens Output $0.15 / 1M tokens 128K token context window","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"cydonia-24b-v4.1","name":"Cydonia 24B v4.1","maker":"TheDrummer","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.15,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Cydonia 24B v4.1 $0.30 $0.50 $0.15","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-chat","name":"DeepSeek V3","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.14,"cached_input_per_m":null,"output_per_m":4.56,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek V3 Global $1.14 N/A $4.56","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-chat","name":"DeepSeek-V3","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3","tier":"standard","input_per_m":0.32,"cached_input_per_m":null,"output_per_m":0.89,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V3","checked":"2026-11-14","quote":"$0.32 in $0.89 out / 1M tokens","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-chat","name":"DeepSeek-V3","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1,"context":163840,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V3 164K $0.25 $1.0","notes":"Context shown as 164K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-chat","name":"DeepSeek-V3","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3","tier":"flex","input_per_m":0.256,"cached_input_per_m":null,"output_per_m":0.712,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V3","checked":"2026-11-14","quote":"Flex (0.8×) $0.256 $0.712","notes":"Flex service tier (0.8× standard)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3-0324","name":"DeepSeek V3 0324","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.14,"cached_input_per_m":null,"output_per_m":4.56,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek V3 0324 Global $1.14 N/A $4.56","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3-0324","name":"DeepSeek-V3-0324","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3-0324","tier":"standard","input_per_m":0.385,"cached_input_per_m":null,"output_per_m":1.625,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V3-0324","checked":"2026-11-15","quote":"PRICING: INPUT $0.385 / OUTPUT $1.625","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3-0324","name":"DeepSeek V3 0324","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3-0324","tier":"standard","input_per_m":0.29,"cached_input_per_m":0.11,"output_per_m":1.14,"context":128000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v3-0324/54540344-cd74-40e8-ade4-c84048307645","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.29 Output $1.14 Cache Read $0.11 Cache Write -","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek-V3.1","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.23,"cached_input_per_m":null,"output_per_m":4.94,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek-V3.1 $1.23 N/A $4.94","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"Deepseek V3.1","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.2,"output_per_m":1.5,"context":161000,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Deepseek V3.1 $0.50 $1.50 $0.20","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek-V3.1","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.13,"output_per_m":0.95,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V3.1","checked":"2026-11-14","quote":"$0.25 in $0.95 out $0.13 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek-V3.1","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1","tier":"standard","input_per_m":0.285,"cached_input_per_m":null,"output_per_m":1,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V3.1","checked":"2026-11-15","quote":"PRICING: INPUT $0.285 / OUTPUT $1","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek V3.1","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1","tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":1,"context":163840,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v3-1/9dfb44f6-d52d-4793-a504-98b6ab95531c","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.27 Output $1.00","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek V3.1","maker":"DeepSeek","provider_model_id":"deepseek-v3.1","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.06,"output_per_m":1.7,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.1 Input $0.60 … Output $1.70 … Cache Hit $0.06","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek-V3.1","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":1,"context":163840,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.1 164K $0.27 $1.0","notes":"Context shown as 164K."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek V3.1","maker":"DeepSeek","provider_model_id":"deepseek-v3.1","tier":"batch","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.85,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.1 Batch Input $0.30 … Batch Output $0.85","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-chat-v3.1","name":"DeepSeek-V3.1","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1","tier":"flex","input_per_m":0.2,"cached_input_per_m":0.104,"output_per_m":0.76,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V3.1","checked":"2026-11-14","quote":"Flex (0.8×) $0.20 $0.76 $0.104","notes":"Flex service tier (0.8× standard)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-prover-v2-671b","name":"DeepSeek Prover V2 671B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-Prover-V2-671B","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":2.18,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-deepseek-prover-v2-671b/57bc0854-4e0b-435b-a316-28519301723c","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.50 Output $2.18","notes":"No cache-read price published."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"deepseek-r1","name":"DeepSeek-R1","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.35,"cached_input_per_m":null,"output_per_m":5.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"DeepSeek-R1 $1.35 $5.40","notes":"Standard tier. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-r1","name":"DeepSeek R1","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.35,"cached_input_per_m":null,"output_per_m":5.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek R1 Global $1.35 N/A $5.40","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1","name":"DeepSeek R1","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":2.18,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-r1/56f9685a-99a9-4e9e-9e03-1b7de29fc973","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.50 Output $2.18","notes":"No cache-read price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-r1","name":"DeepSeek-R1","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":2.18,"context":163840,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-15","quote":"DeepSeek-R1 164K $0.5 $2.18","notes":"Context shown as 164K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"DeepSeek-R1-0528","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-0528","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.35,"output_per_m":2.15,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-R1-0528","checked":"2026-11-14","quote":"$0.50 in $2.15 out $0.35 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"DeepSeek-R1-0528","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-0528","tier":"standard","input_per_m":0.385,"cached_input_per_m":null,"output_per_m":1.625,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-R1-0528","checked":"2026-11-15","quote":"PRICING: INPUT $0.385 / OUTPUT $1.625","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"deepseek-ai/DeepSeek-R1-0528","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-0528","tier":"standard","input_per_m":0.57,"cached_input_per_m":0.23,"output_per_m":2.29,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-ai-deepseek-r1-0528/19a10465-f028-46cd-bd6f-91921c886699","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.57 Output $2.29 Cache Read $0.23 Cache Write -","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"DeepSeek R1 0528","maker":"DeepSeek","provider_model_id":"deepseek-r1-0528","tier":"standard","input_per_m":1.35,"cached_input_per_m":null,"output_per_m":5.4,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-R1 (0528) Input $1.35 … Output $5.40","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"DeepSeek R1 0528","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-r1-0528","tier":"standard","input_per_m":0.7,"cached_input_per_m":0.35,"output_per_m":2.5,"context":163840,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek R1 0528 160K $0.7 /Mt · Cache Read $0.35 /Mt $2.5 /Mt","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"DeepSeek R1 0528","maker":"DeepSeek","provider_model_id":"deepseek-r1-0528","tier":"batch","input_per_m":0.675,"cached_input_per_m":null,"output_per_m":2.7,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-R1 (0528) Batch Input $0.675 … Batch Output $2.70","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-r1-0528","name":"DeepSeek-R1-0528","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-0528","tier":"flex","input_per_m":0.4,"cached_input_per_m":0.28,"output_per_m":1.72,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-R1-0528","checked":"2026-11-14","quote":"Flex (0.8×) $0.40 $1.72 $0.28","notes":"Flex service tier (0.8× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-llama-70b","name":"DeepSeek-R1-Distill-Llama-70B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","tier":"standard","input_per_m":2.6,"cached_input_per_m":0.52,"output_per_m":3,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","checked":"2026-11-15","quote":"PRICING: INPUT $2.6 / CACHED $0.52 / OUTPUT $3","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":0.75,"context":131072,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/deepseek-r1-distill-llama-70b/c271c9b8-621b-4f5d-ab1c-7725506bb2c5","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.25 Output $0.75","notes":"No cache-read price published."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-llama-8b","name":"DeepSeek-R1-Distill-Llama-8B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.028,"output_per_m":0.32,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-8B","checked":"2026-11-15","quote":"PRICING: INPUT $0.2 / CACHED $0.028 / OUTPUT $0.32","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-llama-8b","name":"DeepSeek R1 Distill Llama 8B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.39,"context":131072,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/deepseek-r1-distill-llama-8b/97926200-2bd6-45d4-9c3f-a2c6b4c0e8bf","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.14 Output $0.39","notes":"No cache-read price published."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-14b","name":"DeepSeek-R1-Distill-Qwen-14B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","tier":"standard","input_per_m":0.431,"cached_input_per_m":0.0862,"output_per_m":1.12,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","checked":"2026-11-15","quote":"PRICING: INPUT $0.431 / CACHED $0.0862 / OUTPUT $1.12","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-14b","name":"DeepSeek R1 Distill Qwen 14B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.2,"context":131072,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/deepseek-r1-distill-qwen-14b/daa868d8-5e41-4f11-b14b-b130ffeac43e","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.20 Output $0.20","notes":"No cache-read price published."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-32b","name":"DeepSeek R1 Distill Qwen 32B","maker":"DeepSeek","provider_model_id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","tier":"standard","input_per_m":0.497,"cached_input_per_m":null,"output_per_m":4.881,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b $0.497 per M input tokens $4.881 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-32b","name":"DeepSeek-R1-Distill-Qwen-32B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","tier":"standard","input_per_m":2.72,"cached_input_per_m":null,"output_per_m":4.8,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","checked":"2026-11-15","quote":"PRICING: INPUT $2.72 / OUTPUT $4.8","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-32b","name":"DeepSeek R1 Distill Qwen 32B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":0.9,"context":131072,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/deepseek-r1-distill-qwen-32b/215bfbc7-5ccb-40fa-af53-1c75e1554b1d","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.50 Output $0.90","notes":"No cache-read price published."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-7b","name":"DeepSeek-R1-Distill-Qwen-7B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","tier":"standard","input_per_m":0.68,"cached_input_per_m":0.136,"output_per_m":0.8,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","checked":"2026-11-15","quote":"PRICING: INPUT $0.68 / CACHED $0.136 / OUTPUT $0.8","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-r1-distill-qwen-7b","name":"DeepSeek R1 Distill Qwen 7B","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.2,"context":131072,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/deepseek-r1-distill-qwen-7b/64e7dbd9-739a-4e6e-a9e1-c4abf4a79d83","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.10 Output $0.20","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-r1-turbo","name":"DeepSeek R1 Turbo","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-r1-turbo","tier":"standard","input_per_m":0.7,"cached_input_per_m":null,"output_per_m":2.5,"context":64000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek R1 Turbo 63K $0.7 /Mt $2.5 /Mt","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v3.1-terminus","name":"DeepSeek-V3.1-Terminus","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","tier":"standard","input_per_m":0.285,"cached_input_per_m":null,"output_per_m":1,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V3.1-Terminus","checked":"2026-11-15","quote":"PRICING: INPUT $0.285 / OUTPUT $1","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v3.1-terminus","name":"DeepSeek-V3.1-Terminus","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.1-Terminus","tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":1,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v3-1-terminus/07fcd6dc-f952-4550-bffa-9d793f93893a","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.27 Output $1.00","notes":"No cache-read price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v3.1-terminus","name":"DeepSeek-V3.1-Terminus","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":1,"context":163840,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.1-Terminus 164K $0.27 $1.0","notes":"Context shown as 164K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek v3.2","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.62,"cached_input_per_m":null,"output_per_m":1.85,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"DeepSeek v3.2 $ 0.62 $ 1.85","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek V3.2","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.58,"cached_input_per_m":null,"output_per_m":1.68,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek V3.2 Global $0.58 N/A $1.68","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":"deepseek-v3.2","tier":"standard","input_per_m":0.28,"cached_input_per_m":0.028,"output_per_m":0.42,"context":131072,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"DeepSeek-V3.2\tDeepSeek-V3.2\tInference Service\tInput\t0.28\t$/M tokens Cache Hit\t0.028\t$/M tokens Output\t0.42\t$/M tokens","notes":""},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2-TEE","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":1,"context":131072,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"DeepSeek-V3.2 deepseek-ai/DeepSeek-V3.2-TEE $0.10 per 1M tokens $1.00 per 1M tokens $1.00 per 1M tokens 131K","notes":"Runs on confidential TEE compute."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2","tier":"standard","input_per_m":0.26,"cached_input_per_m":0.13,"output_per_m":0.38,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V3.2","checked":"2026-11-14","quote":"$0.26 in $0.38 out $0.13 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek V3.2","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":0.15,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"DeepSeek V3.2 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.50$1.60$0.15","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2","tier":"standard","input_per_m":0.264,"cached_input_per_m":0.06,"output_per_m":0.41,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V3.2","checked":"2026-11-15","quote":"PRICING: INPUT $0.264 / CACHED $0.06 / OUTPUT $0.41","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"deepseek-ai/DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2","tier":"standard","input_per_m":0.2088,"cached_input_per_m":0.0216,"output_per_m":0.3096,"context":163840,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-ai-deepseek-v3-2/8d65e8ed-986d-45c2-b417-95ba8dce6605","checked":"2026-11-15","quote":"Price (per 1M tokens) 28% off Input $0.2088 $0.29 Output $0.3096 $0.43 Cache Read $0.0216 $0.03 Cache Write -","notes":"Promotional price, 28% off list (list 0.29 in / 0.43 out / 0.03 cached)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek V3.2","maker":"DeepSeek","provider_model_id":"deepseek-v3.2","tier":"standard","input_per_m":0.56,"cached_input_per_m":0.056,"output_per_m":1.68,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.2 Input $0.56 … Output $1.68 … Cache Hit $0.056","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.27,"cached_input_per_m":0.135,"output_per_m":0.42,"context":163840,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.2 164K $0.27 $0.135 $0.42","notes":"Context shown as 164K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek V3.2","maker":"DeepSeek","provider_model_id":"deepseek-v3.2","tier":"standard","input_per_m":0.33,"cached_input_per_m":0.16,"output_per_m":0.48,"context":160000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V3.2 | `deepseek-v3.2` | $0.33 | $0.48 | $0.16 | — | Private |","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek V3.2","maker":"DeepSeek","provider_model_id":"deepseek-v3.2","tier":"batch","input_per_m":0.28,"cached_input_per_m":null,"output_per_m":0.84,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.2 Batch Input $0.28 … Batch Output $0.84","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2","name":"DeepSeek-V3.2","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2","tier":"flex","input_per_m":0.208,"cached_input_per_m":0.104,"output_per_m":0.304,"context":163840,"precision":"fp4","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V3.2","checked":"2026-11-14","quote":"Flex (0.8×) $0.208 $0.304 $0.104","notes":"Flex service tier (0.8× standard)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2-exp","name":"DeepSeek-V3.2-Exp","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2-Exp","tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":0.41,"context":163840,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v3-2-exp/3ae3ce59-178d-4f38-893b-d94315804579","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.27 Output $0.41","notes":"No cache-read price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2-exp","name":"DeepSeek-V3.2-Exp","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":0.41,"context":163840,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V3.2-Exp 164K $0.27 $0.41","notes":"Context shown as 164K."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V3.2-Speciale","tier":"standard","input_per_m":0.28,"cached_input_per_m":null,"output_per_m":0.4,"context":163840,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v3-2-speciale/069c106c-3275-49d0-9369-3827414a6cc1","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.28 Output $0.40","notes":"No cache-read price published."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4 Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.19,"cached_input_per_m":0.028,"output_per_m":0.51,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek-V4 Flash Global $0.19 $0.028 $0.51","notes":"Foundry Models serverless (pay-as-you-go), Global deployment. Also sold as \"FW DeepSeek V4 Flash\" (Fireworks on Azure, Data Zone) at a lower price: input $0.15, cached $0.03, output $0.31."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.028,"output_per_m":0.28,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"DeepSeek-V4-Flash\tDeepSeek-V4-Flash\tInference Service\tInput\t0.14\t$/M tokens Cache Hit\t0.028\t$/M tokens Output\t0.28\t$/M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash","tier":"standard","input_per_m":0.09,"cached_input_per_m":0.018,"output_per_m":0.18,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash","checked":"2026-11-14","quote":"$0.09 in $0.18 out $0.018 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.03,"output_per_m":0.28,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V4-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.14 / CACHED $0.03 / OUTPUT $0.28","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash","tier":"standard","input_per_m":0.091,"cached_input_per_m":0.0182,"output_per_m":0.182,"context":1048575,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-flash/16e9ccd2-84e0-43b4-9d9a-5cb31b3341a2","checked":"2026-11-15","quote":"Price (per 1M tokens) 35% off Input $0.091 $0.14 Output $0.182 $0.28 Cache Read $0.0182 $0.028 Cache Write -","notes":"Promotional price, 35% off list (list 0.14 in / 0.28 out / 0.028 cached)."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek V4 Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":0.07,"output_per_m":0.28,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"DeepSeek V4 Flash $0.14 $0.28 $0.07","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.13,"cached_input_per_m":0.028,"output_per_m":0.28,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V4-Flash 1049K $0.13 $0.028 $0.28","notes":"Context shown as 1049K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash","tier":"standard","input_per_m":0.138,"cached_input_per_m":0.028,"output_per_m":0.275,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4 Flash 0423 | `deepseek-v4-flash` | $0.138 | $0.275 | $0.028 | — | Private |","notes":"Listed as \"DeepSeek V4 Flash 0423\"."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash","tier":"flex","input_per_m":0.072,"cached_input_per_m":0.0144,"output_per_m":0.144,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash","checked":"2026-11-14","quote":"Flex (0.8×) $0.072 $0.144 $0.0144","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash","tier":"priority","input_per_m":0.135,"cached_input_per_m":0.027,"output_per_m":0.27,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash","checked":"2026-11-14","quote":"Priority (1.5×) $0.135 $0.27 $0.027","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash-0731","tier":"standard","input_per_m":0.44,"cached_input_per_m":0.044,"output_per_m":1.32,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"deepseek-v4-flash-0731 context caching discount International Busy hours: $0.44 Idle hours: $0.22 Busy hours: $1.32 Idle hours: $0.66","notes":"International (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.22 input, 0.66 output. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 10% of the input price in the International (Singapore) scope."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.44,"cached_input_per_m":0.014,"output_per_m":1.32,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek V4 Flash 0731 Global $0.44 $0.014 $1.32","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash-0731","tier":"standard","input_per_m":0.44,"cached_input_per_m":0.044,"output_per_m":1.32,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"DeepSeek-V4-Flash\tDeepSeek-V4-Flash-0731\tInference Service\tInput\t0.44\t$/M tokens Cache Hit\t0.044\t$/M tokens Output\t1.32\t$/M tokens","notes":""},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"standard","input_per_m":0.13,"cached_input_per_m":0.028,"output_per_m":0.26,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"DeepSeek-V4-Flash-0731 $0.13 $0.028 $0.26","notes":"Context from the model library page (https://www.baseten.co/library/deepseek-v4-flash-0731/), stated as 1M."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","tier":"standard","input_per_m":0.44,"cached_input_per_m":0.044,"output_per_m":1.32,"context":1048576,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash-0731-TEE $0.044 per 1M tokens $0.44 per 1M tokens $1.32 per 1M tokens 1.0M","notes":"Runs on confidential TEE compute."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":"@cf/deepseek-ai/deepseek-v4-flash-0731","tier":"standard","input_per_m":0.44,"cached_input_per_m":0.014,"output_per_m":1.32,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/deepseek-ai/deepseek-v4-flash-0731 $0.440 per M input tokens $0.014 per M cached input tokens $1.320 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"standard","input_per_m":0.13,"cached_input_per_m":0.05,"output_per_m":0.27,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"DeepSeek V4-Flash-0731 $0.13 $0.27 $0.05","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.015,"output_per_m":0.18,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-0731","checked":"2026-11-14","quote":"$0.06 in $0.18 out $0.015 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":0.028,"output_per_m":0.28,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"DeepSeek V4 Flash 0731 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.14$0.28$0.028","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.03,"output_per_m":0.28,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V4-Flash-0731","checked":"2026-11-15","quote":"PRICING: INPUT $0.14 / CACHED $0.03 / OUTPUT $0.28","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"standard","input_per_m":0.286,"cached_input_per_m":0.0091,"output_per_m":0.858,"context":1048575,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-flash-0731/5709fa67-fe41-482b-8197-45282e7ea42a","checked":"2026-11-15","quote":"Price (per 1M tokens) 35% off Input $0.286 $0.44 Output $0.858 $1.32 Cache Read $0.0091 $0.014 Cache Write -","notes":"Promotional price, 35% off list (list 0.44 in / 1.32 out / 0.014 cached)."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash-0731","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.015,"output_per_m":0.18,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"DeepSeek V4 Flash 0731 deepseek-v4-flash-0731 DeepSeek · 1M context · Text $0.06 $0.18 $0.015","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-v4-flash-0731","tier":"standard","input_per_m":0.44,"cached_input_per_m":0.028,"output_per_m":1.32,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4 Flash 0731 1M $0.44 /Mt · Cache Read $0.028 /Mt $1.32 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.22,"cached_input_per_m":0.014,"output_per_m":0.66,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V4-Flash-0731 1049K $0.22 $0.014 $0.66","notes":"Context shown as 1049K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash-0731","tier":"standard","input_per_m":0.13,"cached_input_per_m":0.028,"output_per_m":0.26,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4 Flash 0731 | `deepseek-v4-flash-0731` | $0.13 | $0.26 | $0.028 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"flex","input_per_m":0.048,"cached_input_per_m":0.012,"output_per_m":0.144,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-0731","checked":"2026-11-14","quote":"Flex (0.8×) $0.048 $0.144 $0.012","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek-V4-Flash-0731","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-0731","tier":"priority","input_per_m":0.09,"cached_input_per_m":0.0225,"output_per_m":0.27,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-0731","checked":"2026-11-14","quote":"Priority (1.5×) $0.09 $0.27 $0.0225","notes":"Priority service tier (1.5× standard)."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731 Fast","maker":"DeepSeek","provider_model_id":"deepseek-v4-flash-0731-fast","tier":"fast","input_per_m":0.35,"cached_input_per_m":0.0875,"output_per_m":0.7,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4 Flash 0731 Fast | `deepseek-v4-flash-0731-fast` | $0.35 | $0.70 | $0.0875 | — | Private |","notes":"Fast variant, model ID deepseek-v4-flash-0731-fast."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-vision-exp","name":"DeepSeek-V4-Flash-Vision-Exp","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","tier":"standard","input_per_m":0.2156,"cached_input_per_m":0.00686,"output_per_m":0.6468,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","checked":"2026-11-14","quote":"$0.216 in $0.647 out $0.007 cached / 1M tokens","notes":"Promotional price, 51% off list (list 0.44 in / 1.32 out)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-vision-exp","name":"DeepSeek-V4-Flash-Vision-Exp","maker":"DeepSeek","provider_model_id":"deepseek-ai/deepseek-v4-flash-vision-exp","tier":"standard","input_per_m":0.44,"cached_input_per_m":0.014,"output_per_m":1.32,"context":1048575,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-flash-vision-exp/1c0d2152-07d5-4856-8930-824013203309","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.44 Output $1.32 Cache Read $0.014 Cache Write -","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-vision-exp","name":"DeepSeek-V4-Flash-Vision-Exp","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.44,"cached_input_per_m":0.028,"output_per_m":1.32,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V4-Flash-Vision-Exp 1049K $0.44 $0.028 $1.32","notes":"Context shown as 1049K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-vision-exp","name":"DeepSeek-V4-Flash-Vision-Exp","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","tier":"flex","input_per_m":0.1725,"cached_input_per_m":0.0055,"output_per_m":0.5174,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","checked":"2026-11-14","quote":"Flex (0.8×) $0.1725 $0.5174 $0.0055","notes":"Flex service tier (0.8× standard). Promotional price, 51% off list (list 0.44 in / 1.32 out)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-flash-vision-exp","name":"DeepSeek-V4-Flash-Vision-Exp","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","tier":"priority","input_per_m":0.3234,"cached_input_per_m":0.0103,"output_per_m":0.9702,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","checked":"2026-11-14","quote":"Priority (1.5×) $0.3234 $0.9702 $0.0103","notes":"Priority service tier (1.5× standard). Promotional price, 51% off list (list 0.44 in / 1.32 out)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek V4 Pro","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro","tier":"standard","input_per_m":2.4,"cached_input_per_m":null,"output_per_m":4.8,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"deepseek-v4-pro context caching discount International $2.400 $4.800","notes":"International (Singapore) deployment. Flat price, no peak/off-peak split. Alibaba lists it separately from deepseek-v4-pro-0813; which snapshot it serves is not stated. Cached price not listed (see the Model Studio console)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4 Pro","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.74,"cached_input_per_m":0.145,"output_per_m":3.48,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek-V4 Pro Global $1.74 $0.145 $3.48","notes":"Foundry Models serverless (pay-as-you-go), Global deployment. Also sold as \"FW DeepSeek V4 Pro\" (Fireworks on Azure, Data Zone): input $1.925, cached $0.165, output $3.828."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro","tier":"standard","input_per_m":1.69,"cached_input_per_m":0.14,"output_per_m":3.38,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"DeepSeek-V4-Pro\tDeepSeek-V4-Pro\tInference Service\tInput\t1.69\t$/M tokens Cache Hit\t0.14\t$/M tokens Output\t3.38\t$/M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro","tier":"standard","input_per_m":1.3,"cached_input_per_m":0.1,"output_per_m":2.6,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro","checked":"2026-11-14","quote":"$1.30 in $2.60 out $0.10 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek V4 Pro","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.74,"cached_input_per_m":0.348,"output_per_m":3.48,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"DeepSeek V4 Pro — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.74$3.48$0.348","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro","tier":"standard","input_per_m":1.6,"cached_input_per_m":0.2,"output_per_m":3.2,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V4-Pro","checked":"2026-11-15","quote":"PRICING: INPUT $1.6 / CACHED $0.2 / OUTPUT $3.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro","tier":"standard","input_per_m":0.957,"cached_input_per_m":0.07975,"output_per_m":1.914,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-pro/cbecb2f4-480e-4d25-b3d7-8f38ea0c3913","checked":"2026-11-15","quote":"Price (per 1M tokens) 45% off Input $0.957 $1.74 Output $1.914 $3.48 Cache Read $0.07975 $0.145 Cache Write -","notes":"Promotional price, 45% off list (list 1.74 in / 3.48 out / 0.145 cached)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek V4 Pro","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-v4-pro","tier":"standard","input_per_m":1.6,"cached_input_per_m":0.135,"output_per_m":3.2,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4 Pro 1M $1.6 /Mt · Cache Read $0.135 /Mt $3.2 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek V4 Pro","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.74,"cached_input_per_m":0.1,"output_per_m":3.48,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"DeepSeek V4 Pro $1.74 $3.48 $0.10","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.50162,"cached_input_per_m":0.135,"output_per_m":3.135,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V4-Pro 1049K $1.50162 $0.135 $3.135","notes":"Context shown as 1049K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek V4 Pro","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro","tier":"standard","input_per_m":1.65,"cached_input_per_m":0.33,"output_per_m":3.301,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4 Pro | `deepseek-v4-pro` | $1.65 | $3.301 | $0.33 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro","tier":"flex","input_per_m":1.04,"cached_input_per_m":0.08,"output_per_m":2.08,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro","checked":"2026-11-14","quote":"Flex (0.8×) $1.04 $2.08 $0.08","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro","tier":"priority","input_per_m":1.95,"cached_input_per_m":0.15,"output_per_m":3.9,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro","checked":"2026-11-14","quote":"Priority (1.5×) $1.95 $3.90 $0.15","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro-0813","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.132,"output_per_m":3.96,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"deepseek-v4-pro-0813 context caching discount International Busy hours: $1.32 Idle hours: $0.66 Busy hours: $3.96 Idle hours: $1.98","notes":"International (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.66 input, 1.98 output. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 10% of the input price in the International (Singapore) scope."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro-0813","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.132,"output_per_m":3.96,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"DeepSeek-V4-Pro-0813\tDeepSeek-V4-Pro-0813\tInference Service\tInput\t1.32\t$/M tokens Cache Hit\t0.132\t$/M tokens Output\t3.96\t$/M tokens","notes":""},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.132,"output_per_m":3.96,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"DeepSeek V4 Pro 0813 $1.32 $0.132 $3.96","notes":"Context from the model library page (https://www.baseten.co/library/deepseek-v4-pro-0813/), stated as 1M."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"standard","input_per_m":0.85,"cached_input_per_m":0.15,"output_per_m":2.65,"context":1000000,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"DeepSeek-V4-Pro-0813 deepseek-ai/DeepSeek-V4-Pro-0813 $0.15 per 1M tokens $0.85 per 1M tokens $2.65 per 1M tokens 1.0M","notes":""},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":"@cf/deepseek-ai/deepseek-v4-pro-0813","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.044,"output_per_m":3.96,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/deepseek-ai/deepseek-v4-pro-0813 $1.320 per M input tokens $0.044 per M cached input tokens $3.960 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"standard","input_per_m":1.31,"cached_input_per_m":0.044,"output_per_m":3.96,"context":1048576,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"DeepSeek V4-Pro-0813 $1.31 $3.96 $0.044","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"standard","input_per_m":1.3,"cached_input_per_m":0.1,"output_per_m":2.6,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro-0813","checked":"2026-11-14","quote":"$1.30 in $2.60 out $0.10 cached / 1M tokens","notes":""},{"provider":"deepseek","provider_name":"DeepSeek","provider_kind":"maker","maker_api":true,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.044,"output_per_m":3.96,"context":1000000,"precision":null,"source_url":"https://api-docs.deepseek.com/quick_start/pricing","checked":"2026-11-14","quote":"(CACHE HIT) OFF-PEAK $0.003 $0.022 PEAK $0.006 $0.044 1M INPUT TOKENS (CACHE MISS) OFF-PEAK $0.15 $0.66 PEAK $0.3 $1.32 1M OUTPUT TOKENS OFF-PEAK $0.6 $1.98 PEAK $1.2 $3.96","notes":"Peak-hour price (second price column of the quoted table). Off-peak is half: 0.66 input, 0.022 cached, 1.98 output. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak. API model name deepseek-v4-pro serves DeepSeek-V4-Pro-0813. Context 1M, max output 384K."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.32,"cached_input_per_m":0.044,"output_per_m":3.96,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"DeepSeek V4 Pro 0813 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.32$3.96$0.044","notes":"DigitalOcean-hosted."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"standard","input_per_m":1.056,"cached_input_per_m":0.0352,"output_per_m":3.168,"context":1048575,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-pro-0813/de6e71be-d065-49a7-b77c-53cec002d8b2","checked":"2026-11-15","quote":"Price (per 1M tokens) 20% off Input $1.056 $1.32 Output $3.168 $3.96 Cache Read $0.0352 $0.044 Cache Write -","notes":"Promotional price, 20% off list (list 1.32 in / 3.96 out / 0.044 cached)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-v4-pro-0813","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.044,"output_per_m":3.96,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4 Pro 0813 1M $1.32 /Mt · Cache Read $0.044 /Mt $3.96 /Mt","notes":""},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"perplexity/deepseek-v4-pro-0813","tier":"standard","input_per_m":1.32,"cached_input_per_m":0.044,"output_per_m":3.96,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`perplexity/deepseek-v4-pro-0813` | 1.32 | 3.96 | 0.044","notes":"Hosted by Perplexity (\"Perplexity-Hosted Models\"); tool calls billed separately."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.32,"cached_input_per_m":0.044,"output_per_m":3.96,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V4-Pro-0813 1049K $1.32 $0.044 $3.96","notes":"Context shown as 1049K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":1.32,"cached_input_per_m":0.13,"output_per_m":3.96,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4 Pro 0813 $1.32 $0.13 (cached) $3.96","notes":"US geo-pinned option: $1.65 in / $4.95 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","maker":"DeepSeek","provider_model_id":"deepseek-v4-pro-0813","tier":"standard","input_per_m":1.65,"cached_input_per_m":0.165,"output_per_m":4.95,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4 Pro 0813 | `deepseek-v4-pro-0813` | $1.65 | $4.95 | $0.165 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"flex","input_per_m":1.04,"cached_input_per_m":0.08,"output_per_m":2.08,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro-0813","checked":"2026-11-14","quote":"Flex (0.8×) $1.04 $2.08 $0.08","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4-pro-0813","name":"DeepSeek-V4-Pro-0813","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4-Pro-0813","tier":"priority","input_per_m":1.95,"cached_input_per_m":0.15,"output_per_m":3.9,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4-Pro-0813","checked":"2026-11-14","quote":"Priority (1.5×) $1.95 $3.90 $0.15","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek-v4.1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"deepseek-v4.1-flash context caching discount International Busy hours: $0.3 Idle hours: $0.15 Busy hours: $1.2 Idle hours: $0.6","notes":"International (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.15 input, 0.6 output. Cached price from the Context Cache page: \"a fixed $0.003 per 1M tokens during off-peak hours and $0.006 per 1M tokens during peak hours\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash Global $0.30 $0.006 $1.20","notes":"Foundry Models serverless (pay-as-you-go), Global deployment. Also sold as \"FW DeepSeek V4.1 Flash\" (Fireworks on Azure, Global): input $0.375, cached $0.008, output $1.50."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.007,"output_per_m":1.2,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash $0.30 $0.007 $1.20","notes":"Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash/), stated as 1M."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"standard","input_per_m":0.13,"cached_input_per_m":0.002,"output_per_m":0.65,"context":1048576,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"DeepSeek V4.1-Flash $0.13 $0.65 $0.002","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.0042,"output_per_m":0.42,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash","checked":"2026-11-14","quote":"$0.14 in $0.42 out $0.004 cached / 1M tokens","notes":"Promotional price, 30% off list (list 0.2 in / 0.6 out)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.30$1.20$0.006","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V4.1-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.3 / CACHED $0.03 / OUTPUT $1.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"standard","input_per_m":0.18,"cached_input_per_m":0.0036,"output_per_m":0.72,"context":1048575,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-1-flash/0049392b-5a6b-4e94-acc0-e18b8e293aac","checked":"2026-11-15","quote":"Price (per 1M tokens) 40% off Input $0.18 $0.30 Output $0.72 $1.20 Cache Read $0.0036 $0.006 Cache Write -","notes":"Promotional price, 40% off list (list 0.3 in / 1.2 out / 0.006 cached)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek-v4.1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"DeepSeek-V4.1-Flash * Input $0.30 … Output $1.20 … Cache Hit $0.03","notes":"Google says it was free until October 16, 2026; this is the price after that date."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek-v4.1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash deepseek-v4.1-flash DeepSeek · 1M context · Text $0.30 $1.20 $0.006","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-v4.1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1M $0.3 /Mt · Cache Read $0.006 /Mt $1.2 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash $0.30 $1.20 $0.006","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.003,"output_per_m":0.6,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"DeepSeek-V4.1-Flash 1049K $0.15 $0.003 $0.6","notes":"Context shown as 1049K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash $0.30 $0.006 (cached) $1.20","notes":"US geo-pinned option: $0.375 in / $1.50 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.0075,"output_per_m":1.2,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4.1 Flash | `deepseek-v4-1-flash` | $0.30 | $1.20 | $0.0075 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"flex","input_per_m":0.112,"cached_input_per_m":0.0034,"output_per_m":0.336,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash","checked":"2026-11-14","quote":"Flex (0.8×) $0.112 $0.336 $0.0034","notes":"Flex service tier (0.8× standard). Promotional price, 30% off list (list 0.2 in / 0.6 out)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash","tier":"flex","input_per_m":0.21,"cached_input_per_m":0.0042,"output_per_m":0.84,"context":1048576,"precision":null,"source_url":"https://fireworks.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash Spot $0.0042 $0.21 $0.84","notes":"Fireworks \"Spot\" mode: 30% off Standard on best-effort capacity; throughput can drop to zero."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek-V4.1-Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"priority","input_per_m":0.21,"cached_input_per_m":0.0063,"output_per_m":0.63,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash","checked":"2026-11-14","quote":"Priority (1.5×) $0.21 $0.63 $0.0063","notes":"Priority service tier (1.5× standard). Promotional price, 30% off list (list 0.2 in / 0.6 out)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash","tier":"priority","input_per_m":0.375,"cached_input_per_m":0.0075,"output_per_m":1.5,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash | Priority $0.375 / $0.0075 / $1.50","notes":"Priority mode."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash Fast","maker":"DeepSeek","provider_model_id":null,"tier":"fast","input_per_m":0.6,"cached_input_per_m":0.014,"output_per_m":2.4,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash Fast $0.60 $0.014 $2.40","notes":"Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash-fast/), stated as 1M."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"deepseek-v4.1-flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"deepseek-v4.1-flash-1017 context caching discount International Busy hours: $0.3 Idle hours: $0.15 Busy hours: $1.2 Idle hours: $0.6","notes":"International (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.15 input, 0.6 output. Cached price from the Context Cache page: 0.006 peak, 0.003 off-peak."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-v4.1-flash-1017","tier":"standard","input_per_m":0.28,"cached_input_per_m":0.006,"output_per_m":1.13,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"DeepSeek-V4.1-Flash\tDeepSeek-V4.1-Flash-1017\tInference Service\tInput\t0.28\t$/M tokens Cache Hit\t0.006\t$/M tokens Output\t1.13\t$/M tokens","notes":""},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.007,"output_per_m":1.2,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 $0.30 $0.007 $1.20","notes":"Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash-1017/), stated as 1M."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":1000000,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"DeepSeek-V4.1-Flash-1017 deepseek-ai/DeepSeek-V4.1-Flash-1017 $0.03 per 1M tokens $0.30 per 1M tokens $1.20 per 1M tokens 1.0M","notes":""},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"@cf/deepseek-ai/deepseek-v4.1-flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/deepseek-ai/deepseek-v4.1-flash-1017 $0.300 per M input tokens $0.006 per M cached input tokens $1.200 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash","tier":"standard","input_per_m":0.29,"cached_input_per_m":0.007,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"DeepSeek V4.1 Flash text, image $0.29 $1.20 $0.007","notes":"Crusoe's docs link this model ID to the DeepSeek-V4.1-Flash-1017 weights."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","tier":"standard","input_per_m":0.098,"cached_input_per_m":0.00294,"output_per_m":0.294,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017","checked":"2026-11-14","quote":"$0.098 in $0.294 out $0.003 cached / 1M tokens","notes":"Promotional price, 51% off list (list 0.2 in / 0.6 out)."},{"provider":"deepseek","provider_name":"DeepSeek","provider_kind":"maker","maker_api":true,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"deepseek-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":1000000,"precision":null,"source_url":"https://api-docs.deepseek.com/quick_start/pricing","checked":"2026-11-14","quote":"(CACHE HIT) OFF-PEAK $0.003 $0.022 PEAK $0.006 $0.044 1M INPUT TOKENS (CACHE MISS) OFF-PEAK $0.15 $0.66 PEAK $0.3 $1.32 1M OUTPUT TOKENS OFF-PEAK $0.6 $1.98 PEAK $1.2 $3.96","notes":"Peak-hour price (first price column of the quoted table). Off-peak is half: 0.15 input, 0.003 cached, 0.6 output. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak. API model name deepseek-flash serves DeepSeek-V4.1-Flash-1017; the legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp are retired and served by this model at the Flash price. Context 1M, max output 384K."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.30$1.20$0.006","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","tier":"standard","input_per_m":0.225,"cached_input_per_m":0.006,"output_per_m":0.9,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/deepseek-ai/DeepSeek-V4.1-Flash-1017","checked":"2026-11-15","quote":"PRICING: INPUT $0.225 / CACHED $0.006 / OUTPUT $0.9","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-ai/deepseek-v4.1-flash-1017","tier":"standard","input_per_m":0.18,"cached_input_per_m":0.0036,"output_per_m":0.72,"context":1048575,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/deepseek-v4-1-flash-1017/9aa6bb1e-170b-41ec-929d-1532858f9390","checked":"2026-11-15","quote":"Price (per 1M tokens) 40% off Input $0.18 $0.30 Output $0.72 $1.20 Cache Read $0.0036 $0.006 Cache Write -","notes":"Promotional price, 40% off list (list 0.3 in / 1.2 out / 0.006 cached)."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.007,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 ↗\t$0.3\t$0.007\t$1.2","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Mistral lists it as Public Preview. Context from the docs model card."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"deepseek/deepseek-v4.1-flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 1M $0.3 /Mt · Cache Read $0.006 /Mt $1.2 /Mt","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.006,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 $0.30 $0.006 (cached) $1.20","notes":"US geo-pinned option: $0.375 in / $1.50 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek v4.1 Flash (1017)","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-1017","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.0075,"output_per_m":1.2,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek v4.1 Flash (1017) | `deepseek-v4-1-flash-1017` | $0.30 | $1.20 | $0.0075 | — | Private |","notes":""},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-1017","tier":"batch","input_per_m":0.15,"cached_input_per_m":0.0035,"output_per_m":0.6,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 ↗\t$0.15\t$0.0035\t$0.6 (Batch tab, \"Batch (-50%)\")","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Mistral lists it as Public Preview. Context from the docs model card."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","tier":"flex","input_per_m":0.0784,"cached_input_per_m":0.0024,"output_per_m":0.2352,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017","checked":"2026-11-14","quote":"Flex (0.8×) $0.0784 $0.2352 $0.0024","notes":"Flex service tier (0.8× standard). Promotional price, 51% off list (list 0.2 in / 0.6 out)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash-1017","tier":"flex","input_per_m":0.21,"cached_input_per_m":0.0042,"output_per_m":0.84,"context":1048576,"precision":null,"source_url":"https://fireworks.ai/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 Spot $0.0042 $0.21 $0.84","notes":"Fireworks \"Spot\" mode: 30% off Standard on best-effort capacity; throughput can drop to zero."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek-V4.1-Flash-1017","maker":"DeepSeek","provider_model_id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","tier":"priority","input_per_m":0.147,"cached_input_per_m":0.0044,"output_per_m":0.441,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017","checked":"2026-11-14","quote":"Priority (1.5×) $0.147 $0.441 $0.0044","notes":"Priority service tier (1.5× standard). Promotional price, 51% off list (list 0.2 in / 0.6 out)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash-1017","tier":"priority","input_per_m":0.375,"cached_input_per_m":0.0075,"output_per_m":1.5,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 | Priority $0.375 / $0.0075 / $1.50","notes":"Priority mode."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-1017","tier":"priority","input_per_m":0.525,"cached_input_per_m":0.01225,"output_per_m":2.1,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"DeepSeek V4.1 Flash 1017 ↗\t$0.525\t$0.01225\t$2.1 (Priority tab, \"Priority (+75%)\")","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Mistral lists it as Public Preview. Context from the docs model card."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017 Fast","maker":"DeepSeek","provider_model_id":null,"tier":"fast","input_per_m":0.6,"cached_input_per_m":0.014,"output_per_m":2.4,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 Fast $0.60 $0.014 $2.40","notes":"Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash-1017-fast/), stated as 1M."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","maker":"DeepSeek","provider_model_id":"accounts/fireworks/models/deepseek-v4p1-flash-1017","tier":"fast","input_per_m":2.4,"cached_input_per_m":0.048,"output_per_m":9.6,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) | $2.40 / $0.048 / $9.60 | —","notes":"Ultra-fast (Preview) mode."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017 Ultrafast","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-1017-ultrafast","tier":"ultrafast","input_per_m":3,"cached_input_per_m":0.06,"output_per_m":12,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4.1 Flash 1017 Ultrafast | `deepseek-v4-1-flash-1017-ultrafast` | $3.00 | $12.00 | $0.06 | — | Private |","notes":"Ultrafast variant, model ID deepseek-v4-1-flash-1017-ultrafast."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017-abliterated","name":"DeepSeek V4.1 Flash 1017 Abliterated","maker":"DeepSeek","provider_model_id":"e2ee-deepseek-v4-1-flash-1017-abliterated","tier":"standard","input_per_m":0.375,"cached_input_per_m":0.0075,"output_per_m":1.5,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4.1 Flash 1017 Abliterated | `e2ee-deepseek-v4-1-flash-1017-abliterated` | $0.375 | $1.50 | $0.0075 | — | E2EE |","notes":"Abliterated (uncensored) variant of DeepSeek V4.1 Flash 1017, end-to-end encrypted (E2EE) tier."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-1017-uncensored","name":"DeepSeek V4.1 Flash 1017 Uncensored","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-1017-uncensored","tier":"standard","input_per_m":0.33,"cached_input_per_m":0.00825,"output_per_m":1.32,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4.1 Flash 1017 Uncensored | `deepseek-v4-1-flash-1017-uncensored` | $0.33 | $1.32 | $0.00825 | — | Private |","notes":"Uncensored (abliterated) variant of DeepSeek V4.1 Flash 1017."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"deepseek-v4.1-flash-uncensored","name":"DeepSeek V4.1 Flash Uncensored","maker":"DeepSeek","provider_model_id":"deepseek-v4-1-flash-uncensored","tier":"standard","input_per_m":0.33,"cached_input_per_m":0.00825,"output_per_m":1.32,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| DeepSeek V4.1 Flash Uncensored | `deepseek-v4-1-flash-uncensored` | $0.33 | $1.32 | $0.00825 | — | Private |","notes":"Uncensored (abliterated) variant of DeepSeek V4.1 Flash."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"devstral-2512","name":"Devstral 2 123B","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Devstral 2 123B $ 0.40 $ 2.00","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"ember-1","name":"Ember-1","maker":"Fireworks AI","provider_model_id":"accounts/fireworks/models/ember-1","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Ember-1 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"ember-1","name":"Ember-1","maker":"Fireworks AI","provider_model_id":"accounts/fireworks/models/ember-1","tier":"priority","input_per_m":3.75,"cached_input_per_m":0.375,"output_per_m":18.75,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Ember-1 | Priority $3.75 / $0.375 / $18.75","notes":"Priority mode."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":true,"model":"ernie-5.1","name":"ERNIE 5.1","maker":"Baidu","provider_model_id":null,"tier":"standard","input_per_m":0.56,"cached_input_per_m":null,"output_per_m":2.53,"context":null,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"ERNIE 5.1\tERNIE 5.1\tInference Service\tInput (Input<=32k)\t0.56\t$/M tokens Output (Input<=32k)\t2.53\t$/M tokens","notes":"Lowest prompt tier (input ≤32k). 32k–128k input: 0.84 input, 3.1 output."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":true,"model":"ernie-5.5-flash-preview","name":"ERNIE-5.5-Flash-Preview","maker":"Baidu","provider_model_id":"ernie-5.5-flash-preview","tier":"standard","input_per_m":0.28,"cached_input_per_m":0.028,"output_per_m":1.13,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"ERNIE-5.5-Flash\tERNIE-5.5-Flash-Preview\tInference Service\tInput\t0.28\t$/M tokens Cache Hit\t0.028\t$/M tokens Output\t1.13\t$/M tokens","notes":""},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":true,"model":"ernie-light-dt-1.0-intl","name":"ERNIE-Light-DT-1.0","maker":"Baidu","provider_model_id":"ernie-light-dt-1.0","tier":"standard","input_per_m":1.13,"cached_input_per_m":0.113,"output_per_m":3.94,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"ERNIE-Light-DT\tERNIE-Light-DT-1.0\tInference Service\tInput\t1.13\t$/M tokens Cache Hit\t0.113\t$/M tokens Output\t3.94\t$/M tokens","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.0-flash","name":"Gemini 2.0 Flash","maker":"Google","provider_model_id":"gemini-2.0-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.0 Flash Input text $0.15 … Output text $0.60","notes":"No cached price listed for this model."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.0-flash","name":"Gemini 2.0 Flash","maker":"Google","provider_model_id":"gemini-2.0-flash","tier":"batch","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.0 Flash Input text $0.075 … Output text $0.30","notes":"No cached price listed for this model."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.0-flash-lite","name":"Gemini 2.0 Flash Lite","maker":"Google","provider_model_id":"gemini-2.0-flash-lite","tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.0 Flash Lite Input tokens $0.075 … Output text tokens $0.30","notes":"No cached price listed for this model."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.0-flash-lite","name":"Gemini 2.0 Flash Lite","maker":"Google","provider_model_id":"gemini-2.0-flash-lite","tier":"batch","input_per_m":0.0375,"cached_input_per_m":null,"output_per_m":0.15,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.0 Flash Lite Input tokens $0.0375 … Output text tokens $0.15","notes":"No cached price listed for this model."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash","name":"gemini-2.5-flash","maker":"Google","provider_model_id":"google/gemini-2.5-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":2.5,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/google/gemini-2.5-flash","checked":"2026-11-14","quote":"$0.30 in $2.50 out / 1M tokens","notes":""},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash","checked":"2026-11-14","quote":"Gemini 2.5 Flash Standard: Input price $0.30 (text / image / video) $1.00 (audio) … Output price (including thinking tokens) $2.50 … Context caching price $0.03 (text / image / video) $0.1 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Deprecated: from December 1, 2026 requests route to gemini-3.5-flash-lite and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Flash Input (text, image, video) $0.30 … Text output (response and reasoning) $2.50 … cached $0.03","notes":"Text, image and video input; audio input costs more."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"batch","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash","checked":"2026-11-14","quote":"Gemini 2.5 Flash Batch: Input price $0.15 (text / image / video) $0.50 (audio) … Output price (including thinking tokens) $1.25 … Context caching price $0.03 (text / image / video) $0.1 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Deprecated: from December 1, 2026 requests route to gemini-3.5-flash-lite and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"batch","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Flash Input (text, image, video) $0.15 … Text output (response and reasoning) $1.25","notes":"Text, image and video input; audio input costs more. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"flex","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash","checked":"2026-11-14","quote":"Gemini 2.5 Flash Flex: Input price $0.15 (text / image / video) $0.50 (audio) … Output price (including thinking tokens) $1.25 … Context caching price $0.03 (text / image / video) $0.1 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Deprecated: from December 1, 2026 requests route to gemini-3.5-flash-lite and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"priority","input_per_m":0.54,"cached_input_per_m":0.054,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash","checked":"2026-11-14","quote":"Gemini 2.5 Flash Priority: Input price $0.54 (text / image / video) $1.80 (audio) … Output price (including thinking tokens) $4.50 … Context caching price $0.054 (text / image / video) $0.18 (audio) $1.80 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Deprecated: from December 1, 2026 requests route to gemini-3.5-flash-lite and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash","name":"Gemini 2.5 Flash","maker":"Google","provider_model_id":"gemini-2.5-flash","tier":"priority","input_per_m":0.54,"cached_input_per_m":0.054,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Flash Input (text, image, video) $0.54 … Text output (response and reasoning) $4.50 … cached $0.054","notes":"Text, image and video input; audio input costs more."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash-lite","checked":"2026-11-14","quote":"Gemini 2.5 Flash-Lite Standard: Input price $0.10 (text / image / video) $0.30 (audio) … Output price (including thinking tokens) $0.40 … Context caching price $0.01 (text / image / video) $0.03 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Flash Lite Input (text, image, video) $0.10 … Text output (response and reasoning) $0.40 … cached $0.01","notes":"Text, image and video input; audio input costs more."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"batch","input_per_m":0.05,"cached_input_per_m":0.01,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash-lite","checked":"2026-11-14","quote":"Gemini 2.5 Flash-Lite Batch: Input price $0.05 (text / image / video) $0.15 (audio) … Output price (including thinking tokens) $0.20 … Context caching price $0.01 (text / image / video) $0.03 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"batch","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Flash Lite Input (text, image, video) $0.05 … Text output (response and reasoning) $0.20","notes":"Text, image and video input; audio input costs more. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"flex","input_per_m":0.05,"cached_input_per_m":0.01,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash-lite","checked":"2026-11-14","quote":"Gemini 2.5 Flash-Lite Flex: Input price $0.05 (text / image / video) $0.15 (audio) … Output price (including thinking tokens) $0.20 … Context caching price $0.01 (text / image / video) $0.03 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"priority","input_per_m":0.18,"cached_input_per_m":0.018,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-flash-lite","checked":"2026-11-14","quote":"Gemini 2.5 Flash-Lite Priority: Input price $0.18 (text / image / video) $0.54 (audio) … Output price (including thinking tokens) $0.72 … Context caching price $0.018 (text / image / video) $0.054 (audio) $1.80 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-2.5-flash-lite","tier":"priority","input_per_m":0.18,"cached_input_per_m":0.018,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Flash Lite Input (text, image, video) $0.18 … Text output (response and reasoning) $0.72 … cached $0.018","notes":"Text, image and video input; audio input costs more."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemini-2.5-pro","name":"gemini-2.5-pro","maker":"Google","provider_model_id":"google/gemini-2.5-pro","tier":"standard","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":10,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/google/gemini-2.5-pro","checked":"2026-11-14","quote":"$1.25 in $10.00 out / 1M tokens","notes":""},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":10,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-pro","checked":"2026-11-14","quote":"Gemini 2.5 Pro Standard: Input price $1.25, prompts <= 200k tokens $2.50, prompts > 200k tokens … Output price (including thinking tokens) $10.00, prompts <= 200k tokens $15.00, prompts > 200k … Context caching price $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":10,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Pro Input (text, image, video, audio) $1.25 … Text output (response and reasoning) $10.00 … cached $0.125","notes":"Prompts up to 200K tokens; longer prompts bill at higher rates."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"batch","input_per_m":0.625,"cached_input_per_m":0.125,"output_per_m":5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-pro","checked":"2026-11-14","quote":"Gemini 2.5 Pro Batch: Input price $0.625, prompts <= 200k tokens $1.25, prompts > 200k tokens … Output price (including thinking tokens) $5.00, prompts <= 200k tokens $7.50, prompts > 200k … Context caching price $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"batch","input_per_m":0.625,"cached_input_per_m":null,"output_per_m":5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Pro Input (text, image, video, audio) $0.625 … Text output (response and reasoning) $5.00","notes":"Prompts up to 200K tokens; longer prompts bill at higher rates. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"flex","input_per_m":0.625,"cached_input_per_m":0.125,"output_per_m":5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-pro","checked":"2026-11-14","quote":"Gemini 2.5 Pro Flex: Input price $0.625, prompts <= 200k tokens $1.25, prompts > 200k tokens … Output price (including thinking tokens) $5.00, prompts <= 200k tokens $7.50, prompts > 200k … Context caching price $0.125, prompts <= 200k tokens $0.25, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"priority","input_per_m":2.25,"cached_input_per_m":0.225,"output_per_m":18,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-2.5-pro","checked":"2026-11-14","quote":"Gemini 2.5 Pro Priority: Input price $2.25, prompts <= 200k tokens $4.50, prompts > 200k tokens … Output price (including thinking tokens) $18.00, prompts <= 200k tokens $27.00, prompts > 200k … Context caching price $0.225, prompts <= 200k tokens $0.45, prompts > 200k $8.10 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens. Deprecated: from December 1, 2026 requests route to gemini-3.8-flash and bill at its rates. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-2.5-pro","name":"Gemini 2.5 Pro","maker":"Google","provider_model_id":"gemini-2.5-pro","tier":"priority","input_per_m":2.25,"cached_input_per_m":0.225,"output_per_m":18,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 2.5 Pro Input (text, image, video, audio) $2.25 … Text output (response and reasoning) $18.00 … cached $0.225","notes":"Prompts up to 200K tokens; longer prompts bill at higher rates."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","maker":"Google","provider_model_id":"gemini-3-flash-preview","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.05,"output_per_m":3,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3-flash-preview","checked":"2026-11-14","quote":"Gemini 3 Flash Preview Standard: Input price $0.50 (text / image / video) $1.00 (audio) … Output price (including thinking tokens) $3.00 … Context caching price $0.05 (text / image / video) $0.10 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","maker":"Google","provider_model_id":"gemini-3-flash-preview","tier":"batch","input_per_m":0.25,"cached_input_per_m":0.05,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3-flash-preview","checked":"2026-11-14","quote":"Gemini 3 Flash Preview Batch: Input price $0.25 (text / image / video) $0.50 (audio) … Output price (including thinking tokens) $1.50 … Context caching price *Same as Standard* $0.05 (text / image / video) $0.10 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","maker":"Google","provider_model_id":"gemini-3-flash-preview","tier":"flex","input_per_m":0.25,"cached_input_per_m":0.05,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3-flash-preview","checked":"2026-11-14","quote":"Gemini 3 Flash Preview Flex: Input price $0.25 (text / image / video) $0.50 (audio) … Output price (including thinking tokens) $1.50 … Context caching price *Same as Standard* $0.05 (text / image / video) $0.10 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","maker":"Google","provider_model_id":"gemini-3-flash-preview","tier":"priority","input_per_m":0.9,"cached_input_per_m":0.09,"output_per_m":5.4,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3-flash-preview","checked":"2026-11-14","quote":"Gemini 3 Flash Preview Priority: Input price $0.90 (text / image / video) $1.80 (audio) … Output price (including thinking tokens) $5.40 … Context caching price $0.09 (text / image / video) $0.18 (audio) $1.80 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemini-3.1-flash-lite","name":"gemini-3.1-flash-lite","maker":"Google","provider_model_id":"google/gemini-3.1-flash-lite","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1.5,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/google/gemini-3.1-flash-lite","checked":"2026-11-14","quote":"$0.25 in $1.50 out / 1M tokens","notes":""},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.025,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-flash-lite","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite Standard: Input price $0.25 (text / image / video) $0.50 (audio) … Output price (including thinking tokens) $1.50 … Context caching price $0.025 (text / image / video) $0.05 (audio) $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.025,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite [Global] Input (text, image, video) $0.25 … Text output (response and reasoning) $1.50 … cached $0.025","notes":"Global endpoint; text, image and video input (audio input costs more)."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"batch","input_per_m":0.125,"cached_input_per_m":0.0125,"output_per_m":0.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-flash-lite","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite Batch: Input price $0.125 (text / image / video) $0.25 (audio) … Output price (including thinking tokens) $0.75 … Context caching price $0.0125 (text / image / video) $0.025 (audio) $0.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"batch","input_per_m":0.125,"cached_input_per_m":0.0125,"output_per_m":0.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite [Global] Input (text, image, video) $0.125 … Text output (response and reasoning) $0.75 … cached $0.0125","notes":"Global endpoint; text, image and video input (audio input costs more). Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"flex","input_per_m":0.125,"cached_input_per_m":0.0125,"output_per_m":0.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-flash-lite","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite Flex: Input price $0.125 (text / image / video) $0.25 (audio) … Output price (including thinking tokens) $0.75 … Context caching price $0.0125 (text / image / video) $0.025 (audio) $0.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"priority","input_per_m":0.45,"cached_input_per_m":0.045,"output_per_m":2.7,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-flash-lite","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite Priority: Input price $0.45 (text / image / video) $0.90 (audio) … Output price (including thinking tokens) $2.70 … Context caching price $0.045 (text / image / video) $0.09 (audio) $1.80 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Text, image and video input; audio input costs more. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.1-flash-lite","tier":"priority","input_per_m":0.45,"cached_input_per_m":0.045,"output_per_m":2.7,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.1 Flash-Lite [Global] Input (text, image, video) $0.45 … Text output (response and reasoning) $2.70 … cached $0.045","notes":"Global endpoint; text, image and video input (audio input costs more)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash-Lite","maker":"Google","provider_model_id":"google/gemini-3.1-flash-lite-preview","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.025,"output_per_m":1.5,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-1-flash-lite/a0ef7494-9dca-4c58-a764-f0dd8798884e","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.25 Output $1.50 Cache Read $0.025 Cache Write $0.08333","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemini-3.1-pro","name":"gemini-3.1-pro","maker":"Google","provider_model_id":"google/gemini-3.1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":12,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/google/gemini-3.1-pro","checked":"2026-11-14","quote":"$2.00 in $12.00 out / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.1-pro-preview","name":"Gemini-3.1-Pro","maker":"Google","provider_model_id":"google/gemini-3.1-pro-preview","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":12,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-1-pro/4078d9c2-e385-424c-af4b-2753b94d92ff","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $2.00 Output $12.00","notes":"No cache-read price published."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":12,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-pro-preview","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview Standard: Input price $2.00, prompts <= 200k tokens $4.00, prompts > 200k tokens … Output price (including thinking tokens) $12.00, prompts <= 200k tokens $18.00, prompts > 200k … Context caching price $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens; longer prompts bill at higher rates. Same price for gemini-3.1-pro-preview-customtools. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":12,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview [Global] Input (text, image, video, audio) $2.00 … Text output (response and reasoning) $12.00 … cached $0.20","notes":"Global endpoint, prompts up to 200K tokens; longer prompts bill at higher rates."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"batch","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":6,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-pro-preview","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview Batch: Input price $1.00, prompts <= 200k tokens $2.00, prompts > 200k tokens … Output price (including thinking tokens) $6.00, prompts <= 200k tokens $9.00, prompts > 200k … Context caching price *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens; longer prompts bill at higher rates. Same price for gemini-3.1-pro-preview-customtools. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":6,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview [Global] Input (text, image, video, audio) $1.00 … Text output (response and reasoning) $6.00","notes":"Global endpoint, prompts up to 200K tokens; longer prompts bill at higher rates. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"flex","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":6,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-pro-preview","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview Flex: Input price $1.00, prompts <= 200k tokens $2.00, prompts > 200k tokens … Output price (including thinking tokens) $6.00, prompts <= 200k tokens $9.00, prompts > 200k … Context caching price *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens; longer prompts bill at higher rates. Same price for gemini-3.1-pro-preview-customtools. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"priority","input_per_m":3.6,"cached_input_per_m":0.36,"output_per_m":21.6,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.1-pro-preview","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview Priority: Input price $3.60, prompts <= 200k tokens $7.20, prompts > 200k tokens … Output price (including thinking tokens) $21.60, prompts <= 200k tokens $32.40, prompts > 200k … Context caching price $0.36, prompts <= 200k tokens $0.72, prompts > 200k $8.10 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Prompts up to 200K tokens; longer prompts bill at higher rates. Same price for gemini-3.1-pro-preview-customtools. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","maker":"Google","provider_model_id":"gemini-3.1-pro-preview","tier":"priority","input_per_m":3.6,"cached_input_per_m":0.36,"output_per_m":21.6,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.1 Pro Preview [Global] Input (text, image, video, audio) $3.60 … Text output (response and reasoning) $21.60 … cached $0.36","notes":"Global endpoint, prompts up to 200K tokens; longer prompts bill at higher rates."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash","name":"gemini-3.5-flash","maker":"Google","provider_model_id":"google/gemini-3.5-flash","tier":"standard","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":9,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/google/gemini-3.5-flash","checked":"2026-11-14","quote":"$1.50 in $9.00 out / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash","name":"Gemini 3.5 Flash","maker":"Google","provider_model_id":"google/gemini-3.5-flash","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":9,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-5-flash/88943704-646d-47f6-868c-408ed6f78e08","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.50 Output $9.00 Cache Read $0.15 Cache Write $0.08333","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash","name":"Gemini 3.5 Flash","maker":"Google","provider_model_id":"gemini-3.5-flash","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":9,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.5 Flash [Global] Input (text, image, video, audio) $1.50 … Text output (response and reasoning) $9.00 … cached $0.15","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash","name":"Gemini 3.5 Flash","maker":"Google","provider_model_id":"gemini-3.5-flash","tier":"batch","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.5 Flash [Global (Batch)] Input (text, image, video, audio) $0.75 … cached $0.075 … [Global] Text output (response and reasoning) $4.50","notes":"Global endpoint; same price for Flex."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash","name":"Gemini 3.5 Flash","maker":"Google","provider_model_id":"gemini-3.5-flash","tier":"priority","input_per_m":2.7,"cached_input_per_m":0.27,"output_per_m":16.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.5 Flash [Global] Input (text, image, video, audio) $2.70 … Text output (response and reasoning) $16.20 … cached $0.27","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"google/gemini-3.5-flash-lite","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":2.5,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-5-flash-lite/52de98de-cd00-40c8-a99a-5d07576e0b24","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.30 Output $2.50 Cache Read $0.03 Cache Write -","notes":""},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.5-flash-lite","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite Standard: Input price $0.30 (text / image / video / audio) … Output price (including thinking tokens) $2.50 … Context caching price $0.03 $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite [Global] Input (text, image, video, audio) $0.30 … Text output (response and reasoning) $2.50 … cached $0.03","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"batch","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.5-flash-lite","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite Batch: Input price $0.15 (text / image / video / audio) … Output price (including thinking tokens) $1.25 … Context caching price $0.015 $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"batch","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite [Global] Input (text, image, video, audio) $0.15 … Text output (response and reasoning) $1.25 … cached $0.015","notes":"Global endpoint; non-global regions cost 10% more. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"flex","input_per_m":0.15,"cached_input_per_m":0.02,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.5-flash-lite","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite Flex: Input price $0.15 (text / image / video / audio) … Output price (including thinking tokens) $1.25 … Context caching price $0.02 $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"priority","input_per_m":0.54,"cached_input_per_m":0.05,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.5-flash-lite","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite Priority: Input price $0.54 (text / image / video / audio) … Output price (including thinking tokens) $4.50 … Context caching price $0.05 $1.00 / 1,000,000 tokens per hour (storage price)","notes":"Paid tier. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","maker":"Google","provider_model_id":"gemini-3.5-flash-lite","tier":"priority","input_per_m":0.54,"cached_input_per_m":0.054,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.5 Flash-Lite [Global] Input (text, image, video, audio) $0.54 … Text output (response and reasoning) $4.50 … cached $0.054","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"google/gemini-3.6-flash","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":7.5,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-6-flash/86199128-2a04-4f63-9028-c4f238172811","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.50 Output $7.50 Cache Read $0.15 Cache Write -","notes":""},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.6-flash","checked":"2026-11-14","quote":"Gemini 3.6 Flash Standard: Input price $0.75 through December 31, 2026. $1.50 starting January 1, 2027. … Output price (including thinking tokens) $3.75 through December 31, 2026. $7.50 starting January 1, 2027. … Context caching price $0.075 through December 31, 2026. $0.15 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 tok","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 1.50 input / 7.50 output / 0.15 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.6 Flash *through December 31, 2026 [Global] Input (text, image, video, audio) $0.75 … Text output (response and reasoning) $3.75 … cached $0.075","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 1.5 input / 7.5 output per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"batch","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.6-flash","checked":"2026-11-14","quote":"Gemini 3.6 Flash Batch: Input price $0.375 through December 31, 2026. $0.75 starting January 1, 2027. … Output price (including thinking tokens) $1.875 through December 31, 2026. $3.75 starting January 1, 2027. … Context caching price $0.0375 through December 31, 2026. $0.075 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 to","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 0.75 input / 3.75 output / 0.075 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"batch","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.6 Flash *through December 31, 2026 [Global] Input (text, image, video, audio) $0.375 … Text output (response and reasoning) $1.875 … cached $0.0375","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 0.75 input / 3.75 output per 1M tokens. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"flex","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.6-flash","checked":"2026-11-14","quote":"Gemini 3.6 Flash Flex: Input price $0.375 through December 31, 2026. $0.75 starting January 1, 2027. … Output price (including thinking tokens) $1.875 through December 31, 2026. $3.75 starting January 1, 2027. … Context caching price $0.0375 through December 31, 2026. $0.075 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 tok","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 0.75 input / 3.75 output / 0.075 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"priority","input_per_m":1.35,"cached_input_per_m":0.135,"output_per_m":6.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.6-flash","checked":"2026-11-14","quote":"Gemini 3.6 Flash Priority: Input price $1.35 through December 31, 2026. $2.70 starting January 1, 2027. … Output price (including thinking tokens) $6.75 through December 31, 2026. $13.50 starting January 1, 2027. … Context caching price $0.135 through December 31, 2026. $0.27 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 to","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 2.70 input / 13.50 output / 0.27 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.6-flash","name":"Gemini 3.6 Flash","maker":"Google","provider_model_id":"gemini-3.6-flash","tier":"priority","input_per_m":1.35,"cached_input_per_m":0.135,"output_per_m":6.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.6 Flash *through December 31, 2026 [Global] Input (text, image, video, audio) $1.35 … Text output (response and reasoning) $6.75 … cached $0.135","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 2.7 input / 13.5 output per 1M tokens."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemini-3.7-flash","name":"gemini-3.7-flash","maker":"Google","provider_model_id":"google/gemini-3.7-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":null,"output_per_m":3.75,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/google/gemini-3.7-flash","checked":"2026-11-14","quote":"$0.75 in $3.75 out / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.7-flash","name":"Gemini 3.7 Flash","maker":"Google","provider_model_id":"google/gemini-3.7-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-7-flash/7e7e7f50-2a84-4ef6-809e-9db5d51bee96","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.75 Output $3.75 Cache Read $0.075 Cache Write -","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.7-flash","name":"Gemini 3.7 Flash","maker":"Google","provider_model_id":"gemini-3.7-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.7 Flash *through December 31, 2026 [Global] Input (text, image, video, audio) $0.75 … Text output (response and reasoning) $3.75 … cached $0.075","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 1.5 input / 7.5 output per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.7-flash","name":"Gemini 3.7 Flash","maker":"Google","provider_model_id":"gemini-3.7-flash","tier":"batch","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.7 Flash *through December 31, 2026 [Global] Input (text, image, video, audio) $0.375 … Text output (response and reasoning) $1.875 … cached $0.0375","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 0.75 input / 3.75 output per 1M tokens. Google lists one price for Flex and Batch."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.7-flash","name":"Gemini 3.7 Flash","maker":"Google","provider_model_id":"gemini-3.7-flash","tier":"priority","input_per_m":1.35,"cached_input_per_m":0.135,"output_per_m":6.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.7 Flash *through December 31, 2026 [Global] Input (text, image, video, audio) $1.35 … Text output (response and reasoning) $6.75 … cached $0.135","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 2.7 input / 13.5 output per 1M tokens."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"google/gemini-3.8-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-3-8-flash/e5aabab2-5ae8-4de1-875b-8aca0d92a833","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.75 Output $3.75 Cache Read $0.075 Cache Write -","notes":""},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.8-flash","checked":"2026-11-14","quote":"Gemini 3.8 Flash Standard: Input price $0.75 through December 31, 2026. $1.50 starting January 1, 2027. … Output price (including thinking tokens) $3.75 through December 31, 2026. $7.50 starting January 1, 2027. … Context caching price $0.075 through December 31, 2026. $0.15 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 tok","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 1.50 input / 7.50 output / 0.15 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.8 Flash*through December 31, 2026 [Global] Input (text, image, video, audio) $0.75 … Text output (response and reasoning) $3.75 … cached $0.075","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 1.5 input / 7.5 output per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"batch","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.8-flash","checked":"2026-11-14","quote":"Gemini 3.8 Flash Batch: Input price $0.375 through December 31, 2026. $0.75 starting January 1, 2027. … Output price (including thinking tokens) $1.875 through December 31, 2026. $3.75 starting January 1, 2027. … Context caching price $0.0375 through December 31, 2026. $0.075 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 to","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 0.75 input / 3.75 output / 0.075 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"batch","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.8 Flash*through December 31, 2026 [Global] Input (text, image, video, audio) $0.375 … Text output (response and reasoning) $1.875 … cached $0.0375","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 0.75 input / 3.75 output per 1M tokens. Google lists one price for Flex and Batch."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"flex","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.8-flash","checked":"2026-11-14","quote":"Gemini 3.8 Flash Flex: Input price $0.375 through December 31, 2026. $0.75 starting January 1, 2027. … Output price (including thinking tokens) $1.875 through December 31, 2026. $3.75 starting January 1, 2027. … Context caching price $0.0375 through December 31, 2026. $0.075 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 tok","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 0.75 input / 3.75 output / 0.075 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"priority","input_per_m":1.35,"cached_input_per_m":0.135,"output_per_m":6.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-3.8-flash","checked":"2026-11-14","quote":"Gemini 3.8 Flash Priority: Input price $1.35 through December 31, 2026. $2.70 starting January 1, 2027. … Output price (including thinking tokens) $6.75 through December 31, 2026. $13.50 starting January 1, 2027. … Context caching price $0.135 through December 31, 2026. $0.27 starting January 1, 2027. $0.50 / 1,000,000 tokens per hour (storage price) through December 31, 2026. $1.00 / 1,000,000 to","notes":"Paid tier. Promotional price; starting January 1, 2027 it rises to 2.70 input / 13.50 output / 0.27 cached per 1M tokens. Cache storage is billed separately per hour."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash","name":"Gemini 3.8 Flash","maker":"Google","provider_model_id":"gemini-3.8-flash","tier":"priority","input_per_m":1.35,"cached_input_per_m":0.135,"output_per_m":6.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.8 Flash*through December 31, 2026 [Global] Input (text, image, video, audio) $1.35 … Text output (response and reasoning) $6.75 … cached $0.135","notes":"Global endpoint; non-global regions cost 10% more. Promotional price (Google says it is given as 50% credits back on net spend) through December 31, 2026; from January 1, 2027 it is 2.7 input / 13.5 output per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash-cyber","name":"Gemini 3.8 Flash Cyber","maker":"Google","provider_model_id":"gemini-3.8-flash-cyber","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.8 Flash Cyber [Global] Input (text, image, video, audio) $1.50 … Text output (response and reasoning) $7.50 … cached $0.15","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash-cyber","name":"Gemini 3.8 Flash Cyber","maker":"Google","provider_model_id":"gemini-3.8-flash-cyber","tier":"batch","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.8 Flash Cyber [Global] Input (text, image, video, audio) $0.75 … Text output (response and reasoning) $3.75 … cached $0.075","notes":"Global endpoint; non-global regions cost 10% more. Google lists one price for Flex and Batch."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-3.8-flash-cyber","name":"Gemini 3.8 Flash Cyber","maker":"Google","provider_model_id":"gemini-3.8-flash-cyber","tier":"priority","input_per_m":2.7,"cached_input_per_m":0.27,"output_per_m":13.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 3.8 Flash Cyber [Global] Input (text, image, video, audio) $2.70 … Text output (response and reasoning) $13.50 … cached $0.27","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-4-argon","name":"Gemini-4-Argon","maker":"Google","provider_model_id":"google/gemini-4-argon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-4-argon/60b8a012-73ec-4c04-923d-8176ef91aa96","checked":"2026-11-15","quote":"Price (per 1M tokens) 50% off Input $2.00 $4.00 Output $10.00 $20.00 Cache Read $0.10 $0.20 Cache Write -","notes":"Promotional price, 50% off list (list 4 in / 20 out / 0.2 cached)."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-argon","checked":"2026-11-14","quote":"Gemini 4 Argon Standard: Input price $2.00 through November 30, 2026. $4.00 starting December 1, 2026. … Output price (including thinking tokens) $10.00 through November 30, 2026. $20.00 starting December 1, 2026. … Context caching price $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 4.00 input / 20.00 output / 0.20 cached per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Argon*through November 30, 2026 [Global] Input (text, image, video, audio) $2.00 … Text output (response and reasoning) $10.00 … cached $0.10","notes":"Global endpoint; non-global regions cost 10% more. Promotional price through November 30, 2026; from December 1, 2026 it is 4 input / 20 output per 1M tokens."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"google/gemini-4-argon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`google/gemini-4-argon` | 2.00 | 10.00 | 0.10","notes":"Third-party model resold through the Perplexity Agent API. Promotional: \"introductory pricing through November 30, 2026\"."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"batch","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-argon","checked":"2026-11-14","quote":"Gemini 4 Argon Batch: Input price $1.00 through November 30, 2026. $2.00 starting December 1, 2026. … Output price (including thinking tokens) $5.00 through November 30, 2026. $10.00 starting December 1, 2026. … Context caching price $0.05 through November 30, 2026. $0.10 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 2.00 input / 10.00 output / 0.10 cached per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"batch","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Argon*through November 30, 2026 [Global] Input (text, image, video, audio) $1.00 … Text output (response and reasoning) $5.00 … cached $0.05","notes":"Global endpoint; non-global regions cost 10% more. Promotional price through November 30, 2026; from December 1, 2026 it is 2 input / 10 output per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"flex","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-argon","checked":"2026-11-14","quote":"Gemini 4 Argon Flex: Input price $1.00 through November 30, 2026. $2.00 starting December 1, 2026. … Output price (including thinking tokens) $5.00 through November 30, 2026. $10.00 starting December 1, 2026. … Context caching price $0.05 through November 30, 2026. $0.10 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 2.00 input / 10.00 output / 0.10 cached per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"priority","input_per_m":3.6,"cached_input_per_m":0.18,"output_per_m":18,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-argon","checked":"2026-11-14","quote":"Gemini 4 Argon Priority: Input price $3.60 through November 30, 2026. $7.20 starting December 1, 2026. … Output price (including thinking tokens) $18.00 through November 30, 2026. $36.00 starting December 1, 2026. … Context caching price $0.18 through November 30, 2026. $0.36 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 7.20 input / 36.00 output / 0.36 cached per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-argon","name":"Gemini 4 Argon","maker":"Google","provider_model_id":"gemini-4-argon","tier":"priority","input_per_m":3.6,"cached_input_per_m":0.18,"output_per_m":18,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Argon*through November 30, 2026 [Global] Input (text, image, video, audio) $3.60 … Text output (response and reasoning) $18.00 … cached $0.18","notes":"Global endpoint; non-global regions cost 10% more. Promotional price through November 30, 2026; from December 1, 2026 it is 7.2 input / 36 output per 1M tokens."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemini-4-carbon","name":"Gemini-4-Carbon","maker":"Google","provider_model_id":"google/gemini-4-carbon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemini-4-carbon/72d79041-783b-4959-ae43-9f169e38b72b","checked":"2026-11-15","quote":"Price (per 1M tokens) 50% off Input $2.00 $4.00 Output $10.00 $20.00 Cache Read $0.10 $0.20 Cache Write -","notes":"Promotional price, 50% off list (list 4 in / 20 out / 0.2 cached)."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-carbon","checked":"2026-11-14","quote":"Gemini 4 Carbon Standard: Input price $2.00 through November 30, 2026. $4.00 starting December 1, 2026. … Output price (including thinking tokens) $10.00 through November 30, 2026. $20.00 starting December 1, 2026. … Context caching price $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 4.00 input / 20.00 output / 0.20 cached per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Carbon*through November 30, 2026 [Global] Input (text, image, video, audio) $2.00 … Text output (response and reasoning) $10.00 … cached $0.10","notes":"Global endpoint; non-global regions cost 10% more. Promotional price through November 30, 2026; from December 1, 2026 it is 4 input / 20 output per 1M tokens."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"google/gemini-4-carbon","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`google/gemini-4-carbon` | 2.00 | 10.00 | 0.10","notes":"Third-party model resold through the Perplexity Agent API. Promotional: \"introductory pricing through November 30, 2026\"."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"batch","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-carbon","checked":"2026-11-14","quote":"Gemini 4 Carbon Batch: Input price $1.00 through November 30, 2026. $2.00 starting December 1, 2026. … Output price (including thinking tokens) $5.00 through November 30, 2026. $10.00 starting December 1, 2026. … Context caching price $0.05 through November 30, 2026. $0.10 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 2.00 input / 10.00 output / 0.10 cached per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"batch","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Carbon*through November 30, 2026 [Global] Input (text, image, video, audio) $1.00 … Text output (response and reasoning) $5.00 … cached $0.05","notes":"Global endpoint; non-global regions cost 10% more. Promotional price through November 30, 2026; from December 1, 2026 it is 2 input / 10 output per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"flex","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-carbon","checked":"2026-11-14","quote":"Gemini 4 Carbon Flex: Input price $1.00 through November 30, 2026. $2.00 starting December 1, 2026. … Output price (including thinking tokens) $5.00 through November 30, 2026. $10.00 starting December 1, 2026. … Context caching price $0.05 through November 30, 2026. $0.10 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 2.00 input / 10.00 output / 0.10 cached per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"priority","input_per_m":3.6,"cached_input_per_m":0.18,"output_per_m":18,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-carbon","checked":"2026-11-14","quote":"Gemini 4 Carbon Priority: Input price $3.60 through November 30, 2026. $7.20 starting December 1, 2026. … Output price (including thinking tokens) $18.00 through November 30, 2026. $36.00 starting December 1, 2026. … Context caching price $0.18 through November 30, 2026. $0.36 starting December 1, 2026. Implicit caching only (explicit caching is not supported).","notes":"Paid tier. Not on the free tier. Promotional price; starting December 1, 2026 it rises to 7.20 input / 36.00 output / 0.36 cached per 1M tokens."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-carbon","name":"Gemini 4 Carbon","maker":"Google","provider_model_id":"gemini-4-carbon","tier":"priority","input_per_m":3.6,"cached_input_per_m":0.18,"output_per_m":18,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Carbon*through November 30, 2026 [Global] Input (text, image, video, audio) $3.60 … Text output (response and reasoning) $18.00 … cached $0.18","notes":"Global endpoint; non-global regions cost 10% more. Promotional price through November 30, 2026; from December 1, 2026 it is 7.2 input / 36 output per 1M tokens."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.075,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-hydrogen","checked":"2026-11-14","quote":"Gemini 4 Hydrogen Standard: Input price $1.50 … Output price (including thinking tokens) $7.50 … Context caching price $0.075 Implicit caching only (explicit caching is not supported).","notes":"Paid tier."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.075,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Hydrogen [Global] Input (text, image, video, audio) $1.50 … Text output (response and reasoning) $7.50 … cached $0.075","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"google/gemini-4-hydrogen","tier":"standard","input_per_m":1.5,"cached_input_per_m":0.075,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`google/gemini-4-hydrogen` | 1.50 | 7.50 | 0.075","notes":"Third-party model resold through the Perplexity Agent API."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"batch","input_per_m":0.75,"cached_input_per_m":0.0375,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-hydrogen","checked":"2026-11-14","quote":"Gemini 4 Hydrogen Batch: Input price $0.75 … Output price (including thinking tokens) $3.75 … Context caching price $0.0375 Implicit caching only (explicit caching is not supported).","notes":"Paid tier."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"batch","input_per_m":0.75,"cached_input_per_m":0.0375,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Hydrogen [Global] Input (text, image, video, audio) $0.75 … Text output (response and reasoning) $3.75 … cached $0.0375","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"flex","input_per_m":0.75,"cached_input_per_m":0.0375,"output_per_m":3.75,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-hydrogen","checked":"2026-11-14","quote":"Gemini 4 Hydrogen Flex: Input price $0.75 … Output price (including thinking tokens) $3.75 … Context caching price $0.0375 Implicit caching only (explicit caching is not supported).","notes":"Paid tier."},{"provider":"google","provider_name":"Google (Gemini API)","provider_kind":"maker","maker_api":true,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"priority","input_per_m":2.7,"cached_input_per_m":0.135,"output_per_m":13.5,"context":null,"precision":null,"source_url":"https://aistudio.google.com/docs/pricing#gemini-4-hydrogen","checked":"2026-11-14","quote":"Gemini 4 Hydrogen Priority: Input price $2.70 … Output price (including thinking tokens) $13.50 … Context caching price $0.135 Implicit caching only (explicit caching is not supported).","notes":"Paid tier."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","maker":"Google","provider_model_id":"gemini-4-hydrogen","tier":"priority","input_per_m":2.7,"cached_input_per_m":0.135,"output_per_m":13.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemini 4 Hydrogen [Global] Input (text, image, video, audio) $2.70 … Text output (response and reasoning) $13.50 … cached $0.135","notes":"Global endpoint; non-global regions cost 10% more."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gemma-3-12b-it","name":"Gemma 3 12B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.09,"cached_input_per_m":null,"output_per_m":0.29,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Gemma 3 12B $ 0.09 $ 0.29","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"gemma-3-12b-it","name":"Gemma 3 12B","maker":"Google","provider_model_id":"@cf/google/gemma-3-12b-it","tier":"standard","input_per_m":0.345,"cached_input_per_m":null,"output_per_m":0.556,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/google/gemma-3-12b-it $0.345 per M input tokens $0.556 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-12b-it","name":"gemma-3-12b-it","maker":"Google","provider_model_id":"google/gemma-3-12b-it","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.15,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/google/gemma-3-12b-it","checked":"2026-11-14","quote":"$0.05 in $0.15 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gemma-3-12b-it","name":"gemma-3-12b-it","maker":"Google","provider_model_id":"google/gemma-3-12b-it","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.15,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/google/gemma-3-12b-it","checked":"2026-11-15","quote":"PRICING: INPUT $0.05 / OUTPUT $0.15","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-12b-it","name":"gemma-3-12b-it","maker":"Google","provider_model_id":"google/gemma-3-12b-it","tier":"flex","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.12,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/google/gemma-3-12b-it","checked":"2026-11-14","quote":"Flex (0.8×) $0.04 $0.12","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-12b-it","name":"gemma-3-12b-it","maker":"Google","provider_model_id":"google/gemma-3-12b-it","tier":"priority","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.225,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/google/gemma-3-12b-it","checked":"2026-11-14","quote":"Priority (1.5×) $0.075 $0.225","notes":"Priority service tier (1.5× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"Gemma 3 27B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.23,"cached_input_per_m":null,"output_per_m":0.38,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Gemma 3 27B $ 0.23 $ 0.38","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"gemma-3-27b-it","maker":"Google","provider_model_id":"google/gemma-3-27b-it","tier":"standard","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.16,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-3-27b-it","checked":"2026-11-14","quote":"$0.08 in $0.16 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"gemma-3-27b-it","maker":"Google","provider_model_id":"google/gemma-3-27b-it","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.08,"output_per_m":0.3,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/google/gemma-3-27b-it","checked":"2026-11-15","quote":"PRICING: INPUT $0.1 / CACHED $0.08 / OUTPUT $0.3","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"Gemma 3 27B","maker":"Google","provider_model_id":"google/gemma-3-27b-it","tier":"standard","input_per_m":0.119,"cached_input_per_m":null,"output_per_m":0.2,"context":98304,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Gemma 3 27B 96K $0.119 /Mt $0.2 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"Gemma 3 27B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.08,"cached_input_per_m":0.04,"output_per_m":0.45,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Gemma 3 27B $0.08 $0.45 $0.04","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","maker":"Google","provider_model_id":"google-gemma-3-27b-it","tier":"standard","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.2,"context":198000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Google Gemma 3 27B Instruct | `google-gemma-3-27b-it` | $0.12 | $0.20 | — | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"gemma-3-27b-it","maker":"Google","provider_model_id":"google/gemma-3-27b-it","tier":"flex","input_per_m":0.064,"cached_input_per_m":null,"output_per_m":0.128,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-3-27b-it","checked":"2026-11-14","quote":"Flex (0.8×) $0.064 $0.128","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-27b-it","name":"gemma-3-27b-it","maker":"Google","provider_model_id":"google/gemma-3-27b-it","tier":"priority","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.24,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-3-27b-it","checked":"2026-11-14","quote":"Priority (1.5×) $0.12 $0.24","notes":"Priority service tier (1.5× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gemma-3-4b-it","name":"Gemma 3 4B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.08,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Gemma 3 4B $ 0.04 $ 0.08","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-4b-it","name":"gemma-3-4b-it","maker":"Google","provider_model_id":"google/gemma-3-4b-it","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.1,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/google/gemma-3-4b-it","checked":"2026-11-14","quote":"$0.05 in $0.10 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gemma-3-4b-it","name":"gemma-3-4b-it","maker":"Google","provider_model_id":"google/gemma-3-4b-it","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.1,"context":32768,"precision":"bf16","source_url":"https://featherless.ai/models/google/gemma-3-4b-it","checked":"2026-11-15","quote":"PRICING: INPUT $0.05 / OUTPUT $0.1","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-4b-it","name":"gemma-3-4b-it","maker":"Google","provider_model_id":"google/gemma-3-4b-it","tier":"flex","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.08,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/google/gemma-3-4b-it","checked":"2026-11-14","quote":"Flex (0.8×) $0.04 $0.08","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-3-4b-it","name":"gemma-3-4b-it","maker":"Google","provider_model_id":"google/gemma-3-4b-it","tier":"priority","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.15,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/google/gemma-3-4b-it","checked":"2026-11-14","quote":"Priority (1.5×) $0.075 $0.15","notes":"Priority service tier (1.5× standard)."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"gemma-4-12b-it","name":"gemma-4-12B-it","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"gemma-4-12B-it 262K $0.1 $0.3","notes":"Context shown as 262K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.13,"cached_input_per_m":null,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Gemma 4 26B A4B $0.13 $0.40","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","maker":"Google","provider_model_id":"@cf/google/gemma-4-26b-a4b-it","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/google/gemma-4-26b-a4b-it $0.100 per M input tokens $0.300 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","maker":"Google","provider_model_id":"google/gemma-4-26B-A4B-it","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.05,"output_per_m":0.3,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Google Gemma 4 26B A4B Instruct $0.10 $0.30 $0.05","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"gemma-4-26B-A4B-it","maker":"Google","provider_model_id":"google/gemma-4-26B-A4B-it","tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.34,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-26B-A4B-it","checked":"2026-11-14","quote":"$0.07 in $0.34 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"gemma-4-26B-A4B-it","maker":"Google","provider_model_id":"google/gemma-4-26B-A4B-it","tier":"standard","input_per_m":0.07,"cached_input_per_m":0.05,"output_per_m":0.34,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/google/gemma-4-26B-A4B-it","checked":"2026-11-15","quote":"PRICING: INPUT $0.07 / CACHED $0.05 / OUTPUT $0.34","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","maker":"Google","provider_model_id":"google/gemma-4-26b-a4b-it","tier":"standard","input_per_m":0.13,"cached_input_per_m":null,"output_per_m":0.4,"context":256000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemma-4-26b-a4b-it/ea6bbeb1-8aa5-4c58-bfe9-cfc98a6335d1","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.13 Output $0.40","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Gemma 4 26B","maker":"Google","provider_model_id":"gemma-4-26b","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/pricing","checked":"2026-11-14","quote":"Gemma 4 26B Input $0.15 … Output $0.60 … Cache Hit $0.015","notes":"Vertex AI managed API."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","maker":"Google","provider_model_id":"google/gemma-4-26b-a4b-it","tier":"standard","input_per_m":0.13,"cached_input_per_m":null,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Gemma 4 26B A4B 256K $0.13 /Mt $0.4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Gemma 4 26B-A4B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.13,"cached_input_per_m":0.05,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Gemma 4 26B-A4B $0.13 $0.40 $0.05","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"gemma-4-26B-A4B-it","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":0.05,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"gemma-4-26B-A4B-it 262K $0.14 $0.05 $0.4","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","maker":"Google","provider_model_id":"google-gemma-4-26b-a4b-it","tier":"standard","input_per_m":0.13,"cached_input_per_m":0.05,"output_per_m":0.4,"context":256000,"precision":"bf16","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Google Gemma 4 26B A4B Instruct | `google-gemma-4-26b-a4b-it` | $0.13 | $0.40 | $0.05 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"gemma-4-26B-A4B-it","maker":"Google","provider_model_id":"google/gemma-4-26B-A4B-it","tier":"flex","input_per_m":0.056,"cached_input_per_m":null,"output_per_m":0.272,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-26B-A4B-it","checked":"2026-11-14","quote":"Flex (0.8×) $0.056 $0.272","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-it","name":"gemma-4-26B-A4B-it","maker":"Google","provider_model_id":"google/gemma-4-26B-A4B-it","tier":"priority","input_per_m":0.105,"cached_input_per_m":null,"output_per_m":0.51,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-26B-A4B-it","checked":"2026-11-14","quote":"Priority (1.5×) $0.105 $0.51","notes":"Priority service tier (1.5× standard)."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"gemma-4-26b-a4b-uncensored","name":"Gemma 4 26B A4B Uncensored","maker":"Google","provider_model_id":"e2ee-gemma-4-26b-a4b-uncensored-p","tier":"standard","input_per_m":0.19,"cached_input_per_m":null,"output_per_m":0.88,"context":64000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Gemma 4 26B A4B Uncensored | `e2ee-gemma-4-26b-a4b-uncensored-p` | $0.19 | $0.88 | — | — | E2EE |","notes":"Uncensored variant of Gemma 4 26B A4B, end-to-end encrypted (E2EE) tier."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Gemma 4 31B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Gemma 4 31B $0.14 $0.40","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Google Gemma 4 31B","maker":"Google","provider_model_id":"google/gemma-4-31B-it","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.34,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Google Gemma 4 31B $0.10 $0.34 -","notes":""},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Gemma 4 31B","maker":"Google","provider_model_id":"google/gemma-4-31b-it","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.14,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"Gemma 4 31B text, image $0.14 $0.40 $0.14","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":"google/gemma-4-31B-it","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.4,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-31B-it","checked":"2026-11-14","quote":"$0.20 in $0.40 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":"google/gemma-4-31B-it","tier":"standard","input_per_m":0.12,"cached_input_per_m":0.1,"output_per_m":0.36,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/google/gemma-4-31B-it","checked":"2026-11-15","quote":"PRICING: INPUT $0.12 / CACHED $0.1 / OUTPUT $0.36","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"friendli","provider_name":"FriendliAI","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":"google/gemma-4-31B-it","tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://friendli.ai/models/google/gemma-4-31B-it","checked":"2026-11-15","quote":"Input $0.14 / 1M tokens Output $0.4 / 1M tokens","notes":"Context stated as \"262K\". No cached input price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Gemma 4 31B IT","maker":"Google","provider_model_id":"google/gemma-4-31b-it","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.1,"output_per_m":0.4,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gemma-4-31b-it/8b6ca932-9a42-44af-8df7-d006abd4a193","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.14 Output $0.40 Cache Read $0.10 Cache Write -","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Gemma 4 31B","maker":"Google","provider_model_id":"google/gemma-4-31b-it","tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Gemma 4 31B 256K $0.14 /Mt $0.4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Gemma 4 31B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.06,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Gemma 4 31B $0.15 $0.40 $0.06","notes":""},{"provider":"sambanova","provider_name":"SambaNova Cloud","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":"gemma-4-31B-it","tier":"standard","input_per_m":0.38,"cached_input_per_m":null,"output_per_m":1.15,"context":null,"precision":null,"source_url":"https://cloud.sambanova.ai/plans/pricing","checked":"2026-11-14","quote":"gemma-4-31B-it N/A 0.38 USD 1.15 USD","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":0.25,"output_per_m":1,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"gemma-4-31B-it 262K $0.75 $0.25 $1.0","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"Google Gemma 4 31B Instruct","maker":"Google","provider_model_id":"google-gemma-4-31b-it","tier":"standard","input_per_m":0.12,"cached_input_per_m":0.09,"output_per_m":0.36,"context":256000,"precision":"fp4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Google Gemma 4 31B Instruct | `google-gemma-4-31b-it` | $0.12 | $0.36 | $0.09 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":"google/gemma-4-31B-it","tier":"flex","input_per_m":0.16,"cached_input_per_m":null,"output_per_m":0.32,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-31B-it","checked":"2026-11-14","quote":"Flex (0.8×) $0.16 $0.32","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it","name":"gemma-4-31B-it","maker":"Google","provider_model_id":"google/gemma-4-31B-it","tier":"priority","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.6,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-31B-it","checked":"2026-11-14","quote":"Priority (1.5×) $0.30 $0.60","notes":"Priority service tier (1.5× standard)."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it-turbo","name":"gemma-4-31B-turbo","maker":"Google","provider_model_id":"google/gemma-4-31B-turbo-TEE","tier":"standard","input_per_m":0.12,"cached_input_per_m":0.012,"output_per_m":0.37,"context":131072,"precision":"fp4","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"gemma-4-31B-turbo google/gemma-4-31B-turbo-TEE $0.012 per 1M tokens $0.12 per 1M tokens $0.37 per 1M tokens 131K","notes":"Runs on confidential TEE compute. Served from nvidia/Gemma-4-31B-IT-NVFP4 (per the models API \"root\")."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it-turbo","name":"gemma-4-31B-it-turbo","maker":"Google","provider_model_id":"google/gemma-4-31B-it-turbo","tier":"standard","input_per_m":0.09,"cached_input_per_m":0.05,"output_per_m":0.34,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/google/gemma-4-31B-it-turbo","checked":"2026-11-14","quote":"$0.09 in $0.34 out $0.05 cached / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it-turbo","name":"gemma-4-31B-it-turbo","maker":"Google","provider_model_id":"google/gemma-4-31B-it-turbo","tier":"flex","input_per_m":0.072,"cached_input_per_m":0.04,"output_per_m":0.272,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/google/gemma-4-31B-it-turbo","checked":"2026-11-14","quote":"Flex (0.8×) $0.072 $0.272 $0.04","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it-turbo","name":"gemma-4-31B-it-turbo","maker":"Google","provider_model_id":"google/gemma-4-31B-it-turbo","tier":"priority","input_per_m":0.135,"cached_input_per_m":0.075,"output_per_m":0.51,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/google/gemma-4-31B-it-turbo","checked":"2026-11-14","quote":"Priority (1.5×) $0.135 $0.51 $0.075","notes":"Priority service tier (1.5× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gemma-4-31b-it-ultra","name":"gemma-4-31B-it-Ultra","maker":"Google","provider_model_id":"google/gemma-4-31B-it-Ultra","tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":0.76,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/google/gemma-4-31B-it-Ultra","checked":"2026-11-14","quote":"$0.27 in $0.76 out / 1M tokens","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gemma-4-e2b-it","name":"Gemma 4 E2B","maker":"Google","provider_model_id":null,"tier":"standard","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.08,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Gemma 4 E2B $0.04 $ 0.08","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"gemma-4-uncensored","name":"Gemma 4 Uncensored","maker":"Google","provider_model_id":"gemma-4-uncensored","tier":"standard","input_per_m":0.1625,"cached_input_per_m":null,"output_per_m":0.5,"context":256000,"precision":"int4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Gemma 4 Uncensored (Retiring) | `gemma-4-uncensored` | $0.1625 | $0.50 | — | — | Private |","notes":"Uncensored fine-tune of Gemma 4 26B. Marked \"Retiring\" by Venice."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"gemma-sea-lion-v4-27b-it","name":"Gemma SEA-LION v4 27B","maker":"AI Singapore","provider_model_id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","tier":"standard","input_per_m":0.351,"cached_input_per_m":null,"output_per_m":0.555,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/aisingapore/gemma-sea-lion-v4-27b-it $0.351 per M input tokens $0.555 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4-32b-0414-128k","name":"GLM-4-32B-0414-128K","maker":"Z.ai","provider_model_id":"GLM-4-32B-0414-128K","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.1,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4-32B-0414-128K | $0.1 | - | - | $0.1 |","notes":"No cached-input price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-4.5","name":"GLM-4.5-FP8","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.5-FP8","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.2,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/glm-4-5-fp8/84f25cc4-5c28-48b0-931f-72b09e5a8246","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.60 Output $2.20","notes":"No cache-read price published."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.5","name":"GLM-4.5","maker":"Z.ai","provider_model_id":"GLM-4.5","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.5 | $0.6 | $0.11 | Limited-time Free | $2.2 |","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-4.5-air","name":"GLM-4.5-Air-FP8","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.5-Air-FP8","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":1.1,"context":131076,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/glm-4-5-air-fp8/23693705-d653-475a-8724-f07490104b87","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.20 Output $1.10","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-4.5-air","name":"GLM 4.5 Air","maker":"Z.ai","provider_model_id":"zai-org/glm-4.5-air","tier":"standard","input_per_m":0.13,"cached_input_per_m":0.025,"output_per_m":0.85,"context":131072,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 4.5 Air 128K $0.13 /Mt · Cache Read $0.025 /Mt $0.85 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-4.5-air","name":"GLM-4.5-Air","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.86,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-4.5-Air 131K $0.14 $0.86","notes":"Context shown as 131K."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.5-air","name":"GLM-4.5-Air","maker":"Z.ai","provider_model_id":"GLM-4.5-Air","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.03,"output_per_m":1.1,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.5-Air | $0.2 | $0.03 | Limited-time Free | $1.1 |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.5-airx","name":"GLM-4.5-AirX","maker":"Z.ai","provider_model_id":"GLM-4.5-AirX","tier":"standard","input_per_m":1.1,"cached_input_per_m":0.22,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.5-AirX | $1.1 | $0.22 | Limited-time Free | $4.5 |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.5-flash","name":"GLM-4.5-Flash","maker":"Z.ai","provider_model_id":"GLM-4.5-Flash","tier":"standard","input_per_m":0,"cached_input_per_m":0,"output_per_m":0,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.5-Flash | Free | Free | Free | Free |","notes":"Free model."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.5-x","name":"GLM-4.5-X","maker":"Z.ai","provider_model_id":"GLM-4.5-X","tier":"standard","input_per_m":2.2,"cached_input_per_m":0.45,"output_per_m":8.9,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.5-X | $2.2 | $0.45 | Limited-time Free | $8.9 |","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-4.5v","name":"GLM 4.5V","maker":"Z.ai","provider_model_id":"zai-org/glm-4.5v","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":1.8,"context":65536,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 4.5V 64K $0.6 /Mt · Cache Read $0.11 /Mt $1.8 /Mt","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.5v","name":"GLM-4.5V","maker":"Z.ai","provider_model_id":"GLM-4.5V","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":1.8,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.5V | $0.6 | $0.11 | Limited-time Free | $1.8 |","notes":"Vision-language model (text output)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-4.6","name":"GLM-4.6","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.6","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":2,"context":202752,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-4.6","checked":"2026-11-14","quote":"$0.50 in $2.00 out $0.10 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-4.6","name":"GLM-4.6","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.6","tier":"standard","input_per_m":0.55,"cached_input_per_m":0.11,"output_per_m":2.2,"context":202752,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-4.6","checked":"2026-11-15","quote":"PRICING: INPUT $0.55 / CACHED $0.11 / OUTPUT $2.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-4.6","name":"GLM-4.6","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.6","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2,"context":204800,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/glm-4-6/11e2d1e4-2fb7-49a7-b625-fe9e41acbb72","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.60 Output $2.00","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-4.6","name":"GLM 4.6","maker":"Z.ai","provider_model_id":"zai-org/glm-4.6","tier":"standard","input_per_m":0.55,"cached_input_per_m":0.11,"output_per_m":2.2,"context":204800,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 4.6 200K $0.55 /Mt · Cache Read $0.11 /Mt $2.2 /Mt","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-4.6","name":"GLM 4.6","maker":"Z.ai","provider_model_id":"zai-org-glm-4.6","tier":"standard","input_per_m":0.43,"cached_input_per_m":0.08,"output_per_m":1.75,"context":198000,"precision":"fp4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 4.6 | `zai-org-glm-4.6` | $0.43 | $1.75 | $0.08 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.6","name":"GLM-4.6","maker":"Z.ai","provider_model_id":"GLM-4.6","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.6 | $0.6 | $0.11 | Limited-time Free | $2.2 |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-4.6","name":"GLM-4.6","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.6","tier":"flex","input_per_m":0.4,"cached_input_per_m":0.08,"output_per_m":1.6,"context":202752,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-4.6","checked":"2026-11-14","quote":"Flex (0.8×) $0.40 $1.60 $0.08","notes":"Flex service tier (0.8× standard)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-4.6v","name":"GLM 4.6V","maker":"Z.ai","provider_model_id":"zai-org/glm-4.6v","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.055,"output_per_m":0.9,"context":131072,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 4.6V 128K $0.3 /Mt · Cache Read $0.055 /Mt $0.9 /Mt","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.6v","name":"GLM-4.6V","maker":"Z.ai","provider_model_id":"GLM-4.6V","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.05,"output_per_m":0.9,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.6V | $0.3 | $0.05 | Limited-time Free | $0.9 |","notes":"Vision-language model (text output)."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.6v-flash","name":"GLM-4.6V-Flash","maker":"Z.ai","provider_model_id":"GLM-4.6V-Flash","tier":"standard","input_per_m":0,"cached_input_per_m":0,"output_per_m":0,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.6V-Flash | Free | Free | Free | Free |","notes":"Free model. Vision-language model (text output)."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.6v-flashx","name":"GLM-4.6V-FlashX","maker":"Z.ai","provider_model_id":"GLM-4.6V-FlashX","tier":"standard","input_per_m":0.04,"cached_input_per_m":0.004,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.6V-FlashX | $0.04 | $0.004 | Limited-time Free | $0.4 |","notes":"Vision-language model (text output)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM 4.7","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"GLM 4.7 $ 0.60 $ 2.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM-4.7","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.7","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.08,"output_per_m":1.75,"context":202752,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-4.7","checked":"2026-11-14","quote":"$0.40 in $1.75 out $0.08 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM-4.7","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.7","tier":"standard","input_per_m":0.55,"cached_input_per_m":0.11,"output_per_m":2.2,"context":202752,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-4.7","checked":"2026-11-15","quote":"PRICING: INPUT $0.55 / CACHED $0.11 / OUTPUT $2.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM-4.7-FP8","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.7-FP8","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":2.2,"context":202752,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/zai-glm-4-7-fp8/c31a8152-aebe-4f87-8066-a0d2cecad09e","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.60 Output $2.20 Cache Read $0.11 Cache Write -","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM 4.7","maker":"Z.ai","provider_model_id":"glm-4.7","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.06,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"GLM-4.7 Input $0.60 … Output $2.20 … Cache Hit $0.06","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM 4.7","maker":"Z.ai","provider_model_id":"zai-org/glm-4.7","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":2.2,"context":204800,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 4.7 200K $0.6 /Mt · Cache Read $0.11 /Mt $2.2 /Mt","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM 4.7","maker":"Z.ai","provider_model_id":"zai-org-glm-4.7","tier":"standard","input_per_m":0.55,"cached_input_per_m":0.11,"output_per_m":2.65,"context":198000,"precision":"fp4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 4.7 | `zai-org-glm-4.7` | $0.55 | $2.65 | $0.11 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.7","name":"GLM-4.7","maker":"Z.ai","provider_model_id":"GLM-4.7","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.11,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.7 | $0.6 | $0.11 | Limited-time Free | $2.2 |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-4.7","name":"GLM-4.7","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.7","tier":"flex","input_per_m":0.32,"cached_input_per_m":0.064,"output_per_m":1.4,"context":202752,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-4.7","checked":"2026-11-14","quote":"Flex (0.8×) $0.32 $1.40 $0.064","notes":"Flex service tier (0.8× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"glm-4.7-flash","name":"GLM 4.7 Flash","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"GLM 4.7 Flash $ 0.07 $ 0.40","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"glm-4.7-flash","name":"GLM 4.7 Flash","maker":"Z.ai","provider_model_id":"@cf/zai-org/glm-4.7-flash","tier":"standard","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/zai-org/glm-4.7-flash $0.060 per M input tokens $0.400 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-4.7-flash","name":"GLM-4.7-Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.7-Flash","tier":"standard","input_per_m":0.0653,"cached_input_per_m":0.0131,"output_per_m":0.4,"context":202752,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-4.7-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.0653 / CACHED $0.0131 / OUTPUT $0.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-4.7-flash","name":"GLM-4.7-Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-4.7-Flash","tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.4,"context":202752,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/zai-glm-4-7-flash/0113381a-3b4b-4b39-8722-ed4b4adca6f4","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.07 Output $0.40","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-4.7-flash","name":"GLM 4.7 Flash","maker":"Z.ai","provider_model_id":"zai-org/glm-4.7-flash","tier":"standard","input_per_m":0.07,"cached_input_per_m":0.01,"output_per_m":0.4,"context":200000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 4.7 Flash 195K $0.07 /Mt · Cache Read $0.01 /Mt $0.4 /Mt","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.7-flash","name":"GLM-4.7-Flash","maker":"Z.ai","provider_model_id":"GLM-4.7-Flash","tier":"standard","input_per_m":0,"cached_input_per_m":0,"output_per_m":0,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.7-Flash | Free | Free | Free | Free |","notes":"Free model."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-4.7-flash-heretic","name":"GLM 4.7 Flash Heretic","maker":"olafangensan","provider_model_id":"olafangensan-glm-4.7-flash-heretic","tier":"standard","input_per_m":0.07,"cached_input_per_m":0.035,"output_per_m":0.4,"context":200000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 4.7 Flash Heretic | `olafangensan-glm-4.7-flash-heretic` | $0.07 | $0.40 | $0.035 | — | Private |","notes":"Community uncensored fine-tune of GLM 4.7 Flash."},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-4.7-flashx","name":"GLM-4.7-FlashX","maker":"Z.ai","provider_model_id":"GLM-4.7-FlashX","tier":"standard","input_per_m":0.07,"cached_input_per_m":0.01,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-4.7-FlashX | $0.07 | $0.01 | Limited-time Free | $0.4 |","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM 5","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"GLM 5 $ 1.00 $ 3.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"glm-5","name":"GLM-5","maker":"Z.ai","provider_model_id":"glm-5","tier":"standard","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":3.2,"context":198000,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"GLM-5\tGLM-5\tInference Service\tInput\t1.0\t$/M tokens Cache Hit\t0.2\t$/M tokens Output\t3.2\t$/M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM-5","maker":"Z.ai","provider_model_id":"zai-org/GLM-5","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":3.15,"context":202752,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-5","checked":"2026-11-15","quote":"PRICING: INPUT $0.95 / CACHED $0.19 / OUTPUT $3.15","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM-5","maker":"Z.ai","provider_model_id":"zai-org/GLM-5-FP8","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.12,"output_per_m":1.92,"context":202752,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/zai-glm-5/951fef32-e6c8-4a1d-8cac-89405daae6e0","checked":"2026-11-15","quote":"Price (per 1M tokens) 40% off Input $0.60 $1.00 Output $1.92 $3.20 Cache Read $0.12 $0.20 Cache Write -","notes":"Promotional price, 40% off list (list 1 in / 3.2 out / 0.2 cached)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM 5","maker":"Z.ai","provider_model_id":"glm-5","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"GLM-5 Input $1.00 … Output $3.20 … Cache Hit $0.10","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM 5","maker":"Z.ai","provider_model_id":"zai-org/glm-5","tier":"standard","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":3.2,"context":202800,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 5 198K $1 /Mt · Cache Read $0.2 /Mt $3.2 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM-5","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"GLM-5 $1.00 $3.20 $0.20","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM-5","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.95,"cached_input_per_m":0.2,"output_per_m":2.55,"context":204800,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-5 205K $0.95 $0.2 $2.55","notes":"Context shown as 205K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-5","name":"GLM 5","maker":"Z.ai","provider_model_id":"zai-org-glm-5","tier":"standard","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":3.2,"context":198000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 5 | `zai-org-glm-5` | $1.00 | $3.20 | $0.20 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5","name":"GLM-5","maker":"Z.ai","provider_model_id":"GLM-5","tier":"standard","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5 | $1 | $0.2 | Limited-time Free | $3.2 |","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"glm-5.1","name":"GLM 5.1","maker":"Z.ai","provider_model_id":"glm-5.1","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"glm-5.1 International Non-Thinking and Thinking modes 0<Token≤200K $1.400 $4.400","notes":"International (Singapore) deployment. Prompts up to 200K tokens. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 18.57% of the input price in the International (Singapore) scope."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"FW GLM 5.1","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.54,"cached_input_per_m":0.286,"output_per_m":4.84,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW GLM 5.1 Data Zone\tInput: $1.54/1M Tokens | Cached Input: $0.286/1M Tokens | Output: $4.84/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":"glm-5.1","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":198000,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"GLM-5.1\tGLM-5.1\tInference Service\tInput\t1.4\t$/M tokens Cache Hit\t0.26\t$/M tokens Output\t4.4\t$/M tokens","notes":""},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.1-TEE","tier":"standard","input_per_m":0.9,"cached_input_per_m":0.09,"output_per_m":2.9,"context":202752,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"GLM-5.1 zai-org/GLM-5.1-TEE $0.09 per 1M tokens $0.90 per 1M tokens $2.90 per 1M tokens 203K","notes":"Runs on confidential TEE compute."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.1","tier":"standard","input_per_m":1.3,"cached_input_per_m":0.26,"output_per_m":4.3,"context":202752,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-5.1","checked":"2026-11-15","quote":"PRICING: INPUT $1.3 / CACHED $0.26 / OUTPUT $4.3","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"friendli","provider_name":"FriendliAI","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.1","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":203000,"precision":null,"source_url":"https://friendli.ai/models/zai-org/GLM-5.1","checked":"2026-11-15","quote":"Input $1.4 / 1M tokens Cached Input $0.26 / 1M tokens Output $4.4 / 1M tokens","notes":"Context stated as \"203K\"."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.1-FP8","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":202752,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/zai-glm-5-1/4e4d2e35-34ff-45dc-b09f-c50d464d3464","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.40 Output $4.40 Cache Read $0.26 Cache Write -","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM 5.1","maker":"Z.ai","provider_model_id":"zai-org/glm-5.1","tier":"standard","input_per_m":1.38,"cached_input_per_m":0.26,"output_per_m":4.4,"context":204800,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 5.1 200K $1.38 /Mt · Cache Read $0.26 /Mt $4.4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"GLM-5.1 $1.40 $4.40 $0.26","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.19,"cached_input_per_m":0.6,"output_per_m":3.74,"context":204800,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-5.1 205K $1.19 $0.6 $3.74","notes":"Context shown as 205K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-5.1","name":"GLM 5.1","maker":"Z.ai","provider_model_id":"zai-org-glm-5-1","tier":"standard","input_per_m":1.54,"cached_input_per_m":0.286,"output_per_m":4.84,"context":200000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 5.1 | `zai-org-glm-5-1` | $1.54 | $4.84 | $0.286 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5.1","name":"GLM-5.1","maker":"Z.ai","provider_model_id":"GLM-5.1","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5.1 | $1.4 | $0.26 | Limited-time Free | $4.4 |","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"glm-5.2","name":"GLM 5.2","maker":"Z.ai","provider_model_id":"glm-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.28,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"glm-5.2 International Non-Thinking and Thinking modes flat-rate pricing $1.400 $4.400","notes":"International (Singapore) deployment. Deployed by Alibaba Cloud Model Studio. A Zhipu-deployed variant, ZHIPU/GLM-5.2, is listed at the same price. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"FW GLM 5.2","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.54,"cached_input_per_m":0.15,"output_per_m":4.84,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW GLM 5.2 Data Zone\tInput: $1.54/1M Tokens | Cached Input: $0.15/1M Tokens | Output: $4.84/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"glm-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":500000,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"GLM-5.2\tGLM-5.2\tInference Service\tInput\t1.4\t$/M tokens Cache Hit\t0.26\t$/M tokens Output\t4.4\t$/M tokens","notes":""},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.14,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"GLM-5.2 $1.40 $0.14 $4.40","notes":""},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2-TEE","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":3.95,"context":1048576,"precision":"fp4","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"GLM-5.2 zai-org/GLM-5.2-TEE $0.125 per 1M tokens $1.25 per 1M tokens $3.95 per 1M tokens 1.0M","notes":"Runs on confidential TEE compute."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM 5.2","maker":"Z.ai","provider_model_id":"@cf/zai-org/glm-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/zai-org/glm-5.2 $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"Z.AI GLM 5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"standard","input_per_m":0.62,"cached_input_per_m":0.14,"output_per_m":2.42,"context":1048576,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Z.AI GLM 5.2 $0.62 $2.42 $0.14","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"standard","input_per_m":0.5625,"cached_input_per_m":0.105,"output_per_m":1.8,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-5.2","checked":"2026-11-14","quote":"$0.563 in $1.80 out $0.105 cached / 1M tokens","notes":"Promotional price, 25% off list (list 0.75 in / 2.4 out)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.21,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GLM-5.2 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.40$4.40$0.21","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.15,"output_per_m":4.4,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-5.2","checked":"2026-11-15","quote":"PRICING: INPUT $1.4 / CACHED $0.15 / OUTPUT $4.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"friendli","provider_name":"FriendliAI","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://friendli.ai/models/zai-org/GLM-5.2","checked":"2026-11-15","quote":"Input $1.4 / 1M tokens Cached Input $0.26 / 1M tokens Output $4.4 / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"zai-org/GLM-5.2-FP8","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2-FP8","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/zai-org-glm-5-2-fp8/1f12423b-ac10-4690-a670-36f768d7b9bf","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.40 Output $4.40 Cache Read $0.26 Cache Write -","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM 5.2","maker":"Z.ai","provider_model_id":"glm-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.14,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"GLM-5.2 Input $1.40 … Output $4.40 … Cached Input: $0.14","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM 5.2","maker":"Z.ai","provider_model_id":"zai-org/glm-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 5.2 1M $1.4 /Mt · Cache Read $0.26 /Mt $4.4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"GLM-5.2 $1.40 $4.40 $0.26","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.302,"cached_input_per_m":0.26,"output_per_m":4.092,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-5.2 1049K $1.302 $0.26 $4.092","notes":"Context shown as 1049K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"GLM-5.2 $1.40 $0.26 (cached) $4.40","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM 5.2","maker":"Z.ai","provider_model_id":"zai-org-glm-5-2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 5.2 | `zai-org-glm-5-2` | $1.40 | $4.40 | $0.26 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"GLM-5.2","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5.2 | $1.4 | $0.26 | Limited-time Free | $4.4 |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"flex","input_per_m":0.45,"cached_input_per_m":0.084,"output_per_m":1.44,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-5.2","checked":"2026-11-14","quote":"Flex (0.8×) $0.45 $1.44 $0.084","notes":"Flex service tier (0.8× standard). Promotional price, 25% off list (list 0.75 in / 2.4 out)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2","tier":"priority","input_per_m":0.8438,"cached_input_per_m":0.1575,"output_per_m":2.7,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-5.2","checked":"2026-11-14","quote":"Priority (1.5×) $0.8438 $2.70 $0.1575","notes":"Priority service tier (1.5× standard). Promotional price, 25% off list (list 0.75 in / 2.4 out)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"glm-5.2","name":"GLM 5.2","maker":"Z.ai","provider_model_id":"glm-5.2-fast-preview","tier":"fast","input_per_m":2.8,"cached_input_per_m":0.56,"output_per_m":8.8,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/prime-mode","checked":"2026-11-14","quote":"glm-5.2-fast-preview $2.800 $8.800 $0.560","notes":"International (Singapore) deployment. Fast mode (Prime), Singapore tab of the Fast mode page; the model pricing page lists the same 2.8 input, 8.8 output."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"FW GLM 5.2 Fast","maker":"Z.ai","provider_model_id":null,"tier":"fast","input_per_m":2.31,"cached_input_per_m":0.231,"output_per_m":7.26,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW GLM 5.2 Fast Data Zone\tInput: $2.31/1M Tokens | Cached Input: $0.231/1M Tokens | Output: $7.26/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"glm-5.2","name":"GLM-5.2-Fast","maker":"Z.ai","provider_model_id":"glm-5.2-fast","tier":"fast","input_per_m":2.25,"cached_input_per_m":0.56,"output_per_m":7.88,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"GLM-5.2-Fast\tGLM-5.2-Fast\tInference Service\tInput\t2.25\t$/M tokens Cache Hit\t0.56\t$/M tokens Output\t7.88\t$/M tokens","notes":"GLM-5.2-Fast, the fast version of GLM-5.2."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2 Fast","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2-Fast","tier":"fast","input_per_m":2.1,"cached_input_per_m":0.21,"output_per_m":6.6,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"GLM-5.2 Fast $2.10 $0.21 $6.60","notes":""},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"glm-5.2","name":"GLM-5.2-Fast","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.2-Fast","tier":"fast","input_per_m":2.45,"cached_input_per_m":0.49,"output_per_m":7.7,"context":1048576,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"GLM-5.2-Fast zai-org/GLM-5.2-Fast $0.49 per 1M tokens $2.45 per 1M tokens $7.70 per 1M tokens 1.0M","notes":"Fast variant, model ID zai-org/GLM-5.2-Fast."},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":0.19,"cached_input_per_m":0.19,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://akashml.com/models/glm-5.3","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read GLM 5.3 $0.19 $4.40 $0.19","notes":"Labelled \"Limited Trial\" on AkashML."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"glm-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.28,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"glm-5.3 International Non-Thinking and Thinking modes flat-rate pricing $1.400 $4.400","notes":"International (Singapore) deployment. Deployed by Alibaba Cloud Model Studio. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.848,"cached_input_per_m":0.3432,"output_per_m":5.808,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"US CRIS $ 1.848 $ 5.808 $ 0.3432 $ 2.31","notes":"US cross-region (US CRIS) row; Global CRIS is $1.68 / $5.28 / cache read $0.312. Cache write (30 min) $2.31."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.14,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"GLM-5.3 $1.40 $0.14 $4.40","notes":""},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":1.225,"cached_input_per_m":0.245,"output_per_m":3.85,"context":1048576,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"GLM-5.3 zai-org/GLM-5.3 $0.245 per 1M tokens $1.225 per 1M tokens $3.85 per 1M tokens 1.0M","notes":""},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"@cf/zai-org/glm-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/zai-org/glm-5.3 $1.400 per M input tokens $0.260 per M cached input tokens $4.400 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"GLM-5.3 $1.40 $4.40 $0.26","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":0.5625,"cached_input_per_m":0.125,"output_per_m":2.5,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-5.3","checked":"2026-11-14","quote":"$0.563 in $2.50 out $0.125 cached / 1M tokens","notes":"Promotional price, 38% off list (list 0.9 in / 4.0 out)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GLM-5.3 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.40$4.40$0.26","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-5.3","checked":"2026-11-15","quote":"PRICING: INPUT $1.4 / CACHED $0.26 / OUTPUT $4.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"accounts/fireworks/models/glm-5p3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"GLM 5.3 | $1.40 / $0.26 / $4.40 | $1.75 / $0.325 / $5.50","notes":""},{"provider":"friendli","provider_name":"FriendliAI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":1.26,"cached_input_per_m":0.234,"output_per_m":3.96,"context":1048576,"precision":null,"source_url":"https://friendli.ai/models/zai-org/GLM-5.3","checked":"2026-11-15","quote":"10% OFF Input $1.26 $1.4 / 1M tokens Cached Input $0.234 $0.26 / 1M tokens Output $3.96 $4.4","notes":"Promotional price, 10% off list (list 1.4 in / 0.26 cached / 4.4 out)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"standard","input_per_m":0.7,"cached_input_per_m":0.13,"output_per_m":2.2,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/zai-glm-5-3/f2b6325c-ea70-4c19-802b-5a5f839259e3","checked":"2026-11-15","quote":"Price (per 1M tokens) 50% off Input $0.70 $1.40 Output $2.20 $4.40 Cache Read $0.13 $0.26 Cache Write -","notes":"Promotional price, 50% off list (list 1.4 in / 4.4 out / 0.26 cached)."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"glm-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"GLM 5.3 glm-5.3 Z.ai · 1M context · Text $1.40 $4.40 $0.26","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"zai-glm-5-3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.14,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Z.ai GLM 5.3 ↗\t$1.4\t$0.14\t$4.4","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Context from the docs model card."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"zai-org/glm-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 5.3 1M $1.4 /Mt · Cache Read $0.26 /Mt $4.4 /Mt","notes":""},{"provider":"nscale","provider_name":"Nscale","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":null,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.nscale.com/docs/ai-services/models","checked":"2026-11-15","quote":"| GLM 5.3 | Z.ai | $1.40 | $4.40 |","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"GLM-5.3 $1.40 $4.40 $0.26","notes":""},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"perplexity/glm-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`perplexity/glm-5.3` | 1.40 | 4.40 | 0.26","notes":"Hosted by Perplexity (\"Perplexity-Hosted Models\"); tool calls billed separately."},{"provider":"sambanova","provider_name":"SambaNova Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"GLM-5.3","tier":"standard","input_per_m":2.8,"cached_input_per_m":0.14,"output_per_m":8.8,"context":null,"precision":null,"source_url":"https://cloud.sambanova.ai/plans/pricing","checked":"2026-11-14","quote":"GLM-5.3 0.14 USD 2.80 USD 8.80 USD","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-5.3 1049K $1.4 $0.26 $4.4","notes":"Context shown as 1049K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"GLM-5.3 $1.40 $0.26 (cached) $4.40","notes":"US geo-pinned option: $1.75 in / $5.50 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"z-ai-glm-5-3","tier":"standard","input_per_m":1.75,"cached_input_per_m":0.325,"output_per_m":5.5,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 5.3 | `z-ai-glm-5-3` | $1.75 | $5.50 | $0.325 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"GLM-5.3","tier":"standard","input_per_m":1.4,"cached_input_per_m":0.26,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5.3 | $1.4 | $0.26 | Limited-time Free | $4.4 |","notes":""},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"zai-glm-5-3","tier":"batch","input_per_m":0.7,"cached_input_per_m":0.07,"output_per_m":2.2,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Z.ai GLM 5.3 ↗\t$0.7\t$0.07\t$2.2 (Batch tab, \"Batch (-50%)\")","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Context from the docs model card."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3","tier":"flex","input_per_m":0.45,"cached_input_per_m":0.1,"output_per_m":2,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-5.3","checked":"2026-11-14","quote":"Flex (0.8×) $0.45 $2.00 $0.10","notes":"Flex service tier (0.8× standard). Promotional price, 38% off list (list 0.9 in / 4.0 out)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3","maker":"Z.ai","provider_model_id":"accounts/fireworks/models/glm-5p3","tier":"flex","input_per_m":0.98,"cached_input_per_m":0.182,"output_per_m":3.08,"context":1048576,"precision":null,"source_url":"https://fireworks.ai/pricing","checked":"2026-11-14","quote":"GLM-5.3 Spot $0.182 $0.98 $3.08","notes":"Fireworks \"Spot\" mode: 30% off Standard on best-effort capacity; throughput can drop to zero."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"accounts/fireworks/models/glm-5p3","tier":"priority","input_per_m":1.75,"cached_input_per_m":0.325,"output_per_m":5.5,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"GLM 5.3 | Priority $1.75 / $0.325 / $5.50","notes":"Priority mode."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"zai-glm-5-3","tier":"priority","input_per_m":2.45,"cached_input_per_m":0.245,"output_per_m":7.7,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Z.ai GLM 5.3 ↗\t$2.45\t$0.245\t$7.7 (Priority tab, \"Priority (+75%)\")","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Context from the docs model card."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM-5.3 Fast","maker":"Z.ai","provider_model_id":null,"tier":"fast","input_per_m":2.1,"cached_input_per_m":0.21,"output_per_m":6.6,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"GLM-5.3 Fast $2.10 $0.21 $6.60","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"glm-5.3","name":"GLM 5.3","maker":"Z.ai","provider_model_id":"accounts/fireworks/models/glm-5p3","tier":"fast","input_per_m":2.1,"cached_input_per_m":0.39,"output_per_m":6.6,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"GLM 5.3 Fast | $2.10 / $0.39 / $6.60 | —","notes":"Fast mode."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"FW GLM 5.3 Flash","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.188,"cached_input_per_m":0.038,"output_per_m":0.625,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW GLM 5.3 Flash Global\tInput: $0.188/1M Tokens | Cached Input: $0.038/1M Tokens | Output: $0.625/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Global deployment."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"GLM-5.3-Flash $0.15 $0.03 $0.50","notes":""},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"@cf/zai-org/glm-5.3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/zai-org/glm-5.3-flash $0.150 per M input tokens $0.030 per M cached input tokens $0.500 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"Z.AI GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.12,"cached_input_per_m":0.02,"output_per_m":0.38,"context":1048576,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Z.AI GLM 5.3 Flash $0.12 $0.38 $0.02","notes":""},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3 Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"GLM-5.3 Flash text, image $0.15 $0.50 $0.03","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/zai-org/GLM-5.3-Flash","checked":"2026-11-14","quote":"$0.15 in $0.50 out $0.03 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3 Flash","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GLM-5.3 Flash — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.15$0.50$0.03","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/zai-org/GLM-5.3-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.15 / CACHED $0.03 / OUTPUT $0.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"accounts/fireworks/models/glm-5p3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"GLM 5.3 Flash | $0.15 / $0.03 / $0.50 | $0.1875 / $0.0375 / $0.625","notes":""},{"provider":"friendli","provider_name":"FriendliAI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://friendli.ai/models/zai-org/GLM-5.3-Flash","checked":"2026-11-15","quote":"Input $0.15 / 1M tokens Cached Input $0.03 / 1M tokens Output $0.5 / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3 Flash","maker":"Z.ai","provider_model_id":"zai-org/GLM-5.3-Flash","tier":"standard","input_per_m":0.075,"cached_input_per_m":0.015,"output_per_m":0.25,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/zai-glm-5-3-flash/60e50c31-b7d0-45a9-b83b-905a0d169c10","checked":"2026-11-15","quote":"Price (per 1M tokens) 50% off Input $0.075 $0.15 Output $0.25 $0.50 Cache Read $0.015 $0.03 Cache Write -","notes":"Promotional price, 50% off list (list 0.15 in / 0.5 out / 0.03 cached)."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"glm-5.3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"GLM 5.3 Flash glm-5.3-flash Z.ai · 1M context · Text $0.15 $0.50 $0.03","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"zai-glm-5-3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Z.ai GLM 5.3 Flash ↗\t$0.15\t$0.03\t$0.5","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Context from the docs model card."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"zai-org/glm-5.3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 5.3 Flash 1M $0.15 /Mt · Cache Read $0.03 /Mt $0.5 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3 Flash","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"GLM-5.3 Flash $0.15 $0.50 $0.03","notes":""},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3 Flash","maker":"Z.ai","provider_model_id":"perplexity/glm-5.3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`perplexity/glm-5.3-flash` | 0.15 | 0.50 | 0.03","notes":"Hosted by Perplexity (\"Perplexity-Hosted Models\"); tool calls billed separately."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-5.3-Flash 1049K $0.15 $0.03 $0.5","notes":"Context shown as 1049K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"GLM-5.3-Flash $0.15 $0.03 (cached) $0.50","notes":"US geo-pinned option: $0.1875 in / $0.625 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"z-ai-glm-5-3-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| GLM 5.3 Flash | `z-ai-glm-5-3-flash` | $0.15 | $0.50 | $0.03 | — | Private |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5.3-flash","name":"GLM-5.3-Flash","maker":"Z.ai","provider_model_id":"GLM-5.3-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5.3-Flash | $0.15 | $0.03 | Limited-time Free | $0.50 |","notes":""},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"zai-glm-5-3-flash","tier":"batch","input_per_m":0.075,"cached_input_per_m":0.015,"output_per_m":0.25,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Z.ai GLM 5.3 Flash ↗\t$0.075\t$0.015\t$0.25 (Batch tab, \"Batch (-50%)\")","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Context from the docs model card."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"accounts/fireworks/models/glm-5p3-flash","tier":"priority","input_per_m":0.1875,"cached_input_per_m":0.0375,"output_per_m":0.625,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"GLM 5.3 Flash | Priority $0.1875 / $0.0375 / $0.625","notes":"Priority mode."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":false,"model":"glm-5.3-flash","name":"GLM 5.3 Flash","maker":"Z.ai","provider_model_id":"zai-glm-5-3-flash","tier":"priority","input_per_m":0.2625,"cached_input_per_m":0.0525,"output_per_m":0.875,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Z.ai GLM 5.3 Flash ↗\t$0.2625\t$0.0525\t$0.875 (Priority tab, \"Priority (+75%)\")","notes":"Third-party open-weight model hosted by Mistral (Mistral labels it \"served without Mistral modifications\"). Context from the docs model card."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"glm-5.3-flashx","name":"GLM 5.3 FlashX","maker":"Z.ai","provider_model_id":"zai-org/glm-5.3-flashX","tier":"standard","input_per_m":0.37,"cached_input_per_m":0.075,"output_per_m":1.25,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"GLM 5.3 FlashX 1M $0.37 /Mt · Cache Read $0.075 /Mt $1.25 /Mt","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5.3-flashx","name":"GLM-5.3-FlashX","maker":"Z.ai","provider_model_id":"GLM-5.3-FlashX","tier":"standard","input_per_m":0.37,"cached_input_per_m":0.075,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5.3-FlashX | $0.37 | $0.075 | Limited-time Free | $1.25 |","notes":""},{"provider":"z-ai","provider_name":"Z.ai","provider_kind":"maker","maker_api":true,"model":"glm-5.3-flashx-legal","name":"GLM-5.3-FlashX-Legal","maker":"Z.ai","provider_model_id":"GLM-5.3-FlashX-Legal","tier":"standard","input_per_m":0.37,"cached_input_per_m":0.075,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://docs.z.ai/guides/overview/pricing","checked":"2026-11-14","quote":"| GLM-5.3-FlashX-Legal | $0.37 | $0.075 | Limited-time Free | $1.25 |","notes":"Legal-domain variant."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"glm-5.3-prime","name":"GLM 5.3 Prime","maker":"Z.ai","provider_model_id":"glm-5.3-prime","tier":"fast","input_per_m":2.8,"cached_input_per_m":0.56,"output_per_m":8.8,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"glm-5.3-prime International Non-Thinking and Thinking modes flat-rate pricing $2.800 $8.800","notes":"International (Singapore) deployment. Fast mode (Prime): 1.5 to 2 times the output speed of the standard API. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"glm-5v-turbo","name":"GLM-5V-Turbo","maker":"Z.ai","provider_model_id":null,"tier":"standard","input_per_m":1.2,"cached_input_per_m":0.24,"output_per_m":4,"context":204800,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"GLM-5V-Turbo 205K $1.2 $0.24 $4.0","notes":"Context shown as 205K."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1","name":"GPT-4.1 (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":8,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-2025-04-14 Global\tInput: $2 | Cached Input: $0.50 | Output: $8","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-4.1","name":"GPT-4.1","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":8,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-4.1 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.00$8.00$0.50","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4.1","name":"GPT-4.1","maker":"OpenAI","provider_model_id":"gpt-4.1","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":8,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4.1 | $2.00 | $8.00 | $0.50 |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1","name":"GPT-4.1 (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-2025-04-14 Global\tInput: $1 | Output: $4","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4.1","name":"GPT-4.1","maker":"OpenAI","provider_model_id":"gpt-4.1","tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4.1 | $1.00 | $4.00 | - |","notes":"Batch API (asynchronous)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1","name":"GPT-4.1 (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":3.5,"cached_input_per_m":0.88,"output_per_m":14,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-2025-04-14 Global\tInput: $3.50 | Cached Input: $0.88 | Output: $14","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-4.1","name":"GPT-4.1","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":3.5,"cached_input_per_m":0.875,"output_per_m":14,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-4.1 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$3.50$14.00$0.875","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4.1","name":"GPT-4.1","maker":"OpenAI","provider_model_id":"gpt-4.1","tier":"fast","input_per_m":3.5,"cached_input_per_m":0.875,"output_per_m":14,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4.1 | $3.50 | $14.00 | $0.875 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1-mini","name":"GPT-4.1 mini (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.4,"cached_input_per_m":0.1,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-mini-2025-04-14 Global\tInput: $0.40 | Cached Input: $0.10 | Output: $1.60","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4.1-mini","name":"GPT-4.1 Mini","maker":"OpenAI","provider_model_id":"gpt-4.1-mini","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.1,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4.1-mini | $0.40 | $1.60 | $0.10 |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1-mini","name":"GPT-4.1 mini (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.8,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-mini-2025-04-14 Global\tInput: $0.20 | Output: $0.80","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4.1-mini","name":"GPT-4.1 Mini","maker":"OpenAI","provider_model_id":"gpt-4.1-mini","tier":"batch","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.8,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4.1-mini | $0.20 | $0.80 | - |","notes":"Batch API (asynchronous)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1-mini","name":"GPT-4.1 mini (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":0.7,"cached_input_per_m":0.18,"output_per_m":2.8,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-mini-2025-04-14 Global\tInput: $0.70 | Cached Input: $0.18 | Output: $2.80","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4.1-mini","name":"GPT-4.1 Mini","maker":"OpenAI","provider_model_id":"gpt-4.1-mini","tier":"fast","input_per_m":0.7,"cached_input_per_m":0.175,"output_per_m":2.8,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4.1-mini | $0.70 | $2.80 | $0.175 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1-nano","name":"GPT-4.1 nano (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.03,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-nano-2025-04-14 Global\tInput: $0.10 | Cached Input: $0.03 | Output: $0.40","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4.1-nano","name":"GPT-4.1 nano (2025-04-14)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4.1-nano-2025-04-14 Global\tInput: $0.05 | Output: $0.20","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-4o","name":"GPT-4o","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":1.25,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-4o — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.50$10.00$1.25","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4o","name":"GPT-4o","maker":"OpenAI","provider_model_id":"gpt-4o","tier":"standard","input_per_m":2.5,"cached_input_per_m":1.25,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4o | $2.50 | $10.00 | $1.25 |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4o","name":"GPT-4o","maker":"OpenAI","provider_model_id":"gpt-4o","tier":"batch","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4o | $1.25 | $5.00 | - |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-4o","name":"GPT-4o","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":4.25,"cached_input_per_m":2.125,"output_per_m":17,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-4o — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$4.25$17.00$2.125","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4o","name":"GPT-4o","maker":"OpenAI","provider_model_id":"gpt-4o","tier":"fast","input_per_m":4.25,"cached_input_per_m":2.125,"output_per_m":17,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4o | $4.25 | $17.00 | $2.125 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-2024-0513 Global\tInput: $5 | Output: $15","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-2024-0513 Global\tInput: $2.50 | Output: $7.50","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":1.25,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-2024-08-06 Global\tInput: $2.50 | Cached Input: $1.25 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-2024-08-06 Global\tInput: $1.25 | Output: $5","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":1.25,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-2024-1120 Global\tInput: $2.50 | Cached Input: $1.25 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-2024-1120 Global\tInput: $1.25 | Output: $5","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-mini","name":"GPT-4o mini (2024-07-18)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.075,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-mini-0718 Global\tInput: $0.15 | Cached Input: $0.075 | Output: $0.60","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-4o-mini","name":"GPT-4o mini","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.075,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-4o mini — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.15$0.60$0.075","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4o-mini","name":"GPT-4o-mini","maker":"OpenAI","provider_model_id":"gpt-4o-mini","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.075,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4o-mini | $0.15 | $0.60 | $0.075 |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-4o-mini","name":"GPT-4o mini (2024-07-18)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-4o-mini-0718 Global\tInput: $0.075 | Output: $0.30","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4o-mini","name":"GPT-4o-mini","maker":"OpenAI","provider_model_id":"gpt-4o-mini","tier":"batch","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4o-mini | $0.075 | $0.30 | - |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-4o-mini","name":"GPT-4o mini","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":0.25,"cached_input_per_m":0.125,"output_per_m":1,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-4o mini — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$0.25$1.00$0.125","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-4o-mini","name":"GPT-4o-mini","maker":"OpenAI","provider_model_id":"gpt-4o-mini","tier":"fast","input_per_m":0.25,"cached_input_per_m":0.125,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-4o-mini | $0.25 | $1.00 | $0.125 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5","name":"GPT-5 (2025-08-07)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5 2025-08-07 Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.25$10.00$0.125","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":"gpt-5","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5 | $1.25 | $10.00 | $0.125 |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5","name":"GPT-5 (2025-08-07)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.63,"cached_input_per_m":0.07,"output_per_m":5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5 2025-08-07 Global\tInput: $0.63 | Cached Input: $0.07 | Output: $5","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":"gpt-5","tier":"batch","input_per_m":0.625,"cached_input_per_m":0.0625,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5 | $0.625 | $5.00 | $0.0625 |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.625,"cached_input_per_m":0.0625,"output_per_m":5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.625$5.00$0.0625","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":"gpt-5","tier":"flex","input_per_m":0.625,"cached_input_per_m":0.0625,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5 | $0.625 | $5.00 | $0.0625 |","notes":"Flex processing."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":20,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$2.50$20.00$0.25","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5","name":"GPT-5","maker":"OpenAI","provider_model_id":"gpt-5","tier":"fast","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":20,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5 | $2.50 | $20.00 | $0.25 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5-chat","name":"GPT-5 Chat","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5 chat Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5-codex","name":"GPT-5 Codex","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5 Codex Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5-mini","name":"GPT-5 mini","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":0.03,"output_per_m":2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5-mini Global\tInput: $0.25 | Cached Input: $0.03 | Output: $2","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5-mini","name":"GPT-5 mini","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":0.025,"output_per_m":2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 mini — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.25$2.00$0.025","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-mini","name":"GPT-5 Mini","maker":"OpenAI","provider_model_id":"gpt-5-mini","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.025,"output_per_m":2,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-mini | $0.25 | $2.00 | $0.025 |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-mini","name":"GPT-5 Mini","maker":"OpenAI","provider_model_id":"gpt-5-mini","tier":"batch","input_per_m":0.125,"cached_input_per_m":0.0125,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-mini | $0.125 | $1.00 | $0.0125 |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5-mini","name":"GPT-5 mini","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.125,"cached_input_per_m":0.0125,"output_per_m":1,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 mini — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.125$1.00$0.0125","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-mini","name":"GPT-5 Mini","maker":"OpenAI","provider_model_id":"gpt-5-mini","tier":"flex","input_per_m":0.125,"cached_input_per_m":0.0125,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-mini | $0.125 | $1.00 | $0.0125 |","notes":"Flex processing."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5-mini","name":"GPT-5 mini","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":0.45,"cached_input_per_m":0.045,"output_per_m":3.6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 mini — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$0.45$3.60$0.045","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-mini","name":"GPT-5 Mini","maker":"OpenAI","provider_model_id":"gpt-5-mini","tier":"fast","input_per_m":0.45,"cached_input_per_m":0.045,"output_per_m":3.6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-mini | $0.45 | $3.60 | $0.045 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5-nano","name":"GPT-5 nano","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.05,"cached_input_per_m":0.01,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5-nano Global\tInput: $0.05 | Cached Input: $0.01 | Output: $0.40","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5-nano","name":"GPT-5 nano","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.05,"cached_input_per_m":0.005,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 nano — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.05$0.40$0.005","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-nano","name":"GPT-5 Nano","maker":"OpenAI","provider_model_id":"gpt-5-nano","tier":"standard","input_per_m":0.05,"cached_input_per_m":0.005,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-nano | $0.05 | $0.40 | $0.005 |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-nano","name":"GPT-5 Nano","maker":"OpenAI","provider_model_id":"gpt-5-nano","tier":"batch","input_per_m":0.025,"cached_input_per_m":0.0025,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-nano | $0.025 | $0.20 | $0.0025 |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5-nano","name":"GPT-5 nano","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.025,"cached_input_per_m":0.0025,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5 nano — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.025$0.20$0.0025","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-nano","name":"GPT-5 Nano","maker":"OpenAI","provider_model_id":"gpt-5-nano","tier":"flex","input_per_m":0.025,"cached_input_per_m":0.0025,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-nano | $0.025 | $0.20 | $0.0025 |","notes":"Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5-pro","name":"GPT-5 Pro","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":15,"cached_input_per_m":null,"output_per_m":120,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5 Pro Global\tInput: $15 | Output: $120","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-pro","name":"GPT-5 Pro","maker":"OpenAI","provider_model_id":"gpt-5-pro","tier":"standard","input_per_m":15,"cached_input_per_m":null,"output_per_m":120,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-pro | $15.00 | $120.00 | - |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-pro","name":"GPT-5 Pro","maker":"OpenAI","provider_model_id":"gpt-5-pro","tier":"batch","input_per_m":7.5,"cached_input_per_m":null,"output_per_m":60,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5-pro | $7.50 | $60.00 | - |","notes":"Batch API (asynchronous)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5-search-api","name":"GPT-5 Search API","maker":"OpenAI","provider_model_id":"gpt-5-search-api","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Search | gpt-5-search-api | $1.25 | $10.00 | $0.125 | - | - |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.1","name":"GPT-5.1","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.1 Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.1","name":"GPT-5.1","maker":"OpenAI","provider_model_id":"gpt-5.1","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.125,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.1 | $1.25 | $10.00 | $0.125 |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.1","name":"GPT-5.1","maker":"OpenAI","provider_model_id":"gpt-5.1","tier":"batch","input_per_m":0.625,"cached_input_per_m":0.0625,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.1 | $0.625 | $5.00 | $0.0625 |","notes":"Batch API (asynchronous)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.1","name":"GPT-5.1","maker":"OpenAI","provider_model_id":"gpt-5.1","tier":"flex","input_per_m":0.625,"cached_input_per_m":0.0625,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.1 | $0.625 | $5.00 | $0.0625 |","notes":"Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.1","name":"GPT-5.1","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":20,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.1 Global\tInput: $2.50 | Cached Input: $0.25 | Output: $20","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.1","name":"GPT-5.1","maker":"OpenAI","provider_model_id":"gpt-5.1","tier":"fast","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":20,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.1 | $2.50 | $20.00 | $0.25 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.1-chat","name":"GPT-5.1 Chat","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.1-chat Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.1-codex","name":"GPT-5.1 Codex","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.1-codex Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.1-codex-max Global\tInput: $1.25 | Cached Input: $0.13 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":0.03,"output_per_m":2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.1-codex-mini Global\tInput: $0.25 | Cached Input: $0.03 | Output: $2","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.18,"output_per_m":14,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.2 Global\tInput: $1.75 | Cached Input: $0.18 | Output: $14","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.175,"output_per_m":14,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.2 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.75$14.00$0.175","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":"gpt-5.2","tier":"standard","input_per_m":1.75,"cached_input_per_m":0.175,"output_per_m":14,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.2 | $1.75 | $14.00 | $0.175 |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":"gpt-5.2","tier":"batch","input_per_m":0.875,"cached_input_per_m":0.0875,"output_per_m":7,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.2 | $0.875 | $7.00 | $0.0875 |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.875,"cached_input_per_m":0.0875,"output_per_m":7,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.2 — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.875$7.00$0.0875","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":"gpt-5.2","tier":"flex","input_per_m":0.875,"cached_input_per_m":0.0875,"output_per_m":7,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.2 | $0.875 | $7.00 | $0.0875 |","notes":"Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":3.5,"cached_input_per_m":0.35,"output_per_m":28,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.2 Global\tInput: $3.50 | Cached Input: $0.35 | Output: $28","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":3.5,"cached_input_per_m":0.35,"output_per_m":28,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.2 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$3.50$28.00$0.35","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.2","name":"GPT-5.2","maker":"OpenAI","provider_model_id":"gpt-5.2","tier":"fast","input_per_m":3.5,"cached_input_per_m":0.35,"output_per_m":28,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.2 | $3.50 | $28.00 | $0.35 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.2-chat","name":"GPT-5.2 Chat (latest)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.18,"output_per_m":14,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.2-chat latest Global\tInput: $1.75 | Cached Input: $0.18 | Output: $14","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.2-codex","name":"GPT-5.2 Codex","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.18,"output_per_m":14,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.2 Codex Global\tInput: $1.75 | Cached Input: $0.18 | Output: $14","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.2-pro","name":"GPT-5.2 pro","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":21,"cached_input_per_m":null,"output_per_m":168,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.2 pro — Processing modePrompt lengthInputOutput: Standard All prompts$21.00$168.00","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.2-pro","name":"GPT-5.2 Pro","maker":"OpenAI","provider_model_id":"gpt-5.2-pro","tier":"standard","input_per_m":21,"cached_input_per_m":null,"output_per_m":168,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.2-pro | $21.00 | $168.00 | - |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.2-pro","name":"GPT-5.2 Pro","maker":"OpenAI","provider_model_id":"gpt-5.2-pro","tier":"batch","input_per_m":10.5,"cached_input_per_m":null,"output_per_m":84,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.2-pro | $10.50 | $84.00 | - |","notes":"Batch API (asynchronous)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.3-chat","name":"GPT-5.3 Chat","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.18,"output_per_m":14,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.3 Chat Global\tInput: $1.75 | Cached Input: $0.18 | Output: $14","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.3-codex","name":"GPT-5.3 Codex","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.18,"output_per_m":14,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.3 Codex Global\tInput: $1.75 | Cached Input: $0.18 | Output: $14","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.3-codex","name":"GPT-5.3-Codex","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.75,"cached_input_per_m":0.175,"output_per_m":14,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.3-Codex — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.75$14.00$0.175","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.3-codex","name":"GPT-5.3-Codex","maker":"OpenAI","provider_model_id":"gpt-5.3-codex","tier":"standard","input_per_m":1.75,"cached_input_per_m":0.175,"output_per_m":14,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Codex | gpt-5.3-codex | $1.75 | $14.00 | $0.175 | - | - |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.3-codex","name":"GPT-5.3-Codex","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":3.5,"cached_input_per_m":0.35,"output_per_m":28,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.3-Codex — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$3.50$28.00$0.35","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.3-codex","name":"GPT-5.3-Codex","maker":"OpenAI","provider_model_id":"gpt-5.3-codex","tier":"fast","input_per_m":3.5,"cached_input_per_m":0.35,"output_per_m":28,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Codex | gpt-5.3-codex | $3.50 | $28.00 | $0.35 |","notes":"Fast mode."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":"openai.gpt-5.4","tier":"standard","input_per_m":2.75,"cached_input_per_m":0.275,"output_per_m":16.5,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html","checked":"2026-11-14","quote":"In-Region | $2.75 | — | $0.275 | $16.50","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. In-Region only (includes a 10% fee over OpenAI rates). Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 (<272k context length) Global\tInput: $2.50 | Cached Input: $0.25 | Output: $15","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 — Processing modePrompt lengthInputOutputCache read: Standard ≤ 272K tokens$2.50$15.00$0.25","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":"gpt-5.4","tier":"standard","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4 (<272K context length) | $2.50 | $15.00 | $0.25 | - | - | $5.00 | $22.50 | $0.50 | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 (<272k context length) Global\tInput: $1.25 | Cached Input: $0.13 | Output: $7.50","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":"gpt-5.4","tier":"batch","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4 (<272K context length) | $1.25 | $7.50 | $0.13 | - | - | $2.50 | $11.25 | $0.25 | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 — Processing modePrompt lengthInputOutputCache read: Flex Mode ≤ 272K tokens$1.25$7.50$0.13","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":"gpt-5.4","tier":"flex","input_per_m":1.25,"cached_input_per_m":0.13,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4 (<272K context length) | $1.25 | $7.50 | $0.13 | - | - | $2.50 | $11.25 | $0.25 | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 (<272k context length) Global\tInput: $5 | Cached Input: $0.50 | Output: $30","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$5.00$30.00$0.50","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4","name":"GPT-5.4","maker":"OpenAI","provider_model_id":"gpt-5.4","tier":"fast","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4 (<272K context length) | $5.00 | $30.00 | $0.50 | - | - | - | - | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-mini","name":"GPT-5.4 mini","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":0.08,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 mini Global\tInput: $0.75 | Cached Input: $0.08 | Output: $4.50","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-mini","name":"GPT-5.4 mini","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 mini — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.75$4.50$0.075","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-mini","name":"GPT-5.4 Mini","maker":"OpenAI","provider_model_id":"gpt-5.4-mini","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.075,"output_per_m":4.5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-mini | $0.75 | $4.50 | $0.075 |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-mini","name":"GPT-5.4 mini","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.38,"cached_input_per_m":0.04,"output_per_m":2.25,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 mini Global\tInput: $0.38 | Cached Input: $0.04 | Output: $2.25","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-mini","name":"GPT-5.4 Mini","maker":"OpenAI","provider_model_id":"gpt-5.4-mini","tier":"batch","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":2.25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-mini | $0.375 | $2.25 | $0.0375 |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-mini","name":"GPT-5.4 mini","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":2.25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 mini — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.375$2.25$0.0375","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-mini","name":"GPT-5.4 Mini","maker":"OpenAI","provider_model_id":"gpt-5.4-mini","tier":"flex","input_per_m":0.375,"cached_input_per_m":0.0375,"output_per_m":2.25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-mini | $0.375 | $2.25 | $0.0375 |","notes":"Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-mini","name":"GPT-5.4 mini","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":9,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 mini Global\tInput: $1.50 | Cached Input: $0.15 | Output: $9","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-mini","name":"GPT-5.4 mini","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":9,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 mini — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$1.50$9.00$0.15","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-mini","name":"GPT-5.4 Mini","maker":"OpenAI","provider_model_id":"gpt-5.4-mini","tier":"fast","input_per_m":1.5,"cached_input_per_m":0.15,"output_per_m":9,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-mini | $1.50 | $9.00 | $0.15 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-nano","name":"GPT-5.4 nano","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 nano Global\tInput: $0.20 | Cached Input: $0.02 | Output: $1.25","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-nano","name":"GPT-5.4 nano","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 nano — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.20$1.25$0.02","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-nano","name":"GPT-5.4 Nano","maker":"OpenAI","provider_model_id":"gpt-5.4-nano","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-nano | $0.20 | $1.25 | $0.02 |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-nano","name":"GPT-5.4 Nano","maker":"OpenAI","provider_model_id":"gpt-5.4-nano","tier":"batch","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.625,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-nano | $0.10 | $0.625 | $0.01 |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-nano","name":"GPT-5.4 nano","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.625,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 nano — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$0.10$0.625$0.01","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-nano","name":"GPT-5.4 Nano","maker":"OpenAI","provider_model_id":"gpt-5.4-nano","tier":"flex","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.625,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-nano | $0.10 | $0.625 | $0.01 |","notes":"Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-pro","name":"GPT-5.4 Pro","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":30,"cached_input_per_m":null,"output_per_m":180,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.4 Pro (<272k context length) Global\tInput: $30 | Output: $180","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-pro","name":"GPT-5.4 pro","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":30,"cached_input_per_m":null,"output_per_m":180,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 pro — Processing modePrompt lengthInputOutput: Standard ≤ 272K tokens$30.00$180.00","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-pro","name":"GPT-5.4 Pro","maker":"OpenAI","provider_model_id":"gpt-5.4-pro","tier":"standard","input_per_m":30,"cached_input_per_m":null,"output_per_m":180,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-pro (<272K context length) | $30.00 | $180.00 | - | - | - | $60.00 | $270.00 | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-pro","name":"GPT-5.4 Pro","maker":"OpenAI","provider_model_id":"gpt-5.4-pro","tier":"batch","input_per_m":15,"cached_input_per_m":null,"output_per_m":90,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-pro (<272K context length) | $15.00 | $90.00 | - | - | - | $30.00 | $135.00 | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.4-pro","name":"GPT-5.4 pro","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":15,"cached_input_per_m":null,"output_per_m":90,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.4 pro — Processing modePrompt lengthInputOutput: Flex Mode ≤ 272K tokens$15.00$90.00","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.4-pro","name":"GPT-5.4 Pro","maker":"OpenAI","provider_model_id":"gpt-5.4-pro","tier":"flex","input_per_m":15,"cached_input_per_m":null,"output_per_m":90,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.4-pro (<272K context length) | $15.00 | $90.00 | - | - | - | $30.00 | $135.00 | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Flex processing."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"openai.gpt-5.5","tier":"standard","input_per_m":5.5,"cached_input_per_m":0.55,"output_per_m":33,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html","checked":"2026-11-14","quote":"In-Region | $5.50 | — | $0.55 | $33.00","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. In-Region only (includes a 10% fee over OpenAI rates). Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.5 Global\tInput: $5 | Cached Input: $0.50 | Output: $30","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.5 — Processing modePrompt lengthInputOutputCache read: Standard ≤ 272K tokens$5.00$30.00$0.50","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"openai/gpt-5.5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-5-5/39c41644-705e-4f94-894f-475b0e3877a9","checked":"2026-11-15","quote":"Price ≤ 272k token Input $5.00 Output $30.00 Cache Read $0.50 Cache Write - > 272k token Input $10.00 Output $45.00","notes":"Long-prompt tier: prompts over 272,000 tokens cost 10 in / 45 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"gpt-5.5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5 (<272K context length) | $5.00 | $30.00 | $0.50 | - | - | $10.00 | $45.00 | $1.00 | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"openai/gpt-5.5","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-5.5` | 5.00 (≤272k) 10.00 (>272k) | 30.00 (≤272k) 45.00 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 10.00 input, 45.00 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"gpt-5.5","tier":"batch","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5 (<272K context length) | $2.50 | $15.00 | $0.25 | - | - | $5.00 | $22.50 | $0.50 | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.5 — Processing modePrompt lengthInputOutputCache read: Flex Mode ≤ 272K tokens$2.50$15.00$0.25","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"gpt-5.5","tier":"flex","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5 (<272K context length) | $2.50 | $15.00 | $0.25 | - | - | $5.00 | $22.50 | $0.50 | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":12.5,"cached_input_per_m":1.25,"output_per_m":75,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.5 Global\tInput: $12.50 | Cached Input: $1.25 | Output: $75","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":12.5,"cached_input_per_m":1.25,"output_per_m":75,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.5 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$12.50$75.00$1.25","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5","name":"GPT-5.5","maker":"OpenAI","provider_model_id":"gpt-5.5","tier":"fast","input_per_m":12.5,"cached_input_per_m":1.25,"output_per_m":75,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5 (<272K context length) | $12.50 | $75.00 | $1.25 | - | - | - | - | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5-cyber-preview","name":"GPT-5.5 Cyber Preview","maker":"OpenAI","provider_model_id":"gpt-5.5-cyber-preview","tier":"standard","input_per_m":12.5,"cached_input_per_m":1.25,"output_per_m":75,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Cyber — Trusted Access: Daybreak | gpt-5.5-cyber-preview (short context) | $12.50 | $75.00 | $1.25 | - | - |","notes":"Short context; longer prompts bill at the long-context rate where published. Trusted Access program only (Cyber — Trusted Access: Daybreak)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5-pro","name":"GPT-5.5 Pro","maker":"OpenAI","provider_model_id":"gpt-5.5-pro","tier":"standard","input_per_m":30,"cached_input_per_m":null,"output_per_m":180,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5-pro (<272K context length) | $30.00 | $180.00 | - | - | - | $60.00 | $270.00 | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5-pro","name":"GPT-5.5 Pro","maker":"OpenAI","provider_model_id":"gpt-5.5-pro","tier":"batch","input_per_m":15,"cached_input_per_m":null,"output_per_m":90,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5-pro (<272K context length) | $15.00 | $90.00 | - | - | - | - | - | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.5-pro","name":"GPT-5.5 Pro","maker":"OpenAI","provider_model_id":"gpt-5.5-pro","tier":"flex","input_per_m":15,"cached_input_per_m":null,"output_per_m":90,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.5-pro (<272K context length) | $15.00 | $90.00 | - | - | - | - | - | - | - | - |","notes":"Prompts under 272K tokens (short context); longer prompts bill at the long-context rate. Flex processing."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-cyber","name":"GPT-5.6 Cyber","maker":"OpenAI","provider_model_id":"gpt-5.6-cyber","tier":"standard","input_per_m":12.5,"cached_input_per_m":1.25,"output_per_m":75,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Cyber — Trusted Access: Daybreak | gpt-5.6-cyber (short context) | $12.50 | $75.00 | $1.25 | $15.625 | $31.25 |","notes":"Short context; longer prompts bill at the long-context rate where published. Trusted Access program only (Cyber — Trusted Access: Daybreak)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":"openai.gpt-5.6-luna","tier":"standard","input_per_m":0.22,"cached_input_per_m":0.022,"output_per_m":1.32,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html","checked":"2026-11-14","quote":"In-Region | $0.22 | $0.275 | $0.022 | $1.32","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $0.20 / cache read $0.02 / $1.20. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-luna (short context) Global\tInput: $0.20 | Cached Input: $0.02 | Cache writes: $0.25 | Output: $1.20","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $0.25 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Luna — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$0.20$1.20$0.25$0.02","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6-Luna","maker":"OpenAI","provider_model_id":"openai/gpt-5.6-luna","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":6,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-5-6-luna/16746f80-0f3e-4b41-a812-8627ebbc245b","checked":"2026-11-15","quote":"Price ≤ 272k token Input $1.00 Output $6.00 Cache Read $0.10 Cache Write $1.25 > 272k token Input $2.00 Output $9.00","notes":"Long-prompt tier: prompts over 272,000 tokens cost 2 in / 9 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":"gpt-5.6-luna","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | $0.50 | $0.40 | $1.80 | $0.04 | $0.50 | $1.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":"openai/gpt-5.6-luna","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-5.6-luna` | 0.20 (≤272k) 0.40 (>272k) | 1.20 (≤272k) 1.80 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 0.40 input, 1.80 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":"gpt-5.6-luna","tier":"batch","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-luna | $0.10 | $0.60 | $0.01 | $0.125 | $0.25 | $0.20 | $0.90 | $0.02 | $0.25 | $0.50 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-luna (short context) Global\tInput: $0.10 | Cached Input: $0.01 | Cache writes: $0.13 | Output: $0.60","notes":"Azure OpenAI Global deployment, \"Flex Pricing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $0.13 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Luna — Processing modePrompt lengthInputOutputCache writeCache read: Flex Mode ≤ 272K tokens$0.10$0.60$0.125$0.01","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":"gpt-5.6-luna","tier":"flex","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-luna | $0.10 | $0.60 | $0.01 | $0.125 | $0.25 | $0.20 | $0.90 | $0.02 | $0.25 | $0.50 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":0.4,"cached_input_per_m":0.04,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Luna — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$0.40$2.40$0.50$0.04","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-luna","name":"GPT-5.6 Luna","maker":"OpenAI","provider_model_id":"gpt-5.6-luna","tier":"fast","input_per_m":0.4,"cached_input_per_m":0.04,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-luna | $0.40 | $2.40 | $0.04 | $0.50 | $1.00 | $0.80 | $3.60 | $0.08 | $1.00 | $2.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":"openai.gpt-5.6-sol","tier":"standard","input_per_m":4.4,"cached_input_per_m":0.44,"output_per_m":22,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html","checked":"2026-11-14","quote":"In-Region | $4.40 | $5.50 | $0.44 | $22.00","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $4.00 / cache read $0.40 / $20.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":20,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-sol (short context) Global\tInput: $4 | Cached Input: $0.40 | Cache writes: $5 | Output: $20","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":20,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$4.00$20.00$5.00$0.40","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6-Sol","maker":"OpenAI","provider_model_id":"openai/gpt-5.6-sol","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-5-6-sol/97615ebb-523f-4d09-814d-f022033984f9","checked":"2026-11-15","quote":"Price ≤ 272k token Input $5.00 Output $30.00 Cache Read $0.50 Cache Write $6.25 > 272k token Input $10.00 Output $45.00","notes":"Long-prompt tier: prompts over 272,000 tokens cost 10 in / 45 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":"gpt-5.6-sol","tier":"standard","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":20,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-sol | $4.00 | $20.00 | $0.40 | $5.00 | $10.00 | $8.00 | $30.00 | $0.80 | $10.00 | $20.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. OpenAI says GPT-5.6 Sol's promotional pricing is available until November 30, 2026."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":"openai/gpt-5.6-sol","tier":"standard","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":20,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-5.6-sol` | 4.00 (≤272k) 8.00 (>272k) | 20.00 (≤272k) 30.00 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 8.00 input, 30.00 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":"gpt-5.6-sol","tier":"batch","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-sol | $2.00 | $10.00 | $0.20 | $2.50 | $5.00 | $4.00 | $15.00 | $0.40 | $5.00 | $10.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous). OpenAI says GPT-5.6 Sol's promotional pricing is available until November 30, 2026."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-sol (short context) Global\tInput: $2 | Cached Input: $0.20 | Cache writes: $2.50 | Output: $10","notes":"Azure OpenAI Global deployment, \"Flex Pricing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $2.5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Flex Mode ≤ 272K tokens$2.00$10.00$2.50$0.20","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":"gpt-5.6-sol","tier":"flex","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-sol | $2.00 | $10.00 | $0.20 | $2.50 | $5.00 | $4.00 | $15.00 | $0.40 | $5.00 | $10.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing. OpenAI says GPT-5.6 Sol's promotional pricing is available until November 30, 2026."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":8,"cached_input_per_m":0.8,"output_per_m":40,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-sol (short context) Global\tInput: $8 | Cached Input: $0.80 | Cache writes: $10 | Output: $40","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $10 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":8,"cached_input_per_m":0.8,"output_per_m":40,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$8.00$40.00$10.00$0.80","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-sol","name":"GPT-5.6 Sol","maker":"OpenAI","provider_model_id":"gpt-5.6-sol","tier":"fast","input_per_m":8,"cached_input_per_m":0.8,"output_per_m":40,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-sol | $8.00 | $40.00 | $0.80 | $10.00 | $20.00 | $16.00 | $60.00 | $1.60 | $20.00 | $40.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing). OpenAI says GPT-5.6 Sol's promotional pricing is available until November 30, 2026."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":"openai.gpt-5.6-terra","tier":"standard","input_per_m":2.2,"cached_input_per_m":0.22,"output_per_m":13.2,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html","checked":"2026-11-14","quote":"In-Region | $2.20 | $2.75 | $0.22 | $13.20","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $2.00 / cache read $0.20 / $12.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":12,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-terra (short context) Global\tInput: $2 | Cached Input: $0.20 | Cache writes: $2.50 | Output: $12","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $2.5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":12,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$2.00$12.00$2.50$0.20","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6-Terra","maker":"OpenAI","provider_model_id":"openai/gpt-5.6-terra","tier":"standard","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":15,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-5-6-terra/a16c9277-baba-460a-8962-71eeb778ca1d","checked":"2026-11-15","quote":"Price ≤ 272k token Input $2.50 Output $15.00 Cache Read $0.25 Cache Write $3.125 > 272k token Input $5.00 Output $22.50","notes":"Long-prompt tier: prompts over 272,000 tokens cost 5 in / 22.5 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":"gpt-5.6-terra","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":12,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-terra | $2.00 | $12.00 | $0.20 | $2.50 | $5.00 | $4.00 | $18.00 | $0.40 | $5.00 | $10.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":"openai/gpt-5.6-terra","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":12,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-5.6-terra` | 2.00 (≤272k) 4.00 (>272k) | 12.00 (≤272k) 18.00 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 4.00 input, 18.00 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":"gpt-5.6-terra","tier":"batch","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-terra | $1.00 | $6.00 | $0.10 | $1.25 | $2.50 | $2.00 | $9.00 | $0.20 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-terra (short context) Global\tInput: $1 | Cached Input: $0.10 | Cache writes: $1.25 | Output: $6","notes":"Azure OpenAI Global deployment, \"Flex Pricing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $1.25 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Flex Mode ≤ 272K tokens$1.00$6.00$1.25$0.10","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":"gpt-5.6-terra","tier":"flex","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":6,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-terra | $1.00 | $6.00 | $0.10 | $1.25 | $2.50 | $2.00 | $9.00 | $0.20 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":24,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-5.6-terra (short context) Global\tInput: $4 | Cached Input: $0.40 | Cache writes: $5 | Output: $24","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":24,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-5.6 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$4.00$24.00$5.00$0.40","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-5.6-terra","name":"GPT-5.6 Terra","maker":"OpenAI","provider_model_id":"gpt-5.6-terra","tier":"fast","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":24,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-5.6-terra | $4.00 | $24.00 | $0.40 | $5.00 | $10.00 | $8.00 | $36.00 | $0.80 | $10.00 | $20.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"openai.gpt-6-astra","tier":"standard","input_per_m":11,"cached_input_per_m":1.1,"output_per_m":55,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html","checked":"2026-11-14","quote":"In-Region | $11.00 | $13.75 | $1.10 | $55.00","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $10.00 / cache read $1.00 / $50.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-6 Astra (short context) Global\tInput: $10 | Cached Input: $1 | Cache writes: $12.50 | Output: $50","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $12.5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6 Astra — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$10.00$50.00$12.50$1.00","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6-Astra","maker":"OpenAI","provider_model_id":"openai/gpt-6-astra","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-6-astra/c384aac4-dd25-424a-a86d-591dbad9b2e0","checked":"2026-11-15","quote":"Price ≤ 272k token Input $10.00 Output $50.00 Cache Read $1.00 Cache Write $12.50 > 272k token Input $20.00 Output $75.00","notes":"Long-prompt tier: prompts over 272,000 tokens cost 20 in / 75 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"gpt-6-astra","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $25.00 | $20.00 | $75.00 | $2.00 | $25.00 | $50.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"openai/gpt-6-astra","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-6-astra` | 10.00 (≤272k) 20.00 (>272k) | 50.00 (≤272k) 75.00 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 20.00 input, 75.00 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"gpt-6-astra","tier":"batch","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-astra | $5.00 | $25.00 | $0.50 | $6.25 | $12.50 | $10.00 | $37.50 | $1.00 | $12.50 | $25.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6 Astra — Processing modePrompt lengthInputOutputCache writeCache read: Flex Mode ≤ 272K tokens$5.00$25.00$6.25$0.50","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"gpt-6-astra","tier":"flex","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-astra | $5.00 | $25.00 | $0.50 | $6.25 | $12.50 | $10.00 | $37.50 | $1.00 | $12.50 | $25.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra (Ultrafast)","maker":"OpenAI","provider_model_id":"openai.gpt-6-astra","tier":"fast","input_per_m":66,"cached_input_per_m":6.6,"output_per_m":330,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html","checked":"2026-11-14","quote":"In-Region (us-east-1) | $66.00 | $82.50 | $6.60 | $330.00","notes":"Ultrafast tier, short context, in-region us-east-1 row (six times Standard)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":20,"cached_input_per_m":2,"output_per_m":100,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6 Astra — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$20.00$100.00$25.00$2.00","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"gpt-6-astra","tier":"fast","input_per_m":20,"cached_input_per_m":2,"output_per_m":100,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-astra | $20.00 | $100.00 | $2.00 | $25.00 | $50.00 | $40.00 | $150.00 | $4.00 | $50.00 | $100.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-astra","name":"GPT-6 Astra","maker":"OpenAI","provider_model_id":"gpt-6-astra","tier":"ultrafast","input_per_m":60,"cached_input_per_m":6,"output_per_m":300,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-astra | $60.00 | $300.00 | $6.00 | $75.00 | $150.00 | $120.00 | $450.00 | $12.00 | $150.00 | $300.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Ultrafast mode."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-astra-law","name":"GPT-6 Astra for Law","maker":"OpenAI","provider_model_id":"gpt-6-astra-law","tier":"standard","input_per_m":10,"cached_input_per_m":1,"output_per_m":50,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Legal | gpt-6-astra-law | $10.00 | $50.00 | $1.00 | - | - |","notes":"OpenAI says this promotional pricing is available at least through December 31, 2026."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-cyber","name":"GPT-6 Cyber","maker":"OpenAI","provider_model_id":"gpt-6-cyber","tier":"standard","input_per_m":20,"cached_input_per_m":2,"output_per_m":100,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Cyber — Trusted Access: Daybreak | gpt-6-cyber (short context) | $20.00 | $100.00 | $2.00 | $25.00 | $50.00 |","notes":"Short context; longer prompts bill at the long-context rate where published. Trusted Access program only (Cyber — Trusted Access: Daybreak)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"openai.gpt-6-luna","tier":"standard","input_per_m":0.11,"cached_input_per_m":0.011,"output_per_m":0.55,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-luna.html","checked":"2026-11-14","quote":"Mantle in-Region | $0.11 | $0.1375 | $0.011 | $0.55","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $0.10 / cache read $0.01 / $0.50. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-6 Luna (short context) Global\tInput: $0.10 | Cached Input: $0.01 | Cache writes: $0.125 | Output: $0.50","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $0.125 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6 Luna — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$0.10$0.50$0.125$0.01","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"openai/gpt-6-luna","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-6-luna/6a7bb75b-4b97-49bc-b8a6-38dc23757075","checked":"2026-11-15","quote":"Price ≤ 272k token Input $0.10 Output $0.50 Cache Read $0.01 Cache Write $0.125 > 272k token Input $0.20 Output $0.75","notes":"Long-prompt tier: prompts over 272,000 tokens cost 0.2 in / 0.75 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"gpt-6-luna","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-luna | $0.10 | $0.50 | $0.01 | $0.125 | $0.25 | $0.20 | $0.75 | $0.02 | $0.25 | $0.50 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"openai/gpt-6-luna","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-6-luna` | 0.10 (≤272k) 0.20 (>272k) | 0.50 (≤272k) 0.75 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 0.20 input, 0.75 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"gpt-6-luna","tier":"batch","input_per_m":0.05,"cached_input_per_m":0.005,"output_per_m":0.25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-luna | $0.05 | $0.25 | $0.005 | $0.0625 | $0.125 | $0.10 | $0.375 | $0.01 | $0.125 | $0.25 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"gpt-6-luna","tier":"flex","input_per_m":0.05,"cached_input_per_m":0.005,"output_per_m":0.25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-luna | $0.05 | $0.25 | $0.005 | $0.0625 | $0.125 | $0.10 | $0.375 | $0.01 | $0.125 | $0.25 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-luna","name":"GPT-6 Luna","maker":"OpenAI","provider_model_id":"gpt-6-luna","tier":"fast","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-luna | $0.20 | $1.00 | $0.02 | $0.25 | $0.50 | $0.40 | $1.50 | $0.04 | $0.50 | $1.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-rosalind","name":"GPT-6 Rosalind","maker":"OpenAI","provider_model_id":"gpt-6-rosalind","tier":"standard","input_per_m":15,"cached_input_per_m":1.5,"output_per_m":75,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Life Sciences — Trusted Access: Rosalind | gpt-6-rosalind (short context) | $15.00 | $75.00 | $1.50 | $18.75 | $37.50 |","notes":"Short context; longer prompts bill at the long-context rate where published. Trusted Access program only (Life Sciences — Trusted Access: Rosalind)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"openai.gpt-6-sol","tier":"standard","input_per_m":2.2,"cached_input_per_m":0.22,"output_per_m":11,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-sol.html","checked":"2026-11-14","quote":"Mantle in-Region | $2.20 | $2.75 | $0.22 | $11.00","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $2.00 / cache read $0.20 / $10.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-6 Sol (short context) Global\tInput: $2 | Cached Input: $0.20 | Cache writes: $2.50 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $2.5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$2.00$10.00$2.50$0.20","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"openai/gpt-6-sol","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-6-sol/12b03079-038a-44f6-ac45-a8a84b6588e5","checked":"2026-11-15","quote":"Price ≤ 272k token Input $2.00 Output $10.00 Cache Read $0.20 Cache Write $2.50 > 272k token Input $4.00 Output $15.00","notes":"Long-prompt tier: prompts over 272,000 tokens cost 4 in / 15 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"gpt-6-sol","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-sol | $2.00 | $10.00 | $0.20 | $2.50 | $5.00 | $4.00 | $15.00 | $0.40 | $5.00 | $10.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"openai/gpt-6-sol","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-6-sol` | 2.00 (≤272k) 4.00 (>272k) | 10.00 (≤272k) 15.00 (>272k) | 90% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 4.00 input, 15.00 output. Cached price derived from \"90% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"gpt-6-sol","tier":"batch","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-sol | $1.00 | $5.00 | $0.10 | $1.25 | $2.50 | $2.00 | $7.50 | $0.20 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"gpt-6-sol","tier":"flex","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-sol | $1.00 | $5.00 | $0.10 | $1.25 | $2.50 | $2.00 | $7.50 | $0.20 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":20,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-6 Sol (short context) Global\tInput: $4 | Cached Input: $0.40 | Cache writes: $5 | Output: $20","notes":"Azure OpenAI Global deployment, \"Priority Processing (1M Tokens)\" column. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $5 per 1M."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6-sol","name":"GPT-6 Sol","maker":"OpenAI","provider_model_id":"gpt-6-sol","tier":"fast","input_per_m":4,"cached_input_per_m":0.4,"output_per_m":20,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6-sol | $4.00 | $20.00 | $0.40 | $5.00 | $10.00 | $8.00 | $30.00 | $0.80 | $10.00 | $20.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"openai.gpt-6.1-sol","tier":"standard","input_per_m":2.2,"cached_input_per_m":0.11,"output_per_m":11,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html","checked":"2026-11-14","quote":"Regional (bedrock-mantle in US East (N. Virginia)) | $2.20 | $2.75 | $0.11 | $11.00","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $2.00 / cache read $0.10 / $10.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-6.1 Sol (short context) Global\tInput: $2 | Cached Input: $0.10 | Cache writes: $2.50 | Output: $10","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $2.5 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6.1 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$2.00$10.00$2.50$0.10","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"gpt-6.1-sol","maker":"OpenAI","provider_model_id":"openai/gpt-6.1-sol","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":1050000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/gpt-6-1-sol/6aa0142b-ca73-4262-b123-dfc4b5405a30","checked":"2026-11-15","quote":"Price ≤ 272k token Input $2.00 Output $10.00 Cache Read $0.10 Cache Write $2.50 > 272k token Input $4.00 Output $15.00","notes":"Long-prompt tier: prompts over 272,000 tokens cost 4 in / 15 out."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"gpt-6.1-sol","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-sol | $2.00 | $10.00 | $0.10 | $2.50 | $5.00 | $4.00 | $15.00 | $0.20 | $5.00 | $10.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"openai/gpt-6.1-sol","tier":"standard","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`openai/gpt-6.1-sol` | 2.00 (≤272k) 4.00 (>272k) | 10.00 (≤272k) 15.00 (>272k) | 95% off input","notes":"Third-party model resold through the Perplexity Agent API. Prompts over 272k tokens: 4.00 input, 15.00 output. Cached price derived from \"95% off input\"."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"gpt-6.1-sol","tier":"batch","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-sol | $1.00 | $5.00 | $0.05 | $1.25 | $2.50 | $2.00 | $7.50 | $0.10 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6.1 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Flex Mode ≤ 272K tokens$1.00$5.00$1.25$0.05","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"gpt-6.1-sol","tier":"flex","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-sol | $1.00 | $5.00 | $0.05 | $1.25 | $2.50 | $2.00 | $7.50 | $0.10 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol (Ultrafast)","maker":"OpenAI","provider_model_id":"openai.gpt-6.1-sol","tier":"fast","input_per_m":13.2,"cached_input_per_m":0.66,"output_per_m":66,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html","checked":"2026-11-14","quote":"In-Region (bedrock-mantle in us-east-1) | $13.20 | $16.50 | $0.66 | $66.00","notes":"Ultrafast tier, short context, in-region us-east-1 row (six times Standard)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6.1 Sol — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$4.00$20.00$5.00$0.20","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"gpt-6.1-sol","tier":"fast","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-sol | $4.00 | $20.00 | $0.20 | $5.00 | $10.00 | $8.00 | $30.00 | $0.40 | $10.00 | $20.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-sol","name":"GPT-6.1 Sol","maker":"OpenAI","provider_model_id":"gpt-6.1-sol","tier":"ultrafast","input_per_m":12,"cached_input_per_m":0.6,"output_per_m":60,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-sol | $12.00 | $60.00 | $0.60 | $15.00 | $30.00 | $24.00 | $90.00 | $1.20 | $30.00 | $60.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Ultrafast mode."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":"openai.gpt-6.1-terra","tier":"standard","input_per_m":1.1,"cached_input_per_m":0.055,"output_per_m":5.5,"context":1050000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-terra.html","checked":"2026-11-14","quote":"In-Region | $1.10 | $1.375 | $0.055 | $5.50","notes":"Bedrock model card, Standard tier, commercial regions, short context (≤ 272K input tokens), in-region / US geo row. Global CRIS: $1.00 / cache read $0.05 / $5.00. Columns: input | 30-min cache write | cache read | output. Context window 1,050,000 tokens per the card."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-6.1 Terra Short Context Global\tInput: $1 | Cached Input: $0.05 | Cache writes: $1.25 | Output: $5","notes":"Azure OpenAI Global (global standard) deployment. Short-context rate (≤ 272K input tokens); long-context rows are higher. Cache writes $1.25 per 1M."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6.1 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Standard ≤ 272K tokens$1.00$5.00$1.25$0.05","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":"gpt-6.1-terra","tier":"standard","input_per_m":1,"cached_input_per_m":0.05,"output_per_m":5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-terra | $1.00 | $5.00 | $0.05 | $1.25 | $2.50 | $2.00 | $7.50 | $0.10 | $2.50 | $5.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":"gpt-6.1-terra","tier":"batch","input_per_m":0.5,"cached_input_per_m":0.025,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-terra | $0.50 | $2.50 | $0.025 | $0.625 | $1.25 | $1.00 | $3.75 | $0.05 | $1.25 | $2.50 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Batch API (asynchronous)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":"gpt-6.1-terra","tier":"flex","input_per_m":0.5,"cached_input_per_m":0.025,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-terra | $0.50 | $2.50 | $0.025 | $0.625 | $1.25 | $1.00 | $3.75 | $0.05 | $1.25 | $2.50 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Flex processing."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"GPT-6.1 Terra — Processing modePrompt lengthInputOutputCache writeCache read: Fast Mode ≤ 272K tokens$2.00$10.00$2.50$0.10","notes":"Prompts ≤ 272K tokens; long-context rates are higher."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-6.1-terra","name":"GPT-6.1 Terra","maker":"OpenAI","provider_model_id":"gpt-6.1-terra","tier":"fast","input_per_m":2,"cached_input_per_m":0.1,"output_per_m":10,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| gpt-6.1-terra | $2.00 | $10.00 | $0.10 | $2.50 | $5.00 | $4.00 | $15.00 | $0.20 | $5.00 | $10.00 |","notes":"Short context (up to 272K input tokens); longer prompts bill at the long-context rate. Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-chat-latest","name":"GPT-Chat Latest (10142026)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"GPT-Chat Latest 10142026 Global\tInput: $5 | Cached Input: $0.50 | Output: $30","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-chat-latest","name":"GPT Chat Latest","maker":"OpenAI","provider_model_id":"chat-latest","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":30,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| ChatGPT | chat-latest | $5.00 | $30.00 | $0.50 | - | - |","notes":""},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"GPT OSS 120B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.037,"cached_input_per_m":0.037,"output_per_m":0.187,"context":131072,"precision":null,"source_url":"https://akashml.com/models/gpt-oss-120b","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read GPT OSS 120B $0.037 $0.187 $0.037","notes":"Labelled \"Limited Trial\" on AkashML."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-120b $0.15 $0.60","notes":"Standard tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"gpt-oss-120b\tInput: $0.15 | Output: $0.60","notes":"Azure OpenAI page, \"Open Source Models\" table (no deployment type stated; us-east value in the page data)."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"GPT OSS 120B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"GPT OSS 120B $0.10 — $0.50","notes":""},{"provider":"cerebras","provider_name":"Cerebras","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"GPT OSS 120B","maker":"OpenAI","provider_model_id":"gpt-oss-120b","tier":"standard","input_per_m":0.35,"cached_input_per_m":0.35,"output_per_m":0.75,"context":131072,"precision":null,"source_url":"https://www.cerebras.ai/pricing","checked":"2026-11-14","quote":"GPT OSS 120B ~3000 tokens/s $0.35/M tokens $0.75/M tokens","notes":"Developer (pay-as-you-go) tier. Cached input billed at the standard input rate (inference-docs.cerebras.ai/capabilities/prompt-caching). Paid context stated as \"131k tokens\" (inference-docs.cerebras.ai/models/openai-oss)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"@cf/openai/gpt-oss-120b","tier":"standard","input_per_m":0.35,"cached_input_per_m":null,"output_per_m":0.75,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/openai/gpt-oss-120b $0.350 per M input tokens $0.750 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"OpenAI GPT OSS 120B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.03,"cached_input_per_m":null,"output_per_m":0.17,"context":131072,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"OpenAI GPT OSS 120B $0.03 $0.17 -","notes":""},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"GPT-OSS 120B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.05,"cached_input_per_m":0.05,"output_per_m":0.25,"context":128000,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"GPT-OSS 120B $0.05 $0.25 $0.05","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.037,"cached_input_per_m":null,"output_per_m":0.17,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/openai/gpt-oss-120b","checked":"2026-11-14","quote":"$0.037 in $0.17 out / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.7,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"gpt-oss-120b — Processing modePrompt lengthInputOutput: Standard All prompts$0.10$0.70","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.02,"output_per_m":0.6,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/openai/gpt-oss-120b","checked":"2026-11-15","quote":"PRICING: INPUT $0.15 / CACHED $0.02 / OUTPUT $0.6","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"OpenAI GPT OSS 120B","maker":"OpenAI","provider_model_id":"accounts/fireworks/models/gpt-oss-120b","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"OpenAI GPT OSS 120B | $0.15 / $0.015 / $0.60 | $0.18 / $0.018 / $0.72","notes":"Priced in the serverless pricing table; not shown in the serverless model library filter on 2026-11-14."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"gpt-oss-120b","tier":"standard","input_per_m":0.09,"cached_input_per_m":null,"output_per_m":0.36,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"gpt-oss-120b Input $0.09 … Output $0.36","notes":""},{"provider":"groq","provider_name":"Groq","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"GPT OSS 120B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.075,"output_per_m":0.6,"context":131072,"precision":null,"source_url":"https://console.groq.com/docs/model/openai/gpt-oss-120b","checked":"2026-11-14","quote":"$0.15 input$0.60 output | Cached Input $0.075","notes":""},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"gpt-oss-120b","tier":"standard","input_per_m":0.159,"cached_input_per_m":null,"output_per_m":0.636,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"gpt-oss-120b Open AI USD 0.159 per 1M tokens input USD 0.636 per 1M tokens output","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"OpenAI GPT OSS 120B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.25,"context":131072,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"OpenAI GPT OSS 120B 128K $0.05 /Mt $0.25 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.055,"output_per_m":0.75,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"gpt-oss-120b $0.10 $0.75 $0.055","notes":""},{"provider":"sambanova","provider_name":"SambaNova Cloud","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"gpt-oss-120b","tier":"standard","input_per_m":0.22,"cached_input_per_m":null,"output_per_m":0.59,"context":null,"precision":null,"source_url":"https://cloud.sambanova.ai/plans/pricing","checked":"2026-11-14","quote":"gpt-oss-120b N/A 0.22 USD 0.59 USD","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.05,"cached_input_per_m":0.075,"output_per_m":0.45,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"gpt-oss-120b 131K $0.05 $0.075 $0.45","notes":"Context shown as 131K. Page lists a cached-input price higher than the input price; recorded as shown."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120B","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"gpt-oss-120B $0.15 $0.60","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"OpenAI GPT OSS 120B","maker":"OpenAI","provider_model_id":"openai-gpt-oss-120b","tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.3,"context":128000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| OpenAI GPT OSS 120B | `openai-gpt-oss-120b` | $0.07 | $0.30 | — | — | Private |","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-120b $0.075 $0.30","notes":"Batch tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":"gpt-oss-120b","tier":"batch","input_per_m":0.045,"cached_input_per_m":null,"output_per_m":0.18,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"gpt-oss-120b Batch Input $0.045 … Batch Output $0.18","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-120b $0.075 $0.30","notes":"Flex tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":0.2625,"cached_input_per_m":null,"output_per_m":1.05,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-120b $0.2625 $1.05","notes":"Priority tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"OpenAI GPT OSS 120B","maker":"OpenAI","provider_model_id":"accounts/fireworks/models/gpt-oss-120b","tier":"priority","input_per_m":0.18,"cached_input_per_m":0.018,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"OpenAI GPT OSS 120B | Priority $0.18 / $0.018 / $0.72","notes":"Priority mode."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b","name":"gpt-oss-120b (Fast)","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"gpt-oss-120b (Fast) $0.15 $0.60 —","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gpt-oss-120b-ultra","name":"gpt-oss-120b-Ultra","maker":"OpenAI","provider_model_id":"openai/gpt-oss-120b-Ultra","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.95,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/openai/gpt-oss-120b-Ultra","checked":"2026-11-14","quote":"$0.20 in $0.95 out / 1M tokens","notes":""},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"GPT OSS 20B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"standard","input_per_m":0.018,"cached_input_per_m":0.009,"output_per_m":0.09,"context":131072,"precision":null,"source_url":"https://akashml.com/models/gpt-oss-20b","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read GPT OSS 20B $0.018 $0.09 $0.009","notes":"Labelled \"Limited Trial\" on AkashML."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-20b $0.07 $0.30","notes":"Standard tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"@cf/openai/gpt-oss-20b","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/openai/gpt-oss-20b $0.200 per M input tokens $0.300 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"OpenAI GPT OSS 20B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"standard","input_per_m":0.03,"cached_input_per_m":null,"output_per_m":0.13,"context":131072,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"OpenAI GPT OSS 20B $0.03 $0.13 -","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"standard","input_per_m":0.03,"cached_input_per_m":null,"output_per_m":0.14,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/openai/gpt-oss-20b","checked":"2026-11-14","quote":"$0.03 in $0.14 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"standard","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.15,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/openai/gpt-oss-20b","checked":"2026-11-15","quote":"PRICING: INPUT $0.04 / OUTPUT $0.15","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"gpt-oss-20b","tier":"standard","input_per_m":0.07,"cached_input_per_m":0.007,"output_per_m":0.25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"gpt-oss-20b Input $0.07 … Output $0.25 … Cache Hit $0.007","notes":""},{"provider":"groq","provider_name":"Groq","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"GPT OSS 20B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"standard","input_per_m":0.075,"cached_input_per_m":0.037,"output_per_m":0.3,"context":131072,"precision":null,"source_url":"https://console.groq.com/docs/model/openai/gpt-oss-20b","checked":"2026-11-14","quote":"$0.075 input$0.30 output | Cached Input $0.037","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.04,"cached_input_per_m":0.02,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"gpt-oss-20b $0.04 $0.20 $0.02","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.18,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"gpt-oss-20b 131K $0.04 $0.18","notes":"Context shown as 131K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.035,"cached_input_per_m":null,"output_per_m":0.15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-20b $0.035 $0.15","notes":"Batch tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"gpt-oss-20b","tier":"batch","input_per_m":0.035,"cached_input_per_m":null,"output_per_m":0.125,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"gpt-oss-20b Batch Input $0.035 … Batch Output $0.125","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":0.035,"cached_input_per_m":null,"output_per_m":0.15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-20b $0.035 $0.15","notes":"Flex tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"flex","input_per_m":0.024,"cached_input_per_m":null,"output_per_m":0.112,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/openai/gpt-oss-20b","checked":"2026-11-14","quote":"Flex (0.8×) $0.024 $0.112","notes":"Flex service tier (0.8× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":null,"tier":"priority","input_per_m":0.1225,"cached_input_per_m":null,"output_per_m":0.525,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"gpt-oss-20b $0.1225 $0.525","notes":"Priority tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"gpt-oss-20b","name":"gpt-oss-20b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-20b","tier":"priority","input_per_m":0.045,"cached_input_per_m":null,"output_per_m":0.21,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/openai/gpt-oss-20b","checked":"2026-11-14","quote":"Priority (1.5×) $0.045 $0.21","notes":"Priority service tier (1.5× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"GPT OSS Safeguard 120B $ 0.15 $ 0.60","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"GPT OSS Safeguard 20B $ 0.07 $ 0.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","maker":"OpenAI","provider_model_id":"openai/gpt-oss-safeguard-20b","tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/openai/gpt-oss-safeguard-20b","checked":"2026-11-15","quote":"PRICING: INPUT $0.075 / OUTPUT $0.3","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"groq","provider_name":"Groq","provider_kind":"host","maker_api":false,"model":"gpt-oss-safeguard-20b","name":"Safety GPT OSS 20B","maker":"OpenAI","provider_model_id":"openai/gpt-oss-safeguard-20b","tier":"standard","input_per_m":0.075,"cached_input_per_m":0.037,"output_per_m":0.3,"context":131072,"precision":null,"source_url":"https://console.groq.com/docs/model/openai/gpt-oss-safeguard-20b","checked":"2026-11-14","quote":"$0.075 input$0.30 output | Cached Input $0.037","notes":"Preview model (evaluation use only per Groq)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-rosalind-discovery","name":"GPT Rosalind Discovery","maker":"OpenAI","provider_model_id":"gpt-rosalind-discovery","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Life Sciences — Trusted Access: Rosalind | gpt-rosalind-discovery (short context) | $5.00 | $25.00 | $0.50 | - | - |","notes":"Short context; longer prompts bill at the long-context rate where published. Trusted Access program only (Life Sciences — Trusted Access: Rosalind)."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"gpt-rosalind-research","name":"GPT Rosalind Research","maker":"OpenAI","provider_model_id":"gpt-rosalind-research","tier":"standard","input_per_m":5,"cached_input_per_m":0.5,"output_per_m":25,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| Life Sciences — Trusted Access: Rosalind | gpt-rosalind-research (short context) | $5.00 | $25.00 | $0.50 | - | - |","notes":"Short context; longer prompts bill at the long-context rate where published. Trusted Access program only (Life Sciences — Trusted Access: Rosalind)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"granite-4.0-h-micro","name":"Granite 4.0 H Micro","maker":"IBM","provider_model_id":"@cf/ibm-granite/granite-4.0-h-micro","tier":"standard","input_per_m":0.017,"cached_input_per_m":null,"output_per_m":0.112,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/ibm-granite/granite-4.0-h-micro $0.017 per M input tokens $0.112 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":true,"model":"granite-4.0-h-small","name":"Granite 4.0 H Small","maker":"IBM","provider_model_id":"granite-4h-small","tier":"standard","input_per_m":0.0636,"cached_input_per_m":null,"output_per_m":0.265,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"granite-4h-small IBM USD 0.0636 per 1M tokens input USD 0.265 per 1M tokens output","notes":""},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"granite-4.2-8b","name":"IBM Granite 4.2 8B","maker":"IBM","provider_model_id":"ibm-granite/granite-4.2-8b","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.015,"output_per_m":0.15,"context":131072,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"IBM Granite 4.2 8B $0.06 $0.15 $0.015","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"granite-4.2-8b","name":"granite-4.2-8b","maker":"IBM","provider_model_id":"ibm-granite/granite-4.2-8b","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.015,"output_per_m":0.25,"context":131072,"precision":null,"source_url":"https://deepinfra.com/ibm-granite/granite-4.2-8b","checked":"2026-11-14","quote":"$0.06 in $0.25 out $0.015 cached / 1M tokens","notes":""},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":true,"model":"granite-8b-code-instruct","name":"Granite 8B Code Instruct","maker":"IBM","provider_model_id":"granite-8b-code-instruct","tier":"standard","input_per_m":0.636,"cached_input_per_m":null,"output_per_m":0.636,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"granite-8b-code-instruct IBM USD 0.636","notes":"Single published per-1M rate; IBM bills Resource Units \"equivalent to 1000 tokens (including both input and output tokens)\", so input and output cost the same."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-3","name":"Grok-3","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok-3 Global $3 $15","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-3-mini","name":"Grok-3 Mini","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1.27,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok-3 Mini Global $0.25 $1.27","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4","name":"Grok 4","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok 4 $3 $15","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4-fast","name":"Grok 4 Fast","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok 4 Fast $0.20 $0.50","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4.1-fast","name":"Grok 4.1 Fast","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok 4.1 Fast Global $0.20 $0.50","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning","maker":"xAI","provider_model_id":"grok-4.1-fast-non-reasoning","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.05,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.1 Fast Non-Reasoning Input $0.20 … Output $0.50 … Cache Hit $0.05","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.1-fast-reasoning","name":"Grok 4.1 Fast Reasoning","maker":"xAI","provider_model_id":"grok-4.1-fast-reasoning","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.05,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.1 Fast Reasoning Input $0.20 … Output $0.50 … Cache Hit $0.05","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4.20","name":"Grok-4.2","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok-4.2 Global $1.25 $2.50","notes":"Foundry Models serverless (pay-as-you-go), Global deployment. Listed as \"Grok-4.2\"; mapped to Grok 4.20."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.20","name":"Grok 4.20 Reasoning","maker":"xAI","provider_model_id":"grok-4.20","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.20 Reasoning Input $1.25 … Output $2.50 … Cache Hit $0.20","notes":"Prompts under 200K tokens; longer prompts bill at long-context rates."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.20","name":"Grok 4.20 (reasoning)","maker":"xAI","provider_model_id":"grok-4.20-0309-reasoning","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":1000000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.20-0309-reasoning (< 200k prompt tokens) | 1M | $1.25 | $0.20 | $2.50 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","maker":"xAI","provider_model_id":"grok-4.20-multi-agent-0309","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":1000000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.20-multi-agent-0309 (< 200k prompt tokens) | 1M | $1.25 | $0.20 | $2.50 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.20-non-reasoning","name":"Grok 4.20 Non-Reasoning","maker":"xAI","provider_model_id":"grok-4.20-non-reasoning","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.20 Non-Reasoning Input $1.25 … Output $2.50 … Cache Hit $0.20","notes":"Prompts under 200K tokens; longer prompts bill at long-context rates."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.20-non-reasoning","name":"Grok 4.20 (non-reasoning)","maker":"xAI","provider_model_id":"grok-4.20-0309-non-reasoning","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":1000000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.20-0309-non-reasoning (< 200k prompt tokens) | 1M | $1.25 | $0.20 | $2.50 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"grok-4.3","name":"Grok 4.3","maker":"xAI","provider_model_id":"xai.grok-4.3","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":1000000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-3.html","checked":"2026-11-14","quote":"In-Region | $1.25 | $2.50 | $0.20","notes":"Bedrock model card; commercial In-Region row (Grok 4.3 is in-region only). Columns: input | output | cache read. Context stated as \"1M tokens\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4.3","name":"Grok-4.3","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok-4.3 Global $1.25 $2.50","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.3","name":"Grok 4.3","maker":"xAI","provider_model_id":"grok-4.3","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.3 Input $1.25 … Output $2.50 … Cache Hit $0.20","notes":"Prompts under 200K tokens; longer prompts bill at long-context rates."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.3","name":"Grok 4.3","maker":"xAI","provider_model_id":"grok-4.3","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.2,"output_per_m":2.5,"context":1000000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.3 (< 200k prompt tokens) | 1M | $1.25 | $0.20 | $2.50 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"grok-4.5","name":"Grok 4.5","maker":"xAI","provider_model_id":"x-ai/grok-4.5","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":2000000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/grok-4-5/74d835b8-6689-4caa-a580-e4a28128a64d","checked":"2026-11-15","quote":"Price ≤ 200k token Input $2.00 Output $6.00 Cache Read $0.50 Cache Write - > 200k token Input $4.00 Output $12.00","notes":"Long-prompt tier: prompts over 200,000 tokens cost 4 in / 12 out."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"grok-4.5","name":"Grok 4.5","maker":"xAI","provider_model_id":"xai/grok-4.5","tier":"standard","input_per_m":2,"cached_input_per_m":0.3,"output_per_m":6,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`xai/grok-4.5` | 2.00 (<200k) 4.00 (≥200k) | 6.00 (<200k) 12.00 (≥200k) | 0.30 (<200k) 0.60 (≥200k)","notes":"Third-party model resold through the Perplexity Agent API. Prompts of 200k tokens or more: 4.00 input, 0.60 cached, 12.00 output."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.5","name":"Grok 4.5","maker":"xAI","provider_model_id":"grok-4.5","tier":"standard","input_per_m":2,"cached_input_per_m":0.3,"output_per_m":6,"context":500000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.5 (< 200k prompt tokens) | 500k | $2.00 | $0.30 | $6.00 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"grok-4.6","name":"Grok 4.6","maker":"xAI","provider_model_id":"xai.grok-4.6","tier":"standard","input_per_m":2.2,"cached_input_per_m":0.55,"output_per_m":6.6,"context":500000,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-6.html","checked":"2026-11-14","quote":"In-Region | $2.20 | $6.60 | $0.55","notes":"Bedrock model card; In-Region / Geo CRIS row. Global CRIS: $2.00 / $6.00 / cache read $0.50. Context stated as \"500K tokens\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4.6","name":"Grok-4.6","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok-4.6 Global Input: $2 | Cached Input: $0.50 $6","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"grok-4.6","name":"Grok 4.6","maker":"xAI","provider_model_id":"xai/grok4.6","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":2000000,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/grok-4-6/95a8cd9c-de97-456d-8828-261c81e42ac2","checked":"2026-11-15","quote":"Price ≤ 200k token Input $2.00 Output $6.00 Cache Read $0.50 Cache Write - > 200k token Input $4.00 Output $12.00","notes":"Long-prompt tier: prompts over 200,000 tokens cost 4 in / 12 out."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.6","name":"Grok 4.6","maker":"xAI","provider_model_id":"grok-4.6","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.6 Input $2.00 … Output $6.00 … Cache Hit $0.50","notes":"Prompts under 200K tokens; longer prompts bill at long-context rates."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"grok-4.6","name":"Grok 4.6","maker":"xAI","provider_model_id":"xai/grok-4.6","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`xai/grok-4.6` | 2.00 (<200k) 4.00 (≥200k) | 6.00 (<200k) 12.00 (≥200k) | 0.50 (<200k) 1.00 (≥200k)","notes":"Third-party model resold through the Perplexity Agent API. Prompts of 200k tokens or more: 4.00 input, 1.00 cached, 12.00 output."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.6","name":"Grok 4.6","maker":"xAI","provider_model_id":"grok-4.6","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":500000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.6 (< 200k prompt tokens) | 500k | $2.00 | $0.50 | $6.00 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"grok-4.7","name":"Grok 4.7","maker":"xAI","provider_model_id":"us.xai.grok-4.7","tier":"standard","input_per_m":2.2,"cached_input_per_m":0.55,"output_per_m":6.6,"context":524288,"precision":null,"source_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-7.html","checked":"2026-11-14","quote":"Geo CRIS | $2.20 | $6.60 | $0.55","notes":"Bedrock model card; Geo CRIS row (no in-region option). Global CRIS: $2.00 / $6.00 / cache read $0.50. Context 524,288 tokens."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-4.7","name":"Grok-4.7","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok-4.7 Global Input: $2 | Cached Input: $0.50 $6","notes":"Foundry Models serverless (pay-as-you-go), Global deployment. Long-context row: input $4, cached $1, output $12."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"grok-4.7","name":"Grok 4.7","maker":"xAI","provider_model_id":"xai/grok4.7","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":500000,"precision":"int8","source_url":"https://console.gmicloud.ai/model/llm/grok-4-7/eb95a9d7-b568-4813-a0e3-dd88f82aed6d","checked":"2026-11-15","quote":"Price ≤ 200k token Input $2.00 Output $6.00 Cache Read $0.50 Cache Write - > 200k token Input $4.00 Output $12.00","notes":"Long-prompt tier: prompts over 200,000 tokens cost 4 in / 12 out."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"grok-4.7","name":"Grok 4.7","maker":"xAI","provider_model_id":"grok-4.7","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Grok 4.7 Input $2.00 … Output $6.00 … Cache Hit $0.50","notes":"Prompts under 200K tokens; longer prompts bill at long-context rates."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"grok-4.7","name":"Grok 4.7","maker":"xAI","provider_model_id":"xai/grok-4.7","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`xai/grok-4.7` | 2.00 (<200k) 4.00 (≥200k) | 6.00 (<200k) 12.00 (≥200k) | 0.50 (<200k) 1.00 (≥200k)","notes":"Third-party model resold through the Perplexity Agent API. Prompts of 200k tokens or more: 4.00 input, 1.00 cached, 12.00 output."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-4.7","name":"Grok 4.7","maker":"xAI","provider_model_id":"grok-4.7","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":6,"context":500000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-4.7 (< 200k prompt tokens) | 500k | $2.00 | $0.50 | $6.00 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"xai","provider_name":"xAI","provider_kind":"maker","maker_api":true,"model":"grok-build-0.1","name":"Grok Build 0.1","maker":"xAI","provider_model_id":"grok-build-0.1","tier":"standard","input_per_m":1,"cached_input_per_m":0.2,"output_per_m":2,"context":256000,"precision":null,"source_url":"https://docs.x.ai/developers/pricing","checked":"2026-11-14","quote":"| grok-build-0.1 (< 200k prompt tokens) | 256k | $1.00 | $0.20 | $2.00 |","notes":"Prompts under 200K tokens; once a prompt reaches 200K tokens, all tokens in the request bill at the long-context rate (double)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"grok-code-fast-1","name":"Grok Code Fast 1","maker":"xAI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/","checked":"2026-11-14","quote":"Grok Code Fast 1 $0.20 $1.50","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"hunyuan-a13b-instruct","name":"Hunyuan-A13B-Instruct","maker":"Tencent","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.57,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Hunyuan-A13B-Instruct 131K $0.14 $0.57","notes":"Context shown as 131K."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"hy3","name":"Hy3","maker":"Tencent","provider_model_id":"tencent/Hy3","tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/tencent/Hy3","checked":"2026-11-15","quote":"PRICING: INPUT $1 / OUTPUT $4","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"hy3","name":"tencent/Hy3","maker":"Tencent","provider_model_id":"tencent/Hy3","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.035,"output_per_m":0.58,"context":262144,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/tencent-hy3/c95003e0-4186-45bc-82d6-3270e78cf551","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.14 Output $0.58 Cache Read $0.035 Cache Write -","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"hy3","name":"Hy3","maker":"Tencent","provider_model_id":"tencent/hy3","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.035,"output_per_m":0.58,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Hy3 256K $0.14 /Mt · Cache Read $0.035 /Mt $0.58 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"hy3","name":"Hy3","maker":"Tencent","provider_model_id":null,"tier":"standard","input_per_m":0.132,"cached_input_per_m":0.033,"output_per_m":0.528,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Hy3 262K $0.132 $0.033 $0.528","notes":"Context shown as 262K."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"hy3-preview","name":"tencent/hy3-preview","maker":"Tencent","provider_model_id":"tencent/hy3-preview","tier":"standard","input_per_m":0.18,"cached_input_per_m":0.06,"output_per_m":0.6,"context":262144,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/tencent-hy3-preview/222715d2-d787-4feb-b5de-09e05a26bd35","checked":"2026-11-15","quote":"Price ≤ 16.4k token Input $0.18 Output $0.60 Cache Read $0.06 Cache Write - 16.4k - 32.8k token Input $0.24 Output $0.96 > 32.8k token Input $0.30 Output $1.20","notes":"Long-prompt tier: prompts over 16,384 tokens cost 0.24 in / 0.96 out."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"hy4","name":"Hy4","maker":"Tencent","provider_model_id":"tencent/Hy4","tier":"standard","input_per_m":0.525,"cached_input_per_m":0.025,"output_per_m":1.5625,"context":1048576,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Hy4 tencent/Hy4 $0.025 per 1M tokens $0.525 per 1M tokens $1.5625 per 1M tokens 1.0M","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"hy4","name":"tencent/hy4","maker":"Tencent","provider_model_id":"tencent/hy4","tier":"standard","input_per_m":0.417,"cached_input_per_m":0.021,"output_per_m":1.2505,"context":1000000,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/tencent-hy4/e3abda17-1c44-4632-a4ca-5430f487e6f1","checked":"2026-11-15","quote":"Price (per 1M tokens) 50% off Input $0.417 $0.834 Output $1.2505 $2.501 Cache Read $0.021 $0.042 Cache Write -","notes":"Promotional price, 50% off list (list 0.834 in / 2.501 out / 0.042 cached)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"hy4","name":"Hy4","maker":"Tencent","provider_model_id":"tencent/hy4","tier":"standard","input_per_m":0.417,"cached_input_per_m":0.021,"output_per_m":1.2505,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Hy4 977K $0.417 /Mt · Cache Read $0.021 /Mt $0.834 /Mt · Cache Read $0.042 /Mt $1.2505 /Mt $2.501 /Mt","notes":"Promotional price; list 0.834 in / 2.501 out per 1M."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"hy4-preview","name":"Hy4-preview","maker":"Tencent","provider_model_id":"tencent/Hy4-preview","tier":"standard","input_per_m":0.834,"cached_input_per_m":0.042,"output_per_m":2.501,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/tencent/Hy4-preview","checked":"2026-11-14","quote":"$0.834 in $2.501 out $0.042 cached / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"hy4-preview","name":"tencent/hy4-preview","maker":"Tencent","provider_model_id":"tencent/hy4-preview","tier":"standard","input_per_m":0.834,"cached_input_per_m":0.042,"output_per_m":2.501,"context":262144,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/tencent-hy4-preview/d9b8429f-3610-4352-8ba1-d9c494ee03da","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.834 Output $2.501 Cache Read $0.042 Cache Write -","notes":""},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"hy4-preview","name":"Hy4 Preview","maker":"Tencent","provider_model_id":"hy4-preview","tier":"standard","input_per_m":0.834,"cached_input_per_m":0.042,"output_per_m":2.501,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"Hy4 Preview hy4-preview Tencent · 1M context · Text $0.834 $2.501 $0.042","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"hy4-preview","name":"Hy4 Preview","maker":"Tencent","provider_model_id":"tencent/hy4-preview","tier":"standard","input_per_m":0.834,"cached_input_per_m":0.042,"output_per_m":2.501,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Hy4 Preview 977K $0.834 /Mt · Cache Read $0.042 /Mt $2.501 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"hy4-preview","name":"Hy4-preview","maker":"Tencent","provider_model_id":null,"tier":"standard","input_per_m":0.834,"cached_input_per_m":0.042,"output_per_m":2.501,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-15","quote":"Hy4-preview 1049K $0.834 $0.042 $2.501","notes":"Context shown as 1049K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"hy4-preview","name":"Hy4 Preview","maker":"Tencent","provider_model_id":"hy4-preview","tier":"standard","input_per_m":1.0425,"cached_input_per_m":0.0525,"output_per_m":3.12625,"context":1048576,"precision":"fp4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Hy4 Preview | `hy4-preview` | $1.0425 | $3.12625 | $0.0525 | — | Private |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"inkling","name":"FW Inkling","maker":"Thinking Machines","provider_model_id":null,"tier":"standard","input_per_m":1.1,"cached_input_per_m":0.19,"output_per_m":4.46,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW Inkling Data Zone\tInput: $1.10/1M Tokens | Cached Input: $0.19/1M Tokens | Output: $4.46/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"inkling-2-small","name":"Inkling 2 Small","maker":"Thinking Machines","provider_model_id":"@cf/thinkingmachines/inkling-2-small","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.1,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/thinkingmachines/inkling-2-small $0.300 per M input tokens $0.100 per M cached input tokens $1.000 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"inkling-2-small","name":"Inkling-2-Small","maker":"Thinking Machines","provider_model_id":"thinkingmachines/Inkling-2-Small","tier":"standard","input_per_m":0.285,"cached_input_per_m":0.0285,"output_per_m":0.95,"context":1048576,"precision":"fp4","source_url":"https://deepinfra.com/thinkingmachines/Inkling-2-Small","checked":"2026-11-14","quote":"$0.285 in $0.95 out $0.028 cached / 1M tokens","notes":"Promotional price, 5% off list (list 0.3 in / 1.0 out)."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"inkling-2-small","name":"Inkling 2 Small","maker":"Thinking Machines","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Inkling 2 Small $0.30 $0.03 (cached) $1.00","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"inkling-small","name":"Inkling-Small","maker":"Thinking Machines","provider_model_id":"thinkingmachines/Inkling-Small","tier":"standard","input_per_m":0.45,"cached_input_per_m":0.1,"output_per_m":1.2,"context":524288,"precision":"fp4","source_url":"https://deepinfra.com/thinkingmachines/Inkling-Small","checked":"2026-11-14","quote":"$0.45 in $1.20 out $0.10 cached / 1M tokens","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"jamba-1.5-large","name":"Jamba 1.5 Large","maker":"AI21 Labs","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":8,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Jamba 1.5 Large $2.00 $8.00","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"jamba-1.5-mini","name":"Jamba 1.5 Mini","maker":"AI21 Labs","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Jamba 1.5 Mini $0.20 $0.40","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"jamba-instruct","name":"Jamba-Instruct","maker":"AI21 Labs","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":0.7,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Jamba-Instruct $0.50 $0.70","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"ai21","provider_name":"AI21 Labs","provider_kind":"maker","maker_api":true,"model":"jamba-large-1.7","name":"Jamba Large 1.7","maker":"AI21 Labs","provider_model_id":"jamba-large","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":8,"context":262144,"precision":null,"source_url":"https://www.ai21.com/pricing/","checked":"2026-11-15","quote":"Jamba Large The most powerful and efficient long context model $2 / 1M input tokens $8 / 1M output tokens","notes":"API endpoint `jamba-large` currently points to jamba-large-1.7-2025-07 (AI21 docs)."},{"provider":"ai21","provider_name":"AI21 Labs","provider_kind":"maker","maker_api":true,"model":"jamba-mini-2","name":"Jamba Mini 2","maker":"AI21 Labs","provider_model_id":"jamba-mini","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://www.ai21.com/pricing/","checked":"2026-11-15","quote":"Jamba Mini Efficient & lightweight model for a wide range of tasks $0.2 / 1M input tokens $0.4 / 1M output tokens","notes":"API endpoint `jamba-mini` currently points to jamba-mini-2-2026-01 (AI21 docs)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"jurassic-2-mid","name":"Jurassic-2 Mid","maker":"AI21 Labs","provider_model_id":null,"tier":"standard","input_per_m":12.5,"cached_input_per_m":null,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Jurassic-2 Mid $12.50 $12.50","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"jurassic-2-ultra","name":"Jurassic-2 Ultra","maker":"AI21 Labs","provider_model_id":null,"tier":"standard","input_per_m":18.8,"cached_input_per_m":null,"output_per_m":18.8,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Jurassic-2 Ultra $18.80 $18.80","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k2","name":"Kimi-K2-Instruct","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2-Instruct","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.5,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/moonshotai/Kimi-K2-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.6 / OUTPUT $2.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k2","name":"Kimi K2 Instruct","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2-instruct","tier":"standard","input_per_m":0.57,"cached_input_per_m":null,"output_per_m":2.3,"context":131072,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K2 Instruct 128K $0.57 /Mt $2.3 /Mt","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k2-0905","name":"Kimi-K2-Instruct-0905","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2-Instruct-0905","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.5,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/moonshotai/Kimi-K2-Instruct-0905","checked":"2026-11-15","quote":"PRICING: INPUT $0.6 / OUTPUT $2.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k2-0905","name":"Kimi K2 Instruct 0905","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2-0905","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.5,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K2 Instruct 0905 256K $0.6 /Mt $2.5 /Mt","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"kimi-k2-thinking","name":"Kimi K2 Thinking","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Kimi K2 Thinking $ 0.60 $ 2.50","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"kimi-k2-thinking","name":"Kimi K2 Thinking","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/","checked":"2026-11-14","quote":"Kimi K2 Thinking Global $0.60 N/A $2.50","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k2-thinking","name":"Kimi-K2-Thinking","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2-Thinking","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":2.5,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/moonshotai/Kimi-K2-Thinking","checked":"2026-11-15","quote":"PRICING: INPUT $0.6 / OUTPUT $2.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"kimi-k2-thinking","name":"Kimi-K2-Thinking","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2-Thinking","tier":"standard","input_per_m":0.8,"cached_input_per_m":null,"output_per_m":1.2,"context":262144,"precision":"int4","source_url":"https://console.gmicloud.ai/model/llm/kimi-k2-thinking/b17c5a1b-7906-4c82-a041-a1789b55ff33","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.80 Output $1.20","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"kimi-k2-thinking","name":"Kimi K2 Thinking","maker":"Moonshot AI","provider_model_id":"kimi-k2-thinking","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.06,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Kimi-K2-Thinking Input $0.60 … Output $2.50 … Cache Hit $0.06","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k2-thinking","name":"Kimi K2 Thinking","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2-thinking","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.15,"output_per_m":2.5,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K2 Thinking 256K $0.6 /Mt · Cache Read $0.15 /Mt $2.5 /Mt","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi K2.5","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Kimi K2.5 $ 0.60 $ 3.00","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi K2.5 Thinking","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":0.1,"output_per_m":3,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/","checked":"2026-11-14","quote":"Kimi K2.5 Thinking Global $0.60 $0.10 $3","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi K2.5","maker":"Moonshot AI","provider_model_id":"@cf/moonshotai/kimi-k2.5","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.1,"output_per_m":3,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/moonshotai/kimi-k2.5 $0.600 per M input tokens $0.100 per M cached input tokens $3.000 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi-K2.5","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.5","tier":"standard","input_per_m":0.8,"cached_input_per_m":0.154,"output_per_m":3.4,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/moonshotai/Kimi-K2.5","checked":"2026-11-15","quote":"PRICING: INPUT $0.8 / CACHED $0.154 / OUTPUT $3.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"moonshotai/Kimi-K2.5","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.5","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/moonshotai-kimi-k2-5/e6a2ea3d-ba41-49d0-af87-12b997c9cdb6","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.60 Output $3.00","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi K2.5","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2.5","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.1,"output_per_m":3,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K2.5 256K $0.6 /Mt · Cache Read $0.1 /Mt $3 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi-K2.5","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.45,"cached_input_per_m":0.07,"output_per_m":2.25,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Kimi-K2.5 262K $0.45 $0.07 $2.25","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"kimi-k2.5","name":"Kimi K2.5","maker":"Moonshot AI","provider_model_id":"kimi-k2-5","tier":"standard","input_per_m":0.56,"cached_input_per_m":0.22,"output_per_m":3.5,"context":256000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Kimi K2.5 (Retiring) | `kimi-k2-5` | $0.56 | $3.50 | $0.22 | — | Private |","notes":"Marked \"Retiring\" by Venice."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"FW Kimi K2.6","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":1.045,"cached_input_per_m":0.176,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW Kimi K2.6 Data Zone\tInput: $1.045/1M Tokens | Cached Input: $0.176/1M Tokens | Output: $4.40/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment. Also sold as \"FW Kimi K2.6\" (Fireworks on Azure, Data Zone): input $1.045, cached $0.176, output $4.40."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"kimi-k2.6","name":"Kimi-K2.6","maker":"Moonshot AI","provider_model_id":"kimi-k2.6","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.16,"output_per_m":4,"context":262144,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"Kimi-K2.6\tKimi-K2.6\tInference Service\tInput\t0.95\t$/M tokens Cache Hit\t0.16\t$/M tokens Output\t4\t$/M tokens","notes":""},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.6-TEE","tier":"standard","input_per_m":0.39,"cached_input_per_m":0.039,"output_per_m":1.8,"context":262144,"precision":"int4","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Kimi K2.6 moonshotai/Kimi-K2.6-TEE $0.039 per 1M tokens $0.39 per 1M tokens $1.80 per 1M tokens 262K","notes":"Runs on confidential TEE compute."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":"@cf/moonshotai/kimi-k2.6","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.16,"output_per_m":4,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/moonshotai/kimi-k2.6 $0.950 per M input tokens $0.160 per M cached input tokens $4.000 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Moonshot AI Kimi K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.6","tier":"standard","input_per_m":0.65,"cached_input_per_m":0.15,"output_per_m":3.41,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Moonshot AI Kimi K2.6 $0.65 $3.41 $0.15","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi-K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.6","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.15,"output_per_m":3.5,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/moonshotai/Kimi-K2.6","checked":"2026-11-14","quote":"$0.75 in $3.50 out $0.15 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":4,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Kimi K2.6 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.95$4.00$0.19","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi-K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.6","tier":"standard","input_per_m":0.8,"cached_input_per_m":0.154,"output_per_m":3.4,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/moonshotai/Kimi-K2.6","checked":"2026-11-15","quote":"PRICING: INPUT $0.8 / CACHED $0.154 / OUTPUT $3.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":"kimi-k2.6","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.16,"output_per_m":4,"context":262144,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/chat","checked":"2026-11-14","quote":"kimi-k2.6 | $0.95 / MTok | $4.00 / MTok | $0.16 / MTok","notes":"Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2.6","tier":"standard","input_per_m":0.8,"cached_input_per_m":0.16,"output_per_m":3.4,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K2.6 256K $0.8 /Mt · Cache Read $0.16 /Mt $3.4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":0.16,"output_per_m":3.5,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Kimi K2.6 $0.75 $3.50 $0.16","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi-K2.6","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.77,"cached_input_per_m":0.14,"output_per_m":3.4,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Kimi-K2.6 262K $0.77 $0.14 $3.4","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":"kimi-k2-6","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.16,"output_per_m":3.5,"context":256000,"precision":"int4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Kimi K2.6 | `kimi-k2-6` | $0.75 | $3.50 | $0.16 | — | Private |","notes":""},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k2.6","name":"Kimi K2.6","maker":"Moonshot AI","provider_model_id":"kimi-k2.6","tier":"batch","input_per_m":0.57,"cached_input_per_m":0.1,"output_per_m":2.4,"context":262144,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/batch","checked":"2026-11-14","quote":"kimi-k2.6 | $0.57 / MTok | $2.40 / MTok | $0.10 / MTok | — | —","notes":"Batch API, billed at 60% of the standard price. Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi-K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.6","tier":"flex","input_per_m":0.6,"cached_input_per_m":0.12,"output_per_m":2.8,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/moonshotai/Kimi-K2.6","checked":"2026-11-14","quote":"Flex (0.8×) $0.60 $2.80 $0.12","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k2.6","name":"Kimi-K2.6","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.6","tier":"priority","input_per_m":1.125,"cached_input_per_m":0.225,"output_per_m":5.25,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/moonshotai/Kimi-K2.6","checked":"2026-11-14","quote":"Priority (1.5×) $1.125 $5.25 $0.225","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"kimi-k2.7-code","tier":"standard","input_per_m":0.95,"cached_input_per_m":null,"output_per_m":4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"kimi-k2.7-code International $0.95 $4","notes":"International (Singapore) deployment. Singapore tab of the Kimi table."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/","checked":"2026-11-14","quote":"Kimi K2.7 Code $0.95 $0.19 $4","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi-K2.7-Code","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.7-Code","tier":"standard","input_per_m":0.832,"cached_input_per_m":0.167,"output_per_m":3.5,"context":262144,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Kimi-K2.7-Code moonshotai/Kimi-K2.7-Code $0.167 per 1M tokens $0.832 per 1M tokens $3.50 per 1M tokens 262K","notes":""},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"@cf/moonshotai/kimi-k2.7-code","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":4,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/moonshotai/kimi-k2.7-code $0.950 per M input tokens $0.190 per M cached input tokens $4.000 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Moonshot AI Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.7-Code","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.12,"output_per_m":3,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Moonshot AI Kimi K2.7 Code $0.60 $3.00 $0.12","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi-K2.7-Code","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K2.7-Code","tier":"standard","input_per_m":0.8,"cached_input_per_m":0.154,"output_per_m":3.4,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/moonshotai/Kimi-K2.7-Code","checked":"2026-11-15","quote":"PRICING: INPUT $0.8 / CACHED $0.154 / OUTPUT $3.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"moonshotai/Kimi: K2.7-Code","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2.7-code","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":4,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/moonshotai-kimi-k2-7-code/2b6c9f5e-7afa-4125-b512-63d2865dd903","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.95 Output $4.00 Cache Read $0.19 Cache Write -","notes":""},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"kimi-k2.7-code","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":4,"context":262144,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/chat","checked":"2026-11-14","quote":"kimi-k2.7-code | $0.95 / MTok | $4.00 / MTok | $0.19 / MTok","notes":"Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2.7-code","tier":"standard","input_per_m":0.95,"cached_input_per_m":0.19,"output_per_m":4,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K2.7 Code 256K $0.95 /Mt · Cache Read $0.19 /Mt $4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":0.16,"output_per_m":3.5,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Kimi K2.7 Code $0.75 $3.50 $0.16","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi-K2.7-Code","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":0.85916,"cached_input_per_m":0.17993,"output_per_m":3.8,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Kimi-K2.7-Code 262K $0.85916 $0.17993 $3.8","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"kimi-k2-7-code","tier":"standard","input_per_m":0.75,"cached_input_per_m":0.16,"output_per_m":3.5,"context":256000,"precision":"int4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Kimi K2.7 Code | `kimi-k2-7-code` | $0.75 | $3.50 | $0.16 | — | Private |","notes":""},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"kimi-k2.7-code","tier":"batch","input_per_m":0.57,"cached_input_per_m":0.114,"output_per_m":2.4,"context":262144,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/batch","checked":"2026-11-14","quote":"kimi-k2.7-code | $0.57 / MTok | $2.40 / MTok | $0.114 / MTok | — | —","notes":"Batch API, billed at 60% of the standard price. Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026."},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k2.7-code","name":"Kimi K2.7 Code","maker":"Moonshot AI","provider_model_id":"kimi-k2.7-code-highspeed","tier":"fast","input_per_m":1.9,"cached_input_per_m":0.38,"output_per_m":8,"context":262144,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/chat","checked":"2026-11-14","quote":"kimi-k2.7-code-highspeed | $1.90 / MTok | $8.00 / MTok | $0.38 / MTok","notes":"Highspeed variant, API model kimi-k2.7-code-highspeed. Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"kimi-k2.7-code-highspeed","name":"moonshotai/Kimi: K2.7-Code-Highspeed","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k2.7-code-highspeed","tier":"standard","input_per_m":1.9,"cached_input_per_m":0.38,"output_per_m":8,"context":262144,"precision":"int4","source_url":"https://console.gmicloud.ai/model/llm/moonshotai-kimi-k2-7-code-highspeed/b8c17dda-1188-4c50-90f0-dd2832a251d4","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.90 Output $8.00 Cache Read $0.38 Cache Write -","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":null,"output_per_m":15,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"kimi-k3 International $3 $15","notes":"International (Singapore) deployment. Singapore tab of the Kimi table."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi 3","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":3.3,"cached_input_per_m":0.33,"output_per_m":16.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Kimi 3 … US CRIS $3.30 $16.50 $0.33 $4.125","notes":"US cross-region (US CRIS) row; Global CRIS is $3.00 / $15.00 / cache read $0.30."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"FW Kimi K3","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW Kimi K3 Global\tInput: $3/1M Tokens | Cached Input: $0.30/1M Tokens | Output: $15/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Global deployment."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"Kimi K3 $3.00 $0.30 $15.00","notes":"Context from the model library page (https://www.baseten.co/library/kimi-k3/), stated as 1M."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi-K3","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3-TEE","tier":"standard","input_per_m":1.85,"cached_input_per_m":0.185,"output_per_m":9.5,"context":1048576,"precision":"mxfp4","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Kimi-K3 moonshotai/Kimi-K3-TEE $0.185 per 1M tokens $1.85 per 1M tokens $9.50 per 1M tokens 1.0M","notes":"Runs on confidential TEE compute."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi-K3","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3","tier":"standard","input_per_m":2.85,"cached_input_per_m":0.285,"output_per_m":14.25,"context":1048576,"precision":"mxfp4","source_url":"https://deepinfra.com/moonshotai/Kimi-K3","checked":"2026-11-14","quote":"$2.85 in $14.25 out $0.285 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Kimi K3 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$3.00$15.00$0.30","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi-K3","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3","tier":"standard","input_per_m":2,"cached_input_per_m":0.3,"output_per_m":10,"context":262144,"precision":"mxfp4","source_url":"https://featherless.ai/models/moonshotai/Kimi-K3","checked":"2026-11-15","quote":"PRICING: INPUT $2 / CACHED $0.3 / OUTPUT $10","notes":"Developer plan (per-token billing, from 50 USD a month in credits). The page marks this price with \"‡\" (a pricing addendum shown only on hover); Featherless's public model API lists 3 input / 15 output for the same model, so this price may be temporary."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"accounts/fireworks/models/kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Kimi K3 | $3.00 / $0.30 / $15.00 | $3.75 / $0.375 / $18.75","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"moonshotai/Kimi: K3","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1048576,"precision":"fp4","source_url":"https://console.gmicloud.ai/model/llm/moonshotai-kimi-k3/d36120fa-0025-4018-8daa-54fcc1749135","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $3.00 Output $15.00 Cache Read $0.30 Cache Write -","notes":""},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"Kimi K3 kimi-k3 Moonshot AI · 1M context · Text $3.00 $15.00 $0.30","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1048576,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/chat","checked":"2026-11-14","quote":"kimi-k3 | $3.00 / MTok | $15.00 / MTok | $0.30 / MTok | $3.00 / MTok | $6.00 / MTok","notes":"Cache writes are billed separately (5m and 1h TTL)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K3 1M $3 /Mt · Cache Read $0.3 /Mt · Cache Write(5m) $3 /Mt · Cache Write(1h) $6 /Mt $15 /Mt","notes":"Cache write (5m) 3 per 1M."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Kimi K3 $3.00 $15.00 $0.30","notes":""},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"perplexity/kimi-k3","tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`perplexity/kimi-k3` | 3.00 | 15.00 | 0.30","notes":"Hosted by Perplexity (\"Perplexity-Hosted Models\"); tool calls billed separately."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi-K3","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":2.7,"cached_input_per_m":0.27,"output_per_m":13.5,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Kimi-K3 1049K $2.7 $0.27 $13.5","notes":"Context shown as 1049K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Kimi K3 $3.00 $0.30 (cached) $15.00","notes":"US geo-pinned option: $3.75 in / $18.75 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"kimi-k3","tier":"standard","input_per_m":3.75,"cached_input_per_m":0.375,"output_per_m":18.75,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Kimi K3 | `kimi-k3` | $3.75 | $18.75 | $0.375 | — | Private |","notes":""},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"kimi-k3","tier":"batch","input_per_m":1.8,"cached_input_per_m":0.18,"output_per_m":9,"context":1048576,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/batch","checked":"2026-11-14","quote":"kimi-k3 | $1.80 / MTok | $9.00 / MTok | $0.18 / MTok | $1.80 / MTok | $3.60 / MTok","notes":"Batch API, billed at 60% of the standard price. Cache writes are billed separately (5m and 1h TTL)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"accounts/fireworks/models/kimi-k3","tier":"flex","input_per_m":2.1,"cached_input_per_m":0.21,"output_per_m":10.5,"context":1048576,"precision":null,"source_url":"https://fireworks.ai/pricing","checked":"2026-11-14","quote":"Kimi K3 Spot $0.21 $2.10 $10.50","notes":"Fireworks \"Spot\" mode: 30% off Standard on best-effort capacity; throughput can drop to zero."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"accounts/fireworks/models/kimi-k3","tier":"priority","input_per_m":3.75,"cached_input_per_m":0.375,"output_per_m":18.75,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Kimi K3 | Priority $3.75 / $0.375 / $18.75","notes":"Priority mode."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3","maker":"Moonshot AI","provider_model_id":"accounts/fireworks/models/kimi-k3","tier":"fast","input_per_m":4.5,"cached_input_per_m":0.45,"output_per_m":22.5,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Kimi K3 Fast | $4.50 / $0.45 / $22.50 | —","notes":"Fast mode."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"kimi-k3","name":"Kimi K3 Fast","maker":"Moonshot AI","provider_model_id":"kimi-k3-fast-api","tier":"fast","input_per_m":4.5,"cached_input_per_m":0.45,"output_per_m":22.5,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Kimi K3 Fast | `kimi-k3-fast-api` | $4.50 | $22.50 | $0.45 | — | Private |","notes":"Fast variant, model ID kimi-k3-fast-api."},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3.1-Pro","tier":"standard","input_per_m":1.75,"cached_input_per_m":0.18,"output_per_m":10,"context":1048576,"precision":null,"source_url":"https://akashml.com/models/kimi-k3.1-pro","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read Kimi K3.1 Pro $1.75 $10.00 $0.18","notes":"Labelled \"Limited Trial\" on AkashML."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"kimi-k3.1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"kimi-k3.1-pro International $2 Cached input: $0.2 $10","notes":"International (Singapore) deployment. Singapore tab of the Kimi table."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1048576,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"Kimi K3.1 Pro $2.00 $0.20 $10.00","notes":"Context from the model library page (https://www.baseten.co/library/kimi-k31-pro/), stated as 1M / 1,048,576."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi-K3.1-Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3.1-Pro","tier":"standard","input_per_m":1.9,"cached_input_per_m":0.19,"output_per_m":9.5,"context":1048576,"precision":null,"source_url":"https://deepinfra.com/moonshotai/Kimi-K3.1-Pro","checked":"2026-11-14","quote":"$1.90 in $9.50 out $0.19 cached / 1M tokens","notes":"Promotional price, 5% off list (list 2.0 in / 10.0 out)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Kimi K3.1 Pro — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.00$10.00$0.20","notes":"DigitalOcean-hosted."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi-K3.1-Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3.1-Pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":262144,"precision":"mxfp4","source_url":"https://featherless.ai/models/moonshotai/Kimi-K3.1-Pro","checked":"2026-11-15","quote":"PRICING: INPUT $2 / CACHED $0.2 / OUTPUT $10","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"accounts/fireworks/models/kimi-k3p1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Kimi K3.1 Pro | $2.00 / $0.20 / $10.00 | $3.00 / $0.30 / $15.00","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"moonshotai/kimi-k3.1-pro","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k3.1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/moonshotai-kimi-k3-1-pro/370ac334-73cf-4625-b1a8-24761bfb1f70","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $2.00 Output $10.00 Cache Read $0.20 Cache Write -","notes":""},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"kimi-k3.1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1048576,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/chat","checked":"2026-11-14","quote":"kimi-k3.1-pro | $2.00 / MTok | $10.00 / MTok | $0.20 / MTok | $2.00 / MTok | $4.00 / MTok","notes":"Cache writes are billed separately (5m and 1h TTL)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k3.1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K3.1 Pro 1M $2 /Mt · Cache Read $0.2 /Mt · Cache Write(5m) $2 /Mt · Cache Write(1h) $4 /Mt $10 /Mt","notes":"Cache write (5m) 2 per 1M."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Kimi K3.1 Pro $2.00 $10.00 $0.20","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Kimi K3.1 Pro $2.00 $0.20 (cached) $10.00","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"kimi-k3-1-pro","tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":10,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Kimi K3.1 Pro | `kimi-k3-1-pro` | $2.00 | $10.00 | $0.20 | — | Private |","notes":""},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"kimi-k3.1-pro","tier":"batch","input_per_m":1.2,"cached_input_per_m":0.12,"output_per_m":6,"context":1048576,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/batch","checked":"2026-11-14","quote":"kimi-k3.1-pro | $1.20 / MTok | $6.00 / MTok | $0.12 / MTok | $1.20 / MTok | $2.40 / MTok","notes":"Batch API, billed at 60% of the standard price. Cache writes are billed separately (5m and 1h TTL)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi-K3.1-Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3.1-Pro","tier":"flex","input_per_m":1.52,"cached_input_per_m":0.152,"output_per_m":7.6,"context":1048576,"precision":null,"source_url":"https://deepinfra.com/moonshotai/Kimi-K3.1-Pro","checked":"2026-11-14","quote":"Flex (0.8×) $1.52 $7.60 $0.152","notes":"Flex service tier (0.8× standard). Promotional price, 5% off list (list 2.0 in / 10.0 out)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi-K3.1-Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/Kimi-K3.1-Pro","tier":"priority","input_per_m":2.85,"cached_input_per_m":0.285,"output_per_m":14.25,"context":1048576,"precision":null,"source_url":"https://deepinfra.com/moonshotai/Kimi-K3.1-Pro","checked":"2026-11-14","quote":"Priority (1.5×) $2.85 $14.25 $0.285","notes":"Priority service tier (1.5× standard). Promotional price, 5% off list (list 2.0 in / 10.0 out)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"accounts/fireworks/models/kimi-k3p1-pro","tier":"priority","input_per_m":3,"cached_input_per_m":0.3,"output_per_m":15,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Kimi K3.1 Pro | Priority $3.00 / $0.30 / $15.00","notes":"Priority mode."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro - Highspeed","maker":"Moonshot AI","provider_model_id":null,"tier":"fast","input_per_m":4.4,"cached_input_per_m":0.22,"output_per_m":22,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Kimi K3.1 Pro - Highspeed … US CRIS $4.40 $22.00 $0.22 $5.50","notes":"Only the Highspeed variant is listed. US cross-region (US CRIS) row; Global CRIS is $4.00 / $20.00 / cache read $0.20. Cache write (30 min) $5.50."},{"provider":"moonshot","provider_name":"Moonshot AI (Kimi)","provider_kind":"maker","maker_api":true,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"kimi-k3.1-pro-highspeed","tier":"fast","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":1048576,"precision":null,"source_url":"https://platform.kimi.ai/docs/pricing/chat","checked":"2026-11-14","quote":"kimi-k3.1-pro-highspeed | $4.00 / MTok | $20.00 / MTok | $0.20 / MTok | $4.00 / MTok | $8.00 / MTok","notes":"Highspeed variant, API model kimi-k3.1-pro-highspeed. Cache writes are billed separately (5m and 1h TTL)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"kimi-k3.1-pro","name":"Kimi K3.1 Pro","maker":"Moonshot AI","provider_model_id":"moonshotai/kimi-k3.1-pro-highspeed","tier":"fast","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Kimi K3.1 Pro Highspeed 1M $4 /Mt · Cache Read $0.2 /Mt · Cache Write(5m) $4 /Mt · Cache Write(1h) $8 /Mt $20 /Mt","notes":"Kimi K3.1 Pro Highspeed variant. Cache write (5m) 4 per 1M."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"l3-8b-lunaris-v1","name":"L3-8B-Lunaris-v1","maker":"Sao10K","provider_model_id":"Sao10K/L3-8B-Lunaris-v1","tier":"standard","input_per_m":0.0925,"cached_input_per_m":0.074,"output_per_m":0.095,"context":8192,"precision":"fp8","source_url":"https://featherless.ai/models/Sao10K/L3-8B-Lunaris-v1","checked":"2026-11-15","quote":"PRICING: INPUT $0.0925 / CACHED $0.074 / OUTPUT $0.095","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"l3-8b-lunaris-v1-turbo","name":"L3-8B-Lunaris-v1-Turbo","maker":"Sao10K","provider_model_id":"Sao10K/L3-8B-Lunaris-v1-Turbo","tier":"standard","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.05,"context":8192,"precision":"fp8","source_url":"https://deepinfra.com/Sao10K/L3-8B-Lunaris-v1-Turbo","checked":"2026-11-14","quote":"$0.04 in $0.05 out / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"l3-8b-lunaris-v1-turbo","name":"L3-8B-Lunaris-v1-Turbo","maker":"Sao10K","provider_model_id":"Sao10K/L3-8B-Lunaris-v1-Turbo","tier":"flex","input_per_m":0.032,"cached_input_per_m":null,"output_per_m":0.04,"context":8192,"precision":"fp8","source_url":"https://deepinfra.com/Sao10K/L3-8B-Lunaris-v1-Turbo","checked":"2026-11-14","quote":"Flex (0.8×) $0.032 $0.04","notes":"Flex service tier (0.8× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"l3-8b-stheno-v3.2","name":"L3-8B-Stheno-v3.2","maker":"Sao10K","provider_model_id":"Sao10K/L3-8B-Stheno-v3.2","tier":"standard","input_per_m":0.37,"cached_input_per_m":0.074,"output_per_m":0.38,"context":8192,"precision":"fp8","source_url":"https://featherless.ai/models/Sao10K/L3-8B-Stheno-v3.2","checked":"2026-11-15","quote":"PRICING: INPUT $0.37 / CACHED $0.074 / OUTPUT $0.38","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"l3-8b-stheno-v3.2","name":"Llama 3 8B Stheno V3.2","maker":"Sao10K","provider_model_id":"Sao10K/L3-8B-Stheno-v3.2","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.05,"context":8192,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Llama 3 8B Stheno V3.2 8K $0.05 /Mt $0.05 /Mt","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"l3.1-70b-euryale-v2.2","name":"L3.1-70B-Euryale-v2.2","maker":"Sao10K","provider_model_id":"Sao10K/L3.1-70B-Euryale-v2.2","tier":"standard","input_per_m":0.85,"cached_input_per_m":null,"output_per_m":0.85,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/Sao10K/L3.1-70B-Euryale-v2.2","checked":"2026-11-14","quote":"$0.85 / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"l3.1-70b-euryale-v2.2","name":"L3.1-70B-Euryale-v2.2","maker":"Sao10K","provider_model_id":"Sao10K/L3.1-70B-Euryale-v2.2","tier":"standard","input_per_m":0.72,"cached_input_per_m":null,"output_per_m":0.72,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Sao10K/L3.1-70B-Euryale-v2.2","checked":"2026-11-15","quote":"PRICING: INPUT $0.72 / OUTPUT $0.72","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"l3.1-70b-euryale-v2.2","name":"L3.1-70B-Euryale-v2.2","maker":"Sao10K","provider_model_id":"Sao10K/L3.1-70B-Euryale-v2.2","tier":"flex","input_per_m":0.68,"cached_input_per_m":null,"output_per_m":0.68,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/Sao10K/L3.1-70B-Euryale-v2.2","checked":"2026-11-14","quote":"Flex (0.8×) $0.68 $0.68","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"ling-3.0-flash","name":"Ling-3.0-flash","maker":"inclusionAI","provider_model_id":"inclusionAI/Ling-3.0-flash","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.012,"output_per_m":0.18,"context":131072,"precision":"fp4","source_url":"https://deepinfra.com/inclusionAI/Ling-3.0-flash","checked":"2026-11-14","quote":"$0.06 in $0.18 out $0.012 cached / 1M tokens","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"ling-3.0-flash","name":"Ling 3.0 Flash","maker":"inclusionAI","provider_model_id":"inclusionai/ling-3.0-flash","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.012,"output_per_m":0.18,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Ling 3.0 Flash 256K $0.06 /Mt · Cache Read $0.012 /Mt $0.18 /Mt","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"ling-3.0-flash-fin","name":"Ling 3.0 Flash Fin","maker":"inclusionAI","provider_model_id":"inclusionai/ling-3.0-flash-fin","tier":"standard","input_per_m":0.075,"cached_input_per_m":0.015,"output_per_m":0.22,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Ling 3.0 Flash Fin 256K $0.075 /Mt · Cache Read $0.015 /Mt $0.22 /Mt","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"ling-3.0-flash-sante","name":"Ling 3.0 Flash Sante","maker":"inclusionAI","provider_model_id":"inclusionai/ling-3.0-flash-sante","tier":"standard","input_per_m":0.075,"cached_input_per_m":0.015,"output_per_m":0.22,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Ling 3.0 Flash Sante 256K $0.075 /Mt · Cache Read $0.015 /Mt $0.22 /Mt","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"ling-3.0-flash-vl","name":"Ling-3.0-flash-VL","maker":"inclusionAI","provider_model_id":"inclusionAI/Ling-3.0-flash-VL","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.012,"output_per_m":0.18,"context":131072,"precision":"fp4","source_url":"https://deepinfra.com/inclusionAI/Ling-3.0-flash-VL","checked":"2026-11-14","quote":"$0.06 in $0.18 out $0.012 cached / 1M tokens","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"ling-3.0-flash-vl","name":"Ling 3.0 Flash VL","maker":"inclusionAI","provider_model_id":"inclusionai/ling-3.0-flash-vl","tier":"standard","input_per_m":0.075,"cached_input_per_m":0.015,"output_per_m":0.22,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Ling 3.0 Flash VL 256K $0.075 /Mt · Cache Read $0.015 /Mt $0.22 /Mt","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"ling-3.1-flash","name":"Ling 3.1 Flash 1019","maker":"inclusionAI","provider_model_id":"inclusionai/ling-3.1-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":0.9,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Ling 3.1 Flash 1019 977K $0.3 /Mt · Cache Read $0.06 /Mt $0.9 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"ling-flash-2.0","name":"Ling-flash-2.0","maker":"inclusionAI","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.57,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Ling-flash-2.0 131K $0.14 $0.57","notes":"Context shown as 131K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-2-13b-chat","name":"Llama 2 Chat (13B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":null,"output_per_m":1,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 2 Chat (13B) $0.75 $1.00","notes":"Table headed \"Region: US East (N. Virginia) and US West (Oregon)\"."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-2-70b-chat","name":"Llama 2 Chat (70B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":1.95,"cached_input_per_m":null,"output_per_m":2.56,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 2 Chat (70B) $1.95 $2.56","notes":"Table headed \"Region: US East (N. Virginia) and US West (Oregon)\"."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-2-7b-chat","name":"Llama 2 7B Chat (fp16)","maker":"Meta","provider_model_id":"@cf/meta/llama-2-7b-chat-fp16","tier":"standard","input_per_m":0.556,"cached_input_per_m":null,"output_per_m":6.667,"context":null,"precision":"fp16","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-2-7b-chat-fp16 $0.556 per M input tokens $6.667 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3-70b-instruct","name":"Llama 3 Instruct (70B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":2.65,"cached_input_per_m":null,"output_per_m":3.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3 Instruct (70B) $2.65 $3.50","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3-70b-instruct","name":"Meta-Llama-3-70B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Meta-Llama-3-70B-Instruct","tier":"standard","input_per_m":3.5,"cached_input_per_m":0.7,"output_per_m":8.3,"context":8192,"precision":"fp8","source_url":"https://featherless.ai/models/meta-llama/Meta-Llama-3-70B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $3.5 / CACHED $0.7 / OUTPUT $8.3","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3-8b-instruct","name":"Llama 3 Instruct (8B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3 Instruct (8B) $0.30 $0.60","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3-8b-instruct","name":"Llama 3 8B Instruct","maker":"Meta","provider_model_id":"@cf/meta/llama-3-8b-instruct","tier":"standard","input_per_m":0.282,"cached_input_per_m":null,"output_per_m":0.827,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3-8b-instruct $0.282 per M input tokens $0.827 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3-8b-instruct","name":"Meta-Llama-3-8B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Meta-Llama-3-8B-Instruct","tier":"standard","input_per_m":0.0925,"cached_input_per_m":0.074,"output_per_m":0.095,"context":8192,"precision":"fp8","source_url":"https://featherless.ai/models/meta-llama/Meta-Llama-3-8B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.0925 / CACHED $0.074 / OUTPUT $0.095","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3-8b-instruct-awq","name":"Llama 3 8B Instruct (AWQ)","maker":"Meta","provider_model_id":"@cf/meta/llama-3-8b-instruct-awq","tier":"standard","input_per_m":0.123,"cached_input_per_m":null,"output_per_m":0.266,"context":null,"precision":"awq","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3-8b-instruct-awq $0.123 per M input tokens $0.266 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.1-405b-instruct","name":"Llama 3.1 Instruct (405B)","maker":"Meta","provider_model_id":null,"tier":"batch","input_per_m":1.2,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.1 Instruct (405B) $1.20 $1.20","notes":"Only a batch price is shown for us-east-1; the on-demand cells are empty for this region. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.1-70b-instruct","name":"Llama 3.1 Instruct (70B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.72,"cached_input_per_m":null,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.1 Instruct (70B) $0.72 $0.72 $0.36 $0.36","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct (fp8-fast)","maker":"Meta","provider_model_id":"@cf/meta/llama-3.1-70b-instruct-fp8-fast","tier":"standard","input_per_m":0.293,"cached_input_per_m":null,"output_per_m":2.253,"context":null,"precision":"fp8","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.1-70b-instruct-fp8-fast $0.293 per M input tokens $2.253 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3.1-70b-instruct","name":"Llama-3.1-70B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-3.1-70B-Instruct","tier":"standard","input_per_m":2.88,"cached_input_per_m":null,"output_per_m":2.88,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/meta-llama/Llama-3.1-70B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $2.88 / OUTPUT $2.88","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published. The older repo name meta-llama/Meta-Llama-3.1-70B-Instruct is listed separately at 0.72 input / 0.72 output (model API)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.1-70b-instruct","name":"Llama 3.1 Instruct (70B)","maker":"Meta","provider_model_id":null,"tier":"batch","input_per_m":0.36,"cached_input_per_m":null,"output_per_m":0.36,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.1 Instruct (70B) $0.72 $0.72 $0.36 $0.36","notes":"Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.1-70b-instruct","name":"Llama 3.1 Instruct (70B) (w/ latency optimized inference)","maker":"Meta","provider_model_id":null,"tier":"fast","input_per_m":0.9,"cached_input_per_m":null,"output_per_m":0.9,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.1 Instruct (70B) (w/ latency optimized inference) $0.90 $0.90 N/A N/A","notes":"Latency-optimized inference option. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Llama 3.1 Instruct (8B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.22,"cached_input_per_m":null,"output_per_m":0.22,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.1 Instruct (8B) $0.22 $0.22 $0.11 $0.11","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","maker":"Meta","provider_model_id":"@cf/meta/llama-3.1-8b-instruct","tier":"standard","input_per_m":0.282,"cached_input_per_m":null,"output_per_m":0.827,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.1-8b-instruct $0.282 per M input tokens $0.827 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price. Cloudflare also lists fp8, fp8-fast and awq variants at lower prices (separate rows)."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Meta Llama 3.1 8B","maker":"Meta","provider_model_id":"meta-llama/Llama-3.1-8B-Instruct","tier":"standard","input_per_m":0.22,"cached_input_per_m":null,"output_per_m":0.22,"context":131072,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Meta Llama 3.1 8B $0.22 $0.22 -","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Meta-Llama-3.1-8B-Instruct-Turbo","maker":"Meta","provider_model_id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","tier":"standard","input_per_m":0.02,"cached_input_per_m":null,"output_per_m":0.04,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","checked":"2026-11-14","quote":"$0.02 in $0.04 out / 1M tokens","notes":"DeepInfra Turbo variant (quantized)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-3.1-8B-Instruct","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.028,"output_per_m":0.32,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/meta-llama/Llama-3.1-8B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.2 / CACHED $0.028 / OUTPUT $0.32","notes":"Developer plan (per-token billing, from 50 USD a month in credits). The older repo name meta-llama/Meta-Llama-3.1-8B-Instruct is listed separately at 0.05 input / 0.08 output (model API)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","maker":"Meta","provider_model_id":"meta-llama/llama-3.1-8b-instruct","tier":"standard","input_per_m":0.02,"cached_input_per_m":null,"output_per_m":0.05,"context":16384,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Llama 3.1 8B Instruct 16K $0.02 /Mt $0.05 /Mt","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Llama 3.1 Instruct (8B)","maker":"Meta","provider_model_id":null,"tier":"batch","input_per_m":0.11,"cached_input_per_m":null,"output_per_m":0.11,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.1 Instruct (8B) $0.22 $0.22 $0.11 $0.11","notes":"Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct","name":"Meta-Llama-3.1-8B-Instruct-Turbo","maker":"Meta","provider_model_id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","tier":"flex","input_per_m":0.016,"cached_input_per_m":null,"output_per_m":0.032,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","checked":"2026-11-14","quote":"Flex (0.8×) $0.016 $0.032","notes":"Flex service tier (0.8× standard). DeepInfra Turbo variant (quantized)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct-awq","name":"Llama 3.1 8B Instruct (AWQ)","maker":"Meta","provider_model_id":"@cf/meta/llama-3.1-8b-instruct-awq","tier":"standard","input_per_m":0.123,"cached_input_per_m":null,"output_per_m":0.266,"context":null,"precision":"awq","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.1-8b-instruct-awq $0.123 per M input tokens $0.266 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct-fp8","name":"Llama 3.1 8B Instruct (fp8)","maker":"Meta","provider_model_id":"@cf/meta/llama-3.1-8b-instruct-fp8","tier":"standard","input_per_m":0.152,"cached_input_per_m":null,"output_per_m":0.287,"context":null,"precision":"fp8","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.1-8b-instruct-fp8 $0.152 per M input tokens $0.287 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.1-8b-instruct-fp8-fast","name":"Llama 3.1 8B Instruct (fp8-fast)","maker":"Meta","provider_model_id":"@cf/meta/llama-3.1-8b-instruct-fp8-fast","tier":"standard","input_per_m":0.045,"cached_input_per_m":null,"output_per_m":0.384,"context":null,"precision":"fp8","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.1-8b-instruct-fp8-fast $0.045 per M input tokens $0.384 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price. Cloudflare fp8-fast variant of Llama 3.1 8B Instruct."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.2-11b-vision-instruct","name":"Llama 3.2 Instruct (11B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.16,"cached_input_per_m":null,"output_per_m":0.16,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.2 Instruct (11B) $0.16 $0.16","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","maker":"Meta","provider_model_id":"@cf/meta/llama-3.2-11b-vision-instruct","tier":"standard","input_per_m":0.049,"cached_input_per_m":null,"output_per_m":0.676,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.2-11b-vision-instruct $0.049 per M input tokens $0.676 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","maker":"Meta","provider_model_id":"llama-3-2-11b-vision-instruct","tier":"standard","input_per_m":0.371,"cached_input_per_m":null,"output_per_m":0.371,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"llama-3-2-11b-vision-instruct Meta USD 0.371","notes":"Single published per-1M rate; IBM bills Resource Units \"equivalent to 1000 tokens (including both input and output tokens)\", so input and output cost the same."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.2-1b-instruct","name":"Llama 3.2 Instruct (1B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.1,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.2 Instruct (1B) $0.10 $0.10","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","maker":"Meta","provider_model_id":"@cf/meta/llama-3.2-1b-instruct","tier":"standard","input_per_m":0.027,"cached_input_per_m":null,"output_per_m":0.201,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.2-1b-instruct $0.027 per M input tokens $0.201 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3.2-1b-instruct","name":"Llama-3.2-1B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-3.2-1B-Instruct","tier":"standard","input_per_m":0.027,"cached_input_per_m":null,"output_per_m":0.201,"context":32768,"precision":"bf16","source_url":"https://featherless.ai/models/meta-llama/Llama-3.2-1B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.027 / OUTPUT $0.201","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.2-3b-instruct","name":"Llama 3.2 Instruct (3B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.2 Instruct (3B) $0.15 $0.15","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","maker":"Meta","provider_model_id":"@cf/meta/llama-3.2-3b-instruct","tier":"standard","input_per_m":0.051,"cached_input_per_m":null,"output_per_m":0.335,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.2-3b-instruct $0.051 per M input tokens $0.335 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3.2-3b-instruct","name":"Llama-3.2-3B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-3.2-3B-Instruct","tier":"standard","input_per_m":0.0509,"cached_input_per_m":null,"output_per_m":0.335,"context":32768,"precision":"bf16","source_url":"https://featherless.ai/models/meta-llama/Llama-3.2-3B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.0509 / OUTPUT $0.335","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"llama-3.2-3b-instruct","name":"Llama 3.2 3B","maker":"Meta","provider_model_id":"llama-3.2-3b","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":128000,"precision":"fp16","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Llama 3.2 3B | `llama-3.2-3b` | $0.15 | $0.60 | — | — | Private |","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.2-90b-vision-instruct","name":"Llama 3.2 Instruct (90B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.72,"cached_input_per_m":null,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.2 Instruct (90B) $0.72 $0.72","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B","maker":"Meta","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.1,"output_per_m":0.52,"context":131072,"precision":null,"source_url":"https://akashml.com/models/llama-3-3-70b","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read Llama 3.3 70B $0.20 $0.52 $0.10","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 Instruct (70B)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.72,"cached_input_per_m":null,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.3 Instruct (70B) $0.72 $0.72 $0.36 $0.36","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.71,"cached_input_per_m":null,"output_per_m":0.71,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/llama/","checked":"2026-11-14","quote":"Llama 3.3 70B Global $0.71 $0.71","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct (fp8-fast)","maker":"Meta","provider_model_id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","tier":"standard","input_per_m":0.293,"cached_input_per_m":null,"output_per_m":2.253,"context":null,"precision":"fp8","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-3.3-70b-instruct-fp8-fast $0.293 per M input tokens $2.253 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Meta Llama 3.3 70B","maker":"Meta","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct","tier":"standard","input_per_m":0.71,"cached_input_per_m":null,"output_per_m":0.71,"context":128000,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Meta Llama 3.3 70B $0.71 $0.71 -","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct-Turbo","maker":"Meta","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.32,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo","checked":"2026-11-14","quote":"$0.10 in $0.32 out / 1M tokens","notes":"DeepInfra Turbo variant (quantized)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct","tier":"standard","input_per_m":0.65,"cached_input_per_m":0.52,"output_per_m":0.75,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/meta-llama/Llama-3.3-70B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.65 / CACHED $0.52 / OUTPUT $0.75","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":0.75,"context":131072,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/llama-3-3-70b-instruct/d9755097-53db-4a09-bf63-f8150f4c39fb","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.25 Output $0.75","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B","maker":"Meta","provider_model_id":"llama-3.3-70b","tier":"standard","input_per_m":0.72,"cached_input_per_m":null,"output_per_m":0.72,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Llama 3.3 70B Input $0.72 … Output $0.72","notes":""},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","maker":"Meta","provider_model_id":"llama-3-3-70b-instruct","tier":"standard","input_per_m":0.7526,"cached_input_per_m":null,"output_per_m":0.7526,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"llama-3-3-70b-instruct Meta USD 0.7526","notes":"Single published per-1M rate; IBM bills Resource Units \"equivalent to 1000 tokens (including both input and output tokens)\", so input and output cost the same."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","maker":"Meta","provider_model_id":"meta-llama/llama-3.3-70b-instruct","tier":"standard","input_per_m":0.135,"cached_input_per_m":null,"output_per_m":0.4,"context":12288,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Llama 3.3 70B Instruct 12K $0.135 /Mt $0.4 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B (FP8)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.22,"cached_input_per_m":0.11,"output_per_m":0.5,"context":null,"precision":"fp8","source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Llama 3.3 70B (FP8) $0.22 $0.50 $0.11","notes":""},{"provider":"sambanova","provider_name":"SambaNova Cloud","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Meta-Llama-3.3-70B-Instruct","maker":"Meta","provider_model_id":"Meta-Llama-3.3-70B-Instruct","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://cloud.sambanova.ai/plans/pricing","checked":"2026-11-14","quote":"Meta-Llama-3.3-70B-Instruct N/A 0.60 USD 1.20 USD","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B","maker":"Meta","provider_model_id":"llama-3.3-70b","tier":"standard","input_per_m":0.7,"cached_input_per_m":null,"output_per_m":2.8,"context":128000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Llama 3.3 70B | `llama-3.3-70b` | $0.70 | $2.80 | — | — | Private |","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 Instruct (70B)","maker":"Meta","provider_model_id":null,"tier":"batch","input_per_m":0.36,"cached_input_per_m":null,"output_per_m":0.36,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 3.3 Instruct (70B) $0.72 $0.72 $0.36 $0.36","notes":"Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama 3.3 70B","maker":"Meta","provider_model_id":"llama-3.3-70b","tier":"batch","input_per_m":0.36,"cached_input_per_m":null,"output_per_m":0.36,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Llama 3.3 70B Batch Input $0.36 … Batch Output $0.36","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct-Turbo","maker":"Meta","provider_model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","tier":"flex","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.256,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo","checked":"2026-11-14","quote":"Flex (0.8×) $0.08 $0.256","notes":"Flex service tier (0.8× standard). DeepInfra Turbo variant (quantized)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick 17B","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.24,"cached_input_per_m":null,"output_per_m":0.97,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 4 Maverick 17B $0.24 $0.97 $0.12 $0.485","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama4 Maverick 17B","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/llama/","checked":"2026-11-14","quote":"Llama4 Mavrick 17B Global $0.25 $1","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama-4 Maverick 17B 128E Instruct FP8","maker":"Meta","provider_model_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":0.8,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/llama-4-maverick-17b-128e-instruct-fp8/2cf0dd66-225d-4798-99d0-fe9b46b7a957","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.25 Output $0.80","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick","maker":"Meta","provider_model_id":"llama-4-maverick","tier":"standard","input_per_m":0.35,"cached_input_per_m":null,"output_per_m":1.15,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Llama 4 Maverick Input $0.35 … Output $1.15","notes":""},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick 17B 128E Instruct FP8","maker":"Meta","provider_model_id":"llama-4-maverick-17b-128e-instruct-fp8","tier":"standard","input_per_m":0.371,"cached_input_per_m":null,"output_per_m":1.484,"context":null,"precision":"fp8","source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"llama-4-maverick-17b-128e-instruct-fp8 Meta USD 0.371 per 1M tokens input USD 1.484 per 1M tokens output","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick Instruct","maker":"Meta","provider_model_id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":0.85,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Llama 4 Maverick Instruct 1M $0.27 /Mt $0.85 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick (FP8)","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.35,"cached_input_per_m":0.17,"output_per_m":1,"context":null,"precision":"fp8","source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Llama 4 Maverick (FP8) $0.35 $1.00 $0.17","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick 17B","maker":"Meta","provider_model_id":null,"tier":"batch","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.485,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 4 Maverick 17B $0.24 $0.97 $0.12 $0.485","notes":"Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"llama-4-maverick","name":"Llama 4 Maverick","maker":"Meta","provider_model_id":"llama-4-maverick","tier":"batch","input_per_m":0.175,"cached_input_per_m":null,"output_per_m":0.575,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Llama 4 Maverick Batch Input $0.175 … Batch Output $0.575","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama 4 Scout 17B","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.17,"cached_input_per_m":null,"output_per_m":0.66,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 4 Scout 17B $0.17 $0.66 $0.085 $0.33","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama 4 Scout 17B 16E Instruct","maker":"Meta","provider_model_id":"@cf/meta/llama-4-scout-17b-16e-instruct","tier":"standard","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":0.85,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-4-scout-17b-16e-instruct $0.270 per M input tokens $0.850 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama-4-Scout-17B-16E-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":327680,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Llama-4-Scout-17B-16E-Instruct","checked":"2026-11-14","quote":"$0.10 in $0.30 out / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama-4 Scout 17B 16E Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","tier":"standard","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.5,"context":1048576,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/llama-4-scout-17b-16e-instruct/169f3961-e31c-4829-8008-2a3a05184fa8","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.08 Output $0.50","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama 4 Scout","maker":"Meta","provider_model_id":"llama-4-scout","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":0.7,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Llama 4 Scout Input $0.25 … Output $0.70","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama 4 Scout Instruct","maker":"Meta","provider_model_id":"meta-llama/llama-4-scout-17b-16e-instruct","tier":"standard","input_per_m":0.18,"cached_input_per_m":null,"output_per_m":0.59,"context":131072,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Llama 4 Scout Instruct 128K $0.18 /Mt $0.59 /Mt","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama 4 Scout 17B","maker":"Meta","provider_model_id":null,"tier":"batch","input_per_m":0.085,"cached_input_per_m":null,"output_per_m":0.33,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Llama 4 Scout 17B $0.17 $0.66 $0.085 $0.33","notes":"Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama 4 Scout","maker":"Meta","provider_model_id":"llama-4-scout","tier":"batch","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.35,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Llama 4 Scout Batch Input $0.125 … Batch Output $0.35","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama-4-Scout-17B-16E-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","tier":"flex","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.24,"context":327680,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Llama-4-Scout-17B-16E-Instruct","checked":"2026-11-14","quote":"Flex (0.8×) $0.08 $0.24","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-4-scout","name":"Llama-4-Scout-17B-16E-Instruct","maker":"Meta","provider_model_id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","tier":"priority","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.45,"context":327680,"precision":"fp8","source_url":"https://deepinfra.com/meta-llama/Llama-4-Scout-17B-16E-Instruct","checked":"2026-11-14","quote":"Priority (1.5×) $0.15 $0.45","notes":"Priority service tier (1.5× standard)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"llama-guard-3-8b","name":"Llama Guard 3 8B","maker":"Meta","provider_model_id":"@cf/meta/llama-guard-3-8b","tier":"standard","input_per_m":0.484,"cached_input_per_m":null,"output_per_m":0.03,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/meta/llama-guard-3-8b $0.484 per M input tokens $0.030 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price. Safety classifier model."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-guard-4-12b","name":"Llama-Guard-4-12B","maker":"Meta","provider_model_id":"meta-llama/Llama-Guard-4-12B","tier":"standard","input_per_m":0.18,"cached_input_per_m":null,"output_per_m":0.18,"context":163840,"precision":"bfloat16","source_url":"https://deepinfra.com/meta-llama/Llama-Guard-4-12B","checked":"2026-11-14","quote":"$0.18 / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-guard-4-12b","name":"Llama-Guard-4-12B","maker":"Meta","provider_model_id":"meta-llama/Llama-Guard-4-12B","tier":"flex","input_per_m":0.144,"cached_input_per_m":null,"output_per_m":0.144,"context":163840,"precision":"bfloat16","source_url":"https://deepinfra.com/meta-llama/Llama-Guard-4-12B","checked":"2026-11-14","quote":"Flex (0.8×) $0.144 $0.144","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"llama-guard-4-12b","name":"Llama-Guard-4-12B","maker":"Meta","provider_model_id":"meta-llama/Llama-Guard-4-12B","tier":"priority","input_per_m":0.27,"cached_input_per_m":null,"output_per_m":0.27,"context":163840,"precision":"bfloat16","source_url":"https://deepinfra.com/meta-llama/Llama-Guard-4-12B","checked":"2026-11-14","quote":"Priority (1.5×) $0.27 $0.27","notes":"Priority service tier (1.5× standard)."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"longcat-2.0","name":"LongCat-2.0","maker":"Meituan","provider_model_id":null,"tier":"standard","input_per_m":0.75,"cached_input_per_m":0.015,"output_per_m":2.95,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"LongCat-2.0 1049K $0.75 $0.015 $2.95","notes":"Context shown as 1049K."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"macaron-v1-tall","name":"Macaron V1 Tall","maker":"Mind Lab","provider_model_id":"mindai/macaron-v1-tall","tier":"standard","input_per_m":0.2475,"cached_input_per_m":0.044,"output_per_m":1.43,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Macaron V1 Tall 256K $0.2475 /Mt · Cache Read $0.044 /Mt $1.43 /Mt","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"macaron-v1-venti","name":"Macaron V1 Venti","maker":"Mind Lab","provider_model_id":"mindai/macaron-v1-venti","tier":"standard","input_per_m":0.825,"cached_input_per_m":0.165,"output_per_m":2.475,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Macaron V1 Venti 1M $0.825 /Mt · Cache Read $0.165 /Mt $2.475 /Mt","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"magistral-small-1.2","name":"Magistral Small 1.2","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Magistral Small 1.2 $ 0.50 $ 1.50","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"mai-cyber-1-flash","name":"MAI-Cyber-1 Flash","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":0.06,"output_per_m":3.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"MAI-Cyber-1 Flash Global $0.60 $0.06 $3.50","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"mai-ds-r1","name":"MAI-DS-R1","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":1.35,"cached_input_per_m":null,"output_per_m":5.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"MAI-DS-R1 Global $1.35 N/A $5.40","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"mai-thinking-1","name":"MAI-Thinking-1","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":8,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"MAI-Thinking-1 Global $2 $0.20 $8","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"baidu","provider_name":"Baidu","provider_kind":"maker","maker_api":false,"model":"mimo-v2.5","name":"MiMo-V2.5","maker":"Xiaomi","provider_model_id":"mimo-v2.5","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.0028,"output_per_m":0.28,"context":1048576,"precision":null,"source_url":"https://intl.cloud.baidu.com/en/doc/qianfan/s/Jm8r1826a-intl-en","checked":"2026-11-15","quote":"MiMo-V2.5\tMiMo-V2.5\tInference Service\tInput\t0.14\t$/M tokens Cache Hit\t0.0028\t$/M tokens Output\t0.28\t$/M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"mimo-v2.5","name":"MiMo-V2.5","maker":"Xiaomi","provider_model_id":"XiaomiMiMo/MiMo-V2.5","tier":"standard","input_per_m":0.149,"cached_input_per_m":0.028,"output_per_m":0.493,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/XiaomiMiMo/MiMo-V2.5","checked":"2026-11-15","quote":"PRICING: INPUT $0.149 / CACHED $0.028 / OUTPUT $0.493","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"mimo-v2.5","name":"MiMo v2.5","maker":"Xiaomi","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":0.05,"output_per_m":0.28,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"MiMo v2.5 $0.14 $0.28 $0.05","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"mimo-v2.5","name":"MiMo-V2.5","maker":"Xiaomi","provider_model_id":"xiaomi-mimo-v2-5","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.08,"output_per_m":2,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| MiMo-V2.5 | `xiaomi-mimo-v2-5` | $0.40 | $2.00 | $0.08 | — | Private |","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"mimo-v2.5-pro","name":"MiMo V2.5 Pro","maker":"Xiaomi","provider_model_id":null,"tier":"standard","input_per_m":0.8,"cached_input_per_m":0.16,"output_per_m":3,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"MiMo V2.5 Pro — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.80$3.00$0.16","notes":"DigitalOcean-hosted."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","maker":"Xiaomi","provider_model_id":"XiaomiMiMo/MiMo-V2.6-Flash","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.0028,"output_per_m":0.28,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/XiaomiMiMo/MiMo-V2.6-Flash","checked":"2026-11-14","quote":"$0.14 in $0.28 out $0.003 cached / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","maker":"Xiaomi","provider_model_id":"XiaomiMiMo/MiMo-V2.6-Flash","tier":"standard","input_per_m":0.112,"cached_input_per_m":0.00224,"output_per_m":0.224,"context":1050000,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/mimo-v2-6-flash/ecc2d2ea-a257-4da7-895b-828aaa45b370","checked":"2026-11-15","quote":"Price (per 1M tokens) 20% off Input $0.112 $0.14 Output $0.224 $0.28 Cache Read $0.00224 $0.0028 Cache Write -","notes":"Promotional price, 20% off list (list 0.14 in / 0.28 out / 0.0028 cached)."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","maker":"Xiaomi","provider_model_id":"mimo-v2.6-flash","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.0028,"output_per_m":0.28,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"MiMo-V2.6-Flash mimo-v2.6-flash Xiaomi · 1M context · Text $0.14 $0.28 $0.0028","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-flash","name":"MiMo V2.6 Flash","maker":"Xiaomi","provider_model_id":"xiaomimimo/mimo-v2.6-flash","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.0028,"output_per_m":0.28,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"MiMo V2.6 Flash 1M $0.14 /Mt · Cache Read $0.0028 /Mt $0.28 /Mt","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-flash","name":"MiMo-V2.6-Flash","maker":"Xiaomi","provider_model_id":"xiaomi-mimo-v2-6-flash","tier":"standard","input_per_m":0.175,"cached_input_per_m":0.00375,"output_per_m":0.35,"context":1000000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| MiMo-V2.6-Flash | `xiaomi-mimo-v2-6-flash` | $0.175 | $0.35 | $0.00375 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","maker":"Xiaomi","provider_model_id":"XiaomiMiMo/MiMo-V2.6-Pro","tier":"standard","input_per_m":0.387,"cached_input_per_m":0.00324,"output_per_m":0.783,"context":1048576,"precision":"fp8","source_url":"https://deepinfra.com/XiaomiMiMo/MiMo-V2.6-Pro","checked":"2026-11-14","quote":"$0.387 in $0.783 out $0.003 cached / 1M tokens","notes":"Promotional price, 10% off list (list 0.43 in / 0.87 out)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-pro","name":"MiMo-V2.6-Pro","maker":"Xiaomi","provider_model_id":"XiaomiMiMo/MiMo-V2.6-Pro","tier":"standard","input_per_m":0.32625,"cached_input_per_m":0.0027,"output_per_m":0.6525,"context":1050000,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/mimo-v2-6-pro/3a6f9a3e-c703-4abd-af1c-42b7793de789","checked":"2026-11-15","quote":"Price (per 1M tokens) 25% off Input $0.32625 $0.435 Output $0.6525 $0.87 Cache Read $0.0027 $0.0036 Cache Write -","notes":"Promotional price, 25% off list (list 0.435 in / 0.87 out / 0.0036 cached)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"mimo-v2.6-pro","name":"MiMo V2.6 Pro","maker":"Xiaomi","provider_model_id":"xiaomimimo/mimo-v2.6-pro","tier":"standard","input_per_m":0.435,"cached_input_per_m":0.0036,"output_per_m":0.87,"context":1048576,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"MiMo V2.6 Pro 1M $0.435 /Mt · Cache Read $0.0036 /Mt $0.87 /Mt","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"minimax-m2","name":"Minimax M2","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Minimax M2 $ 0.30 $ 1.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"minimax-m2","name":"MiniMax-M2","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2","tier":"standard","input_per_m":0.2775,"cached_input_per_m":0.0555,"output_per_m":1.11,"context":204800,"precision":"fp8","source_url":"https://featherless.ai/models/MiniMaxAI/MiniMax-M2","checked":"2026-11-15","quote":"PRICING: INPUT $0.2775 / CACHED $0.0555 / OUTPUT $1.11","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m2","name":"MiniMax-M2","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":1.2,"context":196608,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/minimax-m2/bbfb2cb6-7d62-43d2-a70c-f01dbdc33bde","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.30 Output $1.20","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"minimax-m2","name":"MiniMax M2","maker":"MiniMax","provider_model_id":"minimax-m2","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"MiniMax-M2 Input $0.30 … Output $1.20 … Cache Hit $0.03","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"minimax-m2.1","name":"Minimax M2.1","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Minimax M2.1 $ 0.30 $ 1.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"minimax-m2.1","name":"MiniMax-M2.1","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2.1","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":204800,"precision":"fp8","source_url":"https://featherless.ai/models/MiniMaxAI/MiniMax-M2.1","checked":"2026-11-15","quote":"PRICING: INPUT $0.3 / CACHED $0.06 / OUTPUT $1.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m2.1","name":"MiniMax-M2.1","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2.1","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":196608,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/minimax-m2-1/1ed90614-96f6-406a-be34-f818210d7fe6","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.30 Output $1.20 Cache Read $0.03 Cache Write -","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"minimax-m2.5","name":"MiniMax M2.5","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"MiniMax M2.5 $ 0.30 $ 1.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"minimax-m2.5","name":"MiniMax M2.5 (Public Preview)","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"MiniMax M2.5 (Public Preview) — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.30$1.20$0.06","notes":"DigitalOcean-hosted; public preview."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"minimax-m2.5","name":"MiniMax-M2.5","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2.5","tier":"standard","input_per_m":0.295,"cached_input_per_m":0.059,"output_per_m":1.2,"context":204800,"precision":"fp8","source_url":"https://featherless.ai/models/MiniMaxAI/MiniMax-M2.5","checked":"2026-11-15","quote":"PRICING: INPUT $0.295 / CACHED $0.059 / OUTPUT $1.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m2.5","name":"MiniMaxAI/MiniMax-M2.5","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2.5","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":196608,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/minimaxai-minimax-m2-5/2a7f5f64-6c5f-4896-a524-8bcadaa3be7f","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.30 Output $1.20 Cache Read $0.03 Cache Write -","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"minimax-m2.5","name":"MiniMax M2.5","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"MiniMax M2.5 $0.30 $1.20 $0.03","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"minimax-m2.5","name":"MiniMax M2.5","maker":"MiniMax","provider_model_id":"minimax-m25","tier":"standard","input_per_m":0.27,"cached_input_per_m":0.03,"output_per_m":0.95,"context":198000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| MiniMax M2.5 | `minimax-m25` | $0.27 | $0.95 | $0.03 | — | Private |","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"minimax-m2.7","name":"MiniMax-M2.7","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2.7","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":204800,"precision":"fp8","source_url":"https://featherless.ai/models/MiniMaxAI/MiniMax-M2.7","checked":"2026-11-15","quote":"PRICING: INPUT $0.3 / CACHED $0.06 / OUTPUT $1.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m2.7","name":"MiniMaxAI/MiniMax-M2.7","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M2.7","tier":"standard","input_per_m":0.21,"cached_input_per_m":0.042,"output_per_m":0.84,"context":196608,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/minimaxai-minimax-m2-7/b55d47ed-0d1e-467e-ae93-f1500402d184","checked":"2026-11-15","quote":"Price (per 1M tokens) 30% off Input $0.21 $0.30 Output $0.84 $1.20 Cache Read $0.042 $0.06 Cache Write -","notes":"Promotional price, 30% off list (list 0.3 in / 1.2 out / 0.06 cached)."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"minimax-m2.7","name":"MiniMax M2.7","maker":"MiniMax","provider_model_id":"minimax-m27","tier":"standard","input_per_m":0.375,"cached_input_per_m":0.06875,"output_per_m":1.5,"context":198000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| MiniMax M2.7 | `minimax-m27` | $0.375 | $1.50 | $0.06875 | — | Private |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"FW MiniMax 3","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.33,"cached_input_per_m":0.066,"output_per_m":1.32,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW MiniMax 3 Data Zone\tInput: $0.33/1M Tokens | Cached Input: $0.066/1M Tokens | Output: $1.32/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment. \"MiniMax 3\" mapped to MiniMax M3."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3","tier":"standard","input_per_m":0.23,"cached_input_per_m":0.05,"output_per_m":0.96,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"MiniMax M3 $0.23 $0.96 $0.05","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax-M3","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3","tier":"standard","input_per_m":0.28,"cached_input_per_m":0.056,"output_per_m":1.1,"context":524288,"precision":"fp8","source_url":"https://deepinfra.com/MiniMaxAI/MiniMax-M3","checked":"2026-11-14","quote":"$0.28 in $1.10 out $0.056 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax-M3","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3","tier":"standard","input_per_m":0.55,"cached_input_per_m":0.06,"output_per_m":2.2,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/MiniMaxAI/MiniMax-M3","checked":"2026-11-15","quote":"PRICING: INPUT $0.55 / CACHED $0.06 / OUTPUT $2.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":"accounts/fireworks/models/minimax-m3","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":512000,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"MiniMax M3 | $0.30 / $0.06 / $1.20 | $0.45 / $0.09 / $1.80","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMaxAI/MiniMax-M3","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3","tier":"standard","input_per_m":0.24,"cached_input_per_m":0.048,"output_per_m":0.96,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/minimaxai-minimax-m3/3c25d31e-d652-4d0b-bb0f-24476766da32","checked":"2026-11-15","quote":"Price 20% off ≤ 512k token Input $0.24 $0.30 Output $0.96 $1.20 Cache Read $0.048 $0.06 Cache Write - > 512k token Input $0.48 $0.60 Output $1.92 $2.40","notes":"Promotional price, 20% off list (list 0.3 in / 1.2 out / 0.06 cached). Long-prompt tier: prompts over 512,000 tokens cost 0.48 in / 1.92 out."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":"minimax-m3","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"MiniMax M3 minimax-m3 MiniMax · 1M context · Text $0.30 $1.20 $0.06","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"minimax","provider_name":"MiniMax","provider_kind":"maker","maker_api":true,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":"MiniMax-M3","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://platform.minimax.io/docs/pricing/overview","checked":"2026-11-14","quote":"| **MiniMax-M3** ≤ 512k input tokens Permanent 50% off | ~~$0.60~~ $0.30 | ~~$2.40~~ $1.20 | ~~$0.12~~ $0.06 |","notes":"Prompts up to 512K input tokens, after the \"Permanent 50% off\" MiniMax shows on its list price (0.6 input, 2.4 output, 0.12 cache read). Prompts over 512K cost double. Cached price is the prompt-caching read price."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"MiniMax M3 $0.30 $1.20 $0.06","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax-M3","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"MiniMax-M3 1049K $0.3 $0.06 $1.2","notes":"Context shown as 1049K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax-M3","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3","tier":"flex","input_per_m":0.224,"cached_input_per_m":0.0448,"output_per_m":0.88,"context":524288,"precision":"fp8","source_url":"https://deepinfra.com/MiniMaxAI/MiniMax-M3","checked":"2026-11-14","quote":"Flex (0.8×) $0.224 $0.88 $0.0448","notes":"Flex service tier (0.8× standard)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":"accounts/fireworks/models/minimax-m3","tier":"priority","input_per_m":0.45,"cached_input_per_m":0.09,"output_per_m":1.8,"context":512000,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"MiniMax M3 | Priority $0.45 / $0.09 / $1.80","notes":"Priority mode."},{"provider":"minimax","provider_name":"MiniMax","provider_kind":"maker","maker_api":true,"model":"minimax-m3","name":"MiniMax M3","maker":"MiniMax","provider_model_id":"MiniMax-M3","tier":"priority","input_per_m":0.45,"cached_input_per_m":0.09,"output_per_m":1.8,"context":null,"precision":null,"source_url":"https://platform.minimax.io/docs/pricing/overview","checked":"2026-11-14","quote":"| **MiniMax-M3** ≤ 512k input tokens Permanent 50% off | ~~$0.90~~ $0.45 | ~~$3.60~~ $1.80 | ~~$0.18~~ $0.09 |","notes":"Priority tier (service_tier=priority, 1.5x standard). Prompts up to 512K input tokens, after the \"Permanent 50% off\" MiniMax shows on its list price (0.9 input, 3.6 output, 0.18 cache read). Prompts over 512K cost double. Cached price is the prompt-caching read price."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"minimax-m3-preview","name":"MiniMax M3 Preview","maker":"MiniMax","provider_model_id":"minimax-m3-preview","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.2,"context":524288,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| MiniMax M3 Preview | `minimax-m3-preview` | $0.30 | $1.20 | $0.06 | — | Private |","notes":"Preview model."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax M3.1-Flash (Public Preview)","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"MiniMax M3.1-Flash (Public Preview) — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.15$0.60$0.015","notes":"DigitalOcean-hosted; public preview."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax-M3.1-Flash","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3.1-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":1048576,"precision":"fp8","source_url":"https://featherless.ai/models/MiniMaxAI/MiniMax-M3.1-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.15 / CACHED $0.015 / OUTPUT $0.6","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","maker":"MiniMax","provider_model_id":"accounts/fireworks/models/minimax-m3p1-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":1048576,"precision":null,"source_url":"https://fireworks.ai/models/fireworks/minimax-m3p1-flash","checked":"2026-11-14","quote":"Available Serverless $0.15 / $0.015 / $0.60 Run queries immediately, pay only for usage Per 1M Tokens (input/cached input/output)","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMaxAI/MiniMax-M3.1-Flash","maker":"MiniMax","provider_model_id":"MiniMaxAI/MiniMax-M3.1-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/minimaxai-minimax-m3-1-flash/e779f6e7-b393-4208-9ec8-61ad2af3348c","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.15 Output $0.60 Cache Read $0.015 Cache Write -","notes":""},{"provider":"minimax","provider_name":"MiniMax","provider_kind":"maker","maker_api":true,"model":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","maker":"MiniMax","provider_model_id":"MiniMax-M3.1-Flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://platform.minimax.io/docs/pricing/overview","checked":"2026-11-14","quote":"MiniMax-M3.1-Flash $0.15 $0.60 $0.015","notes":"Cached price is the prompt-caching read price."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"MiniMax M3.1 Flash $0.15 $0.60 $0.015","notes":""},{"provider":"sambanova","provider_name":"SambaNova Cloud","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax-M3.1-Flash","maker":"MiniMax","provider_model_id":"MiniMax-M3.1-Flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.03,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://cloud.sambanova.ai/plans/pricing","checked":"2026-11-14","quote":"MiniMax-M3.1-Flash 0.03 USD 0.30 USD 1.20 USD","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","maker":"MiniMax","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"MiniMax M3.1 Flash $0.15 $0.015 (cached) $0.60","notes":"US geo-pinned option: $0.1875 in / $0.75 out."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"minimax-m3.1-flash","name":"MiniMax M3.1 Flash","maker":"MiniMax","provider_model_id":"minimax-m3-1-flash","tier":"standard","input_per_m":0.1875,"cached_input_per_m":0.01875,"output_per_m":0.75,"context":1000000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| MiniMax M3.1 Flash | `minimax-m3-1-flash` | $0.1875 | $0.75 | $0.01875 | — | Private |","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"ministral-14b-2512","name":"Ministral 14B 3.0","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Ministral 14B 3.0 $ 0.20 $ 0.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"ministral-14b-2512","name":"Ministral 3 14B Instruct","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Ministral 3 14B Instruct — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.20$0.20$0.04","notes":"DigitalOcean-hosted."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-14b-2512","name":"Ministral 3 14B","maker":"Mistral AI","provider_model_id":"ministral-14b-2512","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":0.2,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Ministral 3 14B ↗\t$0.2\t$0.02\t$0.2","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-14b-2512","name":"Ministral 3 14B","maker":"Mistral AI","provider_model_id":"ministral-14b-2512","tier":"batch","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.1,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Ministral 3 14B ↗\t$0.1\t$0.01\t$0.1 (Batch tab, \"Batch (-50%)\")","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-14b-2512","name":"Ministral 3 14B","maker":"Mistral AI","provider_model_id":"ministral-14b-2512","tier":"priority","input_per_m":0.35,"cached_input_per_m":0.035,"output_per_m":0.35,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Ministral 3 14B ↗\t$0.35\t$0.035\t$0.35 (Priority tab, \"Priority (+75%)\")","notes":"Context from the docs model card."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"ministral-3b-2512","name":"Ministral 3B 3.0","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.1,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Ministral 3B 3.0 $ 0.10 $ 0.10","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-3b-2512","name":"Ministral 3 3B","maker":"Mistral AI","provider_model_id":"ministral-3b-2512","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.01,"output_per_m":0.1,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Ministral 3 3B ↗\t$0.1\t$0.01\t$0.1","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-3b-2512","name":"Ministral 3 3B","maker":"Mistral AI","provider_model_id":"ministral-3b-2512","tier":"batch","input_per_m":0.05,"cached_input_per_m":0.005,"output_per_m":0.05,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Ministral 3 3B ↗\t$0.05\t$0.005\t$0.05 (Batch tab, \"Batch (-50%)\")","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-3b-2512","name":"Ministral 3 3B","maker":"Mistral AI","provider_model_id":"ministral-3b-2512","tier":"priority","input_per_m":0.175,"cached_input_per_m":0.0175,"output_per_m":0.175,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Ministral 3 3B ↗\t$0.175\t$0.0175\t$0.175 (Priority tab, \"Priority (+75%)\")","notes":"Context from the docs model card."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"ministral-8b-2512","name":"Ministral 8B 3.0","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.15,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Ministral 8B 3.0 $ 0.15 $ 0.15","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-8b-2512","name":"Ministral 3 8B","maker":"Mistral AI","provider_model_id":"ministral-8b-2512","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.15,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Ministral 3 8B ↗\t$0.15\t$0.015\t$0.15","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-8b-2512","name":"Ministral 3 8B","maker":"Mistral AI","provider_model_id":"ministral-8b-2512","tier":"batch","input_per_m":0.075,"cached_input_per_m":0.0075,"output_per_m":0.075,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Ministral 3 8B ↗\t$0.075\t$0.0075\t$0.075 (Batch tab, \"Batch (-50%)\")","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"ministral-8b-2512","name":"Ministral 3 8B","maker":"Mistral AI","provider_model_id":"ministral-8b-2512","tier":"priority","input_per_m":0.2625,"cached_input_per_m":0.02625,"output_per_m":0.2625,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Ministral 3 8B ↗\t$0.2625\t$0.02625\t$0.2625 (Priority tab, \"Priority (+75%)\")","notes":"Context from the docs model card."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"mistral-7b-instruct","name":"Mistral 7B","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Mistral 7B $0.15 $0.20 N/A N/A","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"mistral-7b-instruct-v0.1","name":"Mistral 7B Instruct v0.1","maker":"Mistral AI","provider_model_id":"@cf/mistral/mistral-7b-instruct-v0.1","tier":"standard","input_per_m":0.11,"cached_input_per_m":null,"output_per_m":0.19,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/mistral/mistral-7b-instruct-v0.1 $0.110 per M input tokens $0.190 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"mistral-large-2402","name":"Mistral Large (24.02)","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":4,"cached_input_per_m":null,"output_per_m":12,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Mistral Large (24.02) $4.00 $12.00 N/A N/A","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"mistral-large-2512","name":"Mistral Large 3","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Mistral Large 3 $ 0.50 $ 1.50","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"mistral-large-2512","name":"Mistral Large 3","maker":"Mistral AI","provider_model_id":"mistral-large-2512","tier":"standard","input_per_m":0.636,"cached_input_per_m":null,"output_per_m":1.908,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"mistral-large-2512 Mistral AI USD 0.636 per 1M tokens input USD 1.908 per 1M tokens output","notes":""},{"provider":"nscale","provider_name":"Nscale","provider_kind":"host","maker_api":false,"model":"mistral-large-2512","name":"Mistral-Large-3-675B-Instruct-2512-NVFP4","maker":"Mistral AI","provider_model_id":"Mistral-Large-3-675B-Instruct-2512-NVFP4","tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":"nvfp4","source_url":"https://docs.nscale.com/docs/ai-services/models","checked":"2026-11-15","quote":"| Mistral-Large-3-675B-Instruct-2512-NVFP4 | Mistral AI | $1.00 | $2.50 |","notes":"Moves from serverless to dedicated models on 11 December 2026 per Nscale."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"mistral-large-4-0","name":"Mistral Large 4","maker":"Mistral AI","provider_model_id":"mistral-large-4","tier":"standard","input_per_m":0.7,"cached_input_per_m":0.07,"output_per_m":2.1,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Mistral Large 4 ↗\t$0.7\t$0.07\t$2.1","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"mistral-large-4-0","name":"Mistral Large 4","maker":"Mistral AI","provider_model_id":"mistral-large-4","tier":"batch","input_per_m":0.35,"cached_input_per_m":0.035,"output_per_m":1.05,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Mistral Large 4 ↗\t$0.35\t$0.035\t$1.05 (Batch tab, \"Batch (-50%)\")","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"mistral-large-4-0","name":"Mistral Large 4","maker":"Mistral AI","provider_model_id":"mistral-large-4","tier":"priority","input_per_m":1.225,"cached_input_per_m":0.1225,"output_per_m":3.675,"context":1048576,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Mistral Large 4 ↗\t$1.225\t$0.1225\t$3.675 (Priority tab, \"Priority (+75%)\")","notes":"Context from the docs model card."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"mistral-medium-3","name":"Mistral Medium 3","maker":"Mistral AI","provider_model_id":"mistral-medium-3","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Mistral Medium 3 Input $0.40 … Output $2.00","notes":""},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"mistral-medium-3","name":"Mistral Medium 3","maker":"Mistral AI","provider_model_id":"mistral-medium-2505","tier":"standard","input_per_m":3.18,"cached_input_per_m":null,"output_per_m":9.5,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"mistral-medium-2505 Mistral AI USD 3.18 per 1M tokens input USD 9.5per 1M tokens output","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"mistral-medium-3-5","name":"Mistral Medium 3.5","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":1.5,"cached_input_per_m":null,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral-ai/","checked":"2026-11-14","quote":"Mistral Medium 3.5 Global Input: $1.50/1M Tokens | Output: $7.50/1M Tokens","notes":"Foundry Models serverless (pay-as-you-go), Global deployment."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-nemo-instruct-2407","name":"Mistral-Nemo-Instruct-2407","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Nemo-Instruct-2407","tier":"standard","input_per_m":0.029,"cached_input_per_m":null,"output_per_m":0.03,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Nemo-Instruct-2407","checked":"2026-11-14","quote":"$0.029 in $0.03 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"mistral-nemo-instruct-2407","name":"Mistral-Nemo-Instruct-2407","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Nemo-Instruct-2407","tier":"standard","input_per_m":0.2175,"cached_input_per_m":0.2,"output_per_m":0.2475,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/mistralai/Mistral-Nemo-Instruct-2407","checked":"2026-11-15","quote":"PRICING: INPUT $0.2175 / CACHED $0.2 / OUTPUT $0.2475","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-nemo-instruct-2407","name":"Mistral-Nemo-Instruct-2407","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Nemo-Instruct-2407","tier":"flex","input_per_m":0.0232,"cached_input_per_m":null,"output_per_m":0.024,"context":131072,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Nemo-Instruct-2407","checked":"2026-11-14","quote":"Flex (0.8×) $0.0232 $0.024","notes":"Flex service tier (0.8× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"mistral-small-2402","name":"Mistral Small (24.02)","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Mistral Small (24.02) $1.00 $3.00 $0.50 $1.50","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"mistral-small-2402","name":"Mistral Small (24.02)","maker":"Mistral AI","provider_model_id":null,"tier":"batch","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Mistral Small (24.02) $1.00 $3.00 $0.50 $1.50","notes":"Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-small-24b-instruct-2501","name":"Mistral-Small-24B-Instruct-2501","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-24B-Instruct-2501","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.08,"context":32768,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Small-24B-Instruct-2501","checked":"2026-11-14","quote":"$0.05 in $0.08 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"mistral-small-24b-instruct-2501","name":"Mistral-Small-24B-Instruct-2501","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-24B-Instruct-2501","tier":"standard","input_per_m":0.175,"cached_input_per_m":0.04,"output_per_m":0.29,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/mistralai/Mistral-Small-24B-Instruct-2501","checked":"2026-11-15","quote":"PRICING: INPUT $0.175 / CACHED $0.04 / OUTPUT $0.29","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-small-24b-instruct-2501","name":"Mistral-Small-24B-Instruct-2501","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-24B-Instruct-2501","tier":"flex","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.064,"context":32768,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Small-24B-Instruct-2501","checked":"2026-11-14","quote":"Flex (0.8×) $0.04 $0.064","notes":"Flex service tier (0.8× standard)."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"mistral-small-2603","name":"Mistral Small 4","maker":"Mistral AI","provider_model_id":"mistral-small-2603","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.015,"output_per_m":0.6,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Mistral Small 4 ↗\t$0.15\t$0.015\t$0.6","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"mistral-small-2603","name":"Mistral Small 4","maker":"Mistral AI","provider_model_id":"mistral-small-2603","tier":"batch","input_per_m":0.075,"cached_input_per_m":0.0075,"output_per_m":0.3,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-14","quote":"Mistral Small 4 ↗\t$0.075\t$0.0075\t$0.3 (Batch tab, \"Batch (-50%)\")","notes":"Context from the docs model card."},{"provider":"mistral","provider_name":"Mistral AI","provider_kind":"maker","maker_api":true,"model":"mistral-small-2603","name":"Mistral Small 4","maker":"Mistral AI","provider_model_id":"mistral-small-2603","tier":"priority","input_per_m":0.2625,"cached_input_per_m":0.02625,"output_per_m":1.05,"context":262144,"precision":null,"source_url":"https://docs.mistral.ai/inference/pricing","checked":"2026-11-15","quote":"Mistral Small 4 ↗\t$0.2625\t$0.02625\t$1.05 (Priority tab, \"Priority (+75%)\")","notes":"Context from the docs model card."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B Instruct","maker":"Mistral AI","provider_model_id":"@cf/mistralai/mistral-small-3.1-24b-instruct","tier":"standard","input_per_m":0.351,"cached_input_per_m":null,"output_per_m":0.555,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/mistralai/mistral-small-3.1-24b-instruct $0.351 per M input tokens $0.555 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"mistral-small-3.1-24b-instruct","name":"Mistral-Small-3.1-24B-Instruct-2503","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-3.1-24B-Instruct-2503","tier":"standard","input_per_m":0.2168,"cached_input_per_m":null,"output_per_m":0.4025,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/mistralai/Mistral-Small-3.1-24B-Instruct-2503","checked":"2026-11-15","quote":"PRICING: INPUT $0.2168 / OUTPUT $0.4025","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 (25.03)","maker":"Mistral AI","provider_model_id":"mistral-small-2503","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Mistral Small 3.1 (25.03) Input $0.10 … Output $0.30","notes":""},{"provider":"ibm-watsonx","provider_name":"IBM watsonx.ai","provider_kind":"maker","maker_api":false,"model":"mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B Instruct","maker":"Mistral AI","provider_model_id":"mistral-small-3-1-24b-instruct-2503","tier":"standard","input_per_m":0.106,"cached_input_per_m":null,"output_per_m":0.318,"context":null,"precision":null,"source_url":"https://www.ibm.com/products/watsonx-ai/pricing","checked":"2026-11-15","quote":"mistral-small-3-1-24b-instruct-2503 Mistral AI USD 0.106 per 1M tokens input USD 0.318 per 1M tokens output","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-small-3.2-24b-instruct","name":"Mistral-Small-3.2-24B-Instruct-2506","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.2,"context":128000,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Small-3.2-24B-Instruct-2506","checked":"2026-11-14","quote":"$0.075 in $0.20 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"mistral-small-3.2-24b-instruct","name":"Mistral-Small-3.2-24B-Instruct-2506","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","tier":"standard","input_per_m":0.2168,"cached_input_per_m":null,"output_per_m":0.4025,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/mistralai/Mistral-Small-3.2-24B-Instruct-2506","checked":"2026-11-15","quote":"PRICING: INPUT $0.2168 / OUTPUT $0.4025","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.09,"cached_input_per_m":0.05,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Mistral Small 3.2 24B $0.09 $0.30 $0.05","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B Instruct","maker":"Mistral AI","provider_model_id":"mistral-small-3-2-24b-instruct","tier":"standard","input_per_m":0.09375,"cached_input_per_m":null,"output_per_m":0.25,"context":256000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Mistral Small 3.2 24B Instruct | `mistral-small-3-2-24b-instruct` | $0.09375 | $0.25 | — | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-small-3.2-24b-instruct","name":"Mistral-Small-3.2-24B-Instruct-2506","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","tier":"flex","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.16,"context":128000,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Small-3.2-24B-Instruct-2506","checked":"2026-11-14","quote":"Flex (0.8×) $0.06 $0.16","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"mistral-small-3.2-24b-instruct","name":"Mistral-Small-3.2-24B-Instruct-2506","maker":"Mistral AI","provider_model_id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","tier":"priority","input_per_m":0.1125,"cached_input_per_m":null,"output_per_m":0.3,"context":128000,"precision":"fp8","source_url":"https://deepinfra.com/mistralai/Mistral-Small-3.2-24B-Instruct-2506","checked":"2026-11-14","quote":"Priority (1.5×) $0.1125 $0.30","notes":"Priority service tier (1.5× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"mixtral-8x7b-instruct","name":"Mixtral 8*7B","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.45,"cached_input_per_m":null,"output_per_m":0.7,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Mixtral 8*7B $0.45 $0.70 N/A N/A","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"muse-ember","name":"Muse Ember 1.0","maker":"Meta","provider_model_id":"muse-ember-1.0","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.004,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Muse Ember 1.0 Input $0.10 … Output $0.50 … Cache Hit $0.004","notes":"Global endpoint, prompts up to 200K tokens; longer prompts bill at long-context rates."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"muse-glimmer-30b","name":"Muse-Glimmer-30B","maker":"Meta","provider_model_id":"meta-models/Muse-Glimmer-30B","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.04,"output_per_m":1.2,"context":131072,"precision":null,"source_url":"https://deepinfra.com/meta-models/Muse-Glimmer-30B","checked":"2026-11-14","quote":"$0.30 in $1.20 out $0.04 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"muse-glimmer-30b","name":"Muse-Glimmer-30B","maker":"Meta","provider_model_id":"meta-models/Muse-Glimmer-30B","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.04,"output_per_m":1.1,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/meta-models/Muse-Glimmer-30B","checked":"2026-11-15","quote":"PRICING: INPUT $0.3 / CACHED $0.04 / OUTPUT $1.1","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"muse-glimmer-30b","name":"Muse Glimmer 30B","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":0.35,"cached_input_per_m":0.04,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Muse Glimmer 30B $0.35 $0.04 (cached) $1.50","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"muse-spark-1.3","name":"Muse Spark 1.3","maker":"Meta","provider_model_id":"muse-spark-1.3","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.15,"output_per_m":4.25,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Muse Spark 1.3 Input $1.25 … Output $4.25 … Cache Hit $0.15","notes":"Global endpoint."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"muse-spark-open","name":"Muse Spark Open","maker":"Meta","provider_model_id":"meta-models/muse-spark-open","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.15,"output_per_m":4.25,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"Muse Spark Open $1.25 $0.15 $4.25","notes":"Context from the model library page (https://www.baseten.co/library/muse-spark-open/), stated as 1M."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"muse-spark-open","name":"Muse Spark Open","maker":"Meta","provider_model_id":"accounts/fireworks/models/muse-spark-open","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.15,"output_per_m":4.25,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Muse Spark Open | $1.25 / $0.15 / $4.25 | $1.875 / $0.225 / $6.375","notes":"Runs on US-only capacity; US premium waived."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"muse-spark-open","name":"Muse Spark Open 816B A42B","maker":"Meta","provider_model_id":null,"tier":"standard","input_per_m":1.25,"cached_input_per_m":0.15,"output_per_m":4.25,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Muse Spark Open 816B A42B $1.25 $0.15 (cached) $4.25","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"muse-spark-open","name":"Muse Spark Open","maker":"Meta","provider_model_id":"muse-spark-open","tier":"standard","input_per_m":1.5625,"cached_input_per_m":0.1875,"output_per_m":5.3125,"context":1048576,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Muse Spark Open | `muse-spark-open` | $1.5625 | $5.3125 | $0.1875 | — | Private |","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"muse-spark-open","name":"Muse Spark Open","maker":"Meta","provider_model_id":"accounts/fireworks/models/muse-spark-open","tier":"priority","input_per_m":1.875,"cached_input_per_m":0.225,"output_per_m":6.375,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Muse Spark Open | Priority $1.875 / $0.225 / $6.375","notes":"Priority mode."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"muse-wonder","name":"Muse Wonder 1.0","maker":"Meta","provider_model_id":"muse-wonder-1.0","tier":"standard","input_per_m":4,"cached_input_per_m":0.2,"output_per_m":20,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Muse Wonder 1.0 Input $4.00 … Output $20.00 … Cache Hit $0.20","notes":"Global endpoint."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"nemotron-3-nano-30b-a3b","name":"NVIDIA Nemotron 3 Nano 30B A3B","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.24,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"NVIDIA Nemotron 3 Nano 30B A3B $ 0.06 $ 0.24","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"nemotron-3-nano-30b-a3b","name":"NVIDIA Nemotron 3 Nano 30B A3B","maker":"NVIDIA","provider_model_id":"nvidia/nemotron-3-nano-30b-a3b","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.2,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"NVIDIA Nemotron 3 Nano 30B A3B 256K $0.05 /Mt $0.2 /Mt","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"nemotron-3-nano-30b-a3b","name":"NVIDIA Nemotron 3 Nano 30B","maker":"NVIDIA","provider_model_id":"nvidia-nemotron-3-nano-30b-a3b","tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":128000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| NVIDIA Nemotron 3 Nano 30B | `nvidia-nemotron-3-nano-30b-a3b` | $0.075 | $0.30 | — | — | Private |","notes":""},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"nemotron-3-nano-omni-30b-a3b","name":"Nemotron 3 Nano Omni","maker":"NVIDIA","provider_model_id":"nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.3,"output_per_m":1.83,"context":262144,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"Nemotron 3 Nano Omni text, image $0.30 $1.83 $0.30","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"nemotron-3-super-120b-a12b","name":"NVIDIA Nemotron 3 Super 120B A12B","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.65,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"NVIDIA Nemotron 3 Super 120B A12B $ 0.15 $ 0.65","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"nemotron-3-super-120b-a12b","name":"Nemotron 3 120B A12B","maker":"NVIDIA","provider_model_id":"@cf/nvidia/nemotron-3-120b-a12b","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/nvidia/nemotron-3-120b-a12b $0.500 per M input tokens $1.500 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price. Cloudflare id nemotron-3-120b-a12b; mapped to Nemotron 3 Super 120B A12B."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3-super-120b-a12b","name":"NVIDIA-Nemotron-3-Super-120B-A12B","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.4,"context":262144,"precision":"bfloat16","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","checked":"2026-11-14","quote":"$0.075 in $0.40 out / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3-super-120b-a12b","name":"NVIDIA-Nemotron-3-Super-120B-A12B","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","tier":"flex","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.32,"context":262144,"precision":"bfloat16","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","checked":"2026-11-14","quote":"Flex (0.8×) $0.06 $0.32","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3-super-120b-a12b","name":"NVIDIA-Nemotron-3-Super-120B-A12B","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","tier":"priority","input_per_m":0.1125,"cached_input_per_m":null,"output_per_m":0.6,"context":262144,"precision":"bfloat16","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","checked":"2026-11-14","quote":"Priority (1.5×) $0.1125 $0.60","notes":"Priority service tier (1.5× standard)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"FW NVIDIA Nemotron 3U","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.66,"cached_input_per_m":0.13,"output_per_m":2.64,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW NVIDIA Nemotron 3U Data Zone\tInput: $0.66/1M Tokens | Cached Input: $0.13/1M Tokens | Output: $2.64/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment. Name abbreviation \"3U\" read as Nemotron 3 Ultra."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":0.12,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"NVIDIA Nemotron 3 Ultra $0.60 $0.12 $2.40","notes":""},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":2.15,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"NVIDIA Nemotron 3 Ultra $0.50 $2.15 $0.10","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":2.2,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","checked":"2026-11-14","quote":"$0.50 in $2.20 out $0.10 cached / 1M tokens","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","maker":"NVIDIA","provider_model_id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","tier":"standard","input_per_m":0.6,"cached_input_per_m":0.12,"output_per_m":2.4,"context":null,"precision":"nvfp4","source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"NVIDIA Nemotron 3 Ultra (Preview) | $0.60 / $0.12 / $2.40 | $0.75 / $0.15 / $3.00","notes":"Listed as Preview. Priced in the serverless pricing table; not shown in the serverless model library filter on 2026-11-14."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"Nemotron 3 ultra","maker":"NVIDIA","provider_model_id":"nvidia/nemotron-3-ultra-550b-a55b","tier":"standard","input_per_m":0.8,"cached_input_per_m":0.1,"output_per_m":2.6,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/nemotron-3-ultra/d742e342-4051-4098-9401-b0de97a6ecbb","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.80 Output $2.60 Cache Read $0.10 Cache Write -","notes":""},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra","maker":"NVIDIA","provider_model_id":"nemotron-3-ultra-550b-a55b","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":2.2,"context":262000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"Nemotron 3 Ultra nemotron-3-ultra-550b-a55b NVIDIA · 262K context · Text $0.50 $2.20 $0.10","notes":"Context shown on page as \"262K\" (rounded); stored as the decimal value."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B (NVFP4)","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":2.5,"context":null,"precision":"nvfp4","source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Nemotron 3 Ultra 550B (NVFP4) $0.50 $2.50 $0.10","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","maker":"NVIDIA","provider_model_id":"nvidia-nemotron-3-ultra-550b-a55b","tier":"standard","input_per_m":0.625,"cached_input_per_m":0.1875,"output_per_m":3.125,"context":256000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| NVIDIA Nemotron 3 Ultra | `nvidia-nemotron-3-ultra-550b-a55b` | $0.625 | $3.125 | $0.1875 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","tier":"flex","input_per_m":0.4,"cached_input_per_m":0.08,"output_per_m":1.76,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","checked":"2026-11-14","quote":"Flex (0.8×) $0.40 $1.76 $0.08","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA-Nemotron-3-Ultra-550B-A55B","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","tier":"priority","input_per_m":0.75,"cached_input_per_m":0.15,"output_per_m":3.3,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","checked":"2026-11-14","quote":"Priority (1.5×) $0.75 $3.30 $0.15","notes":"Priority service tier (1.5× standard)."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","maker":"NVIDIA","provider_model_id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","tier":"priority","input_per_m":0.75,"cached_input_per_m":0.15,"output_per_m":3,"context":null,"precision":"nvfp4","source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"NVIDIA Nemotron 3 Ultra (Preview) | Priority $0.75 / $0.15 / $3.00","notes":"Priority mode."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-content-safety","name":"Nemotron-Content-Safety-3.5","maker":"NVIDIA","provider_model_id":"nvidia/Nemotron-Content-Safety-3.5","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.2,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/nvidia/Nemotron-Content-Safety-3.5","checked":"2026-11-14","quote":"$0.20 / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-content-safety","name":"Nemotron-Content-Safety-3.5","maker":"NVIDIA","provider_model_id":"nvidia/Nemotron-Content-Safety-3.5","tier":"flex","input_per_m":0.16,"cached_input_per_m":null,"output_per_m":0.16,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/nvidia/Nemotron-Content-Safety-3.5","checked":"2026-11-14","quote":"Flex (0.8×) $0.16 $0.16","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-content-safety","name":"Nemotron-Content-Safety-3.5","maker":"NVIDIA","provider_model_id":"nvidia/Nemotron-Content-Safety-3.5","tier":"priority","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.3,"context":131072,"precision":"bfloat16","source_url":"https://deepinfra.com/nvidia/Nemotron-Content-Safety-3.5","checked":"2026-11-14","quote":"Priority (1.5×) $0.30 $0.30","notes":"Priority service tier (1.5× standard)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-lightning","name":"FW NVIDIA Nemotron 3.5 LN","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.06,"cached_input_per_m":0.01,"output_per_m":0.22,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/","checked":"2026-11-14","quote":"FW NVIDIA Nemotron 3.5 LN Data Zone\tInput: $0.06/1M Tokens | Cached Input: $0.01/1M Tokens | Output: $0.22/1M Tokens","notes":"Foundry Models serverless, served by Fireworks on Azure, Data Zone deployment. \"3.5 LN\" read as Nemotron 3.5 Lightning."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-lightning","name":"NVIDIA Nemotron 3.5 Lightning","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","tier":"standard","input_per_m":0.07,"cached_input_per_m":0.04,"output_per_m":0.2,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"NVIDIA Nemotron 3.5 Lightning $0.07 $0.20 $0.04","notes":""},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B A3B","maker":"NVIDIA","provider_model_id":"nvidia/nemotron-3.5-lightning-30b-a3b","tier":"standard","input_per_m":0.05,"cached_input_per_m":0.03,"output_per_m":0.2,"context":1048576,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"Nemotron 3.5 Lightning 30B A3B $0.05 $0.20 $0.03","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-lightning","name":"NVIDIA-Nemotron-3.5-Lightning","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Lightning","tier":"standard","input_per_m":0.06,"cached_input_per_m":0.03,"output_per_m":0.16,"context":262144,"precision":null,"source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning","checked":"2026-11-14","quote":"$0.06 in $0.16 out $0.03 cached / 1M tokens","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-lightning","name":"NVIDIA Nemotron 3.5 Lightning 30B A3B","maker":"NVIDIA","provider_model_id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","tier":"standard","input_per_m":0.05,"cached_input_per_m":0.01,"output_per_m":0.2,"context":262144,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"NVIDIA Nemotron 3.5 Lightning 30B A3B | $0.05 / $0.01 / $0.20 | $0.0625 / $0.0125 / $0.25","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-lightning","name":"NVIDIA Nemotron 3.5 Lightning 30B A3B","maker":"NVIDIA","provider_model_id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","tier":"priority","input_per_m":0.0625,"cached_input_per_m":0.0125,"output_per_m":0.25,"context":262144,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"NVIDIA Nemotron 3.5 Lightning 30B A3B | Priority $0.0625 / $0.0125 / $0.25","notes":"Priority mode."},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":false,"model":"nemotron-3.5-super-120b-a12b","name":"Nemotron 3.5 Super","maker":"NVIDIA","provider_model_id":"perplexity/nemotron-3.5-super-120b-a12b","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`perplexity/nemotron-3.5-super-120b-a12b` | 0.20 | 0.50 | 0.04","notes":"Hosted by Perplexity (\"Perplexity-Hosted Models\"); tool calls billed separately."},{"provider":"baseten","provider_name":"Baseten","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-super-vl","name":"Nemotron 3.5 Super VL","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":0.5,"context":1000000,"precision":null,"source_url":"https://www.baseten.co/pricing/","checked":"2026-11-14","quote":"Nemotron 3.5 Super VL $0.20 $0.04 $0.50","notes":"Context from the model library page (https://www.baseten.co/library/nemotron-35-super-vl/), stated as 1M."},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-super-vl","name":"Nemotron 3.5 Super VL 120B A12B","maker":"NVIDIA","provider_model_id":"nvidia/nemotron-3.5-super-vl-120b-a12b","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.08,"output_per_m":0.4,"context":262144,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"Nemotron 3.5 Super VL 120B A12B text, image, video $0.10 $0.40 $0.08","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-super-vl","name":"NVIDIA-Nemotron-3.5-Super-VL","maker":"NVIDIA","provider_model_id":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.02,"output_per_m":0.5,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Super-VL","checked":"2026-11-14","quote":"$0.15 in $0.50 out $0.02 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":0.65,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"NVIDIA Nemotron 3.5 Super VL — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.30$0.65$0.06","notes":"DigitalOcean-hosted."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.02,"output_per_m":0.5,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"NVIDIA Nemotron 3.5 Super VL $0.15 $0.02 (cached) $0.50","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"nemotron-3.5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL 120B","maker":"NVIDIA","provider_model_id":"nvidia-nemotron-3-5-super-vl-120b-a12b","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":0.5,"context":262144,"precision":"fp4","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| NVIDIA Nemotron 3.5 Super VL 120B | `nvidia-nemotron-3-5-super-vl-120b-a12b` | $0.20 | $0.50 | $0.04 | — | Private |","notes":""},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"nemotron-nano-2","name":"NVIDIA Nemotron Nano 2","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.23,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"NVIDIA Nemotron Nano 2 $ 0.06 $ 0.23","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"nemotron-nano-2-vl","name":"NVIDIA Nemotron Nano 2 VL","maker":"NVIDIA","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"NVIDIA Nemotron Nano 2 VL $ 0.20 $ 0.60","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-lite-v1","name":"Nova 2 Lite","maker":"Amazon","provider_model_id":"Amazon Nova 2 Lite","tier":"standard","input_per_m":0.33,"cached_input_per_m":null,"output_per_m":2.75,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova 2 Lite\t$0.33\t$2.75","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Global cross-region inference is cheaper: 0.30 input, 2.50 output per 1M (standard tier)."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-lite-v1","name":"Nova 2 Lite","maker":"Amazon","provider_model_id":"Amazon Nova 2 Lite","tier":"batch","input_per_m":0.1595,"cached_input_per_m":null,"output_per_m":1.342,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Amazon Nova 2 Lite\t$0.1595\t$1.342 (Geo Cross-region inference and in-region, Region: US East (Ohio), \"Batch\" table)","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Global cross-region inference is cheaper: 0.30 input, 2.50 output per 1M (standard tier)."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-lite-v1","name":"Nova 2 Lite","maker":"Amazon","provider_model_id":"Amazon Nova 2 Lite","tier":"flex","input_per_m":0.165,"cached_input_per_m":null,"output_per_m":1.375,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Flex Tier ... Amazon Nova 2 Lite\t$0.165\t$1.375","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Global cross-region inference is cheaper: 0.30 input, 2.50 output per 1M (standard tier)."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-lite-v1","name":"Nova 2 Lite","maker":"Amazon","provider_model_id":"Amazon Nova 2 Lite","tier":"priority","input_per_m":0.5775,"cached_input_per_m":null,"output_per_m":4.8125,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Priority Tier ... Amazon Nova 2 Lite\t$0.5775\t$4.8125","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Global cross-region inference is cheaper: 0.30 input, 2.50 output per 1M (standard tier)."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-omni","name":"Nova 2 Omni (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Omni (Preview)","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":2.8,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova 2 Omni (Preview)\t$0.30\t... $2.80","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview, multimodal (also outputs images, priced separately). Text input and text output prices. Global cross-region inference: 0.30 input, 2.50 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-omni","name":"Nova 2 Omni (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Omni (Preview)","tier":"batch","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":1.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Batch ... Amazon Nova 2 Omni (Preview)\t$0.20\t... $1.40","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview, multimodal (also outputs images, priced separately). Text input and text output prices. Global cross-region inference: 0.30 input, 2.50 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-omni","name":"Nova 2 Omni (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Omni (Preview)","tier":"flex","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":1.4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Flex Tier ... Amazon Nova 2 Omni (Preview)\t$0.20\t... $1.40","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview, multimodal (also outputs images, priced separately). Text input and text output prices. Global cross-region inference: 0.30 input, 2.50 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-omni","name":"Nova 2 Omni (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Omni (Preview)","tier":"priority","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":4.8,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Priority Tier ... Amazon Nova 2 Omni (Preview)\t$0.60\t... $4.80","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview, multimodal (also outputs images, priced separately). Text input and text output prices. Global cross-region inference: 0.30 input, 2.50 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-pro","name":"Nova 2 Pro (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Pro (Preview)","tier":"standard","input_per_m":1.375,"cached_input_per_m":null,"output_per_m":11,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova 2 Pro (Preview)\t$1.375\t... $11.00","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-pro","name":"Nova 2 Pro (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Pro (Preview)","tier":"batch","input_per_m":0.6875,"cached_input_per_m":null,"output_per_m":5.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Batch ... Amazon Nova 2 Pro (Preview)\t$0.6875\t... $5.50","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-pro","name":"Nova 2 Pro (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Pro (Preview)","tier":"flex","input_per_m":0.6875,"cached_input_per_m":null,"output_per_m":5.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Flex Tier ... Amazon Nova 2 Pro (Preview)\t$0.6875\t... $5.50","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-2-pro","name":"Nova 2 Pro (Preview)","maker":"Amazon","provider_model_id":"Amazon Nova 2 Pro (Preview)","tier":"priority","input_per_m":2.40625,"cached_input_per_m":null,"output_per_m":19.25,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Priority Tier ... Amazon Nova 2 Pro (Preview)\t$2.40625\t... $19.25","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-lite-v1","name":"Nova Lite 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Lite","tier":"standard","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.24,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova Lite\t$0.06\t$0.24","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-lite-v1","name":"Nova Lite 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Lite","tier":"batch","input_per_m":0.03,"cached_input_per_m":null,"output_per_m":0.12,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Batch ... Amazon Nova Lite\t$0.03\t$0.12","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-micro-v1","name":"Nova Micro 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Micro","tier":"standard","input_per_m":0.035,"cached_input_per_m":null,"output_per_m":0.14,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova Micro\t$0.035\t$0.14","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-micro-v1","name":"Nova Micro 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Micro","tier":"batch","input_per_m":0.0175,"cached_input_per_m":null,"output_per_m":0.07,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Batch ... Amazon Nova Micro\t$0.0175\t$0.07","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-premier-v1","name":"Nova Premier 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Premier","tier":"standard","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":12.5,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova Premier\t$2.50\t$12.50","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-premier-v1","name":"Nova Premier 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Premier","tier":"batch","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":6.25,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Amazon Nova Premier\t$1.25\t$6.25 (Geo Cross-region inference and in-region, Region: US East (Ohio), \"Batch\" table)","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-premier-v1","name":"Nova Premier 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Premier","tier":"flex","input_per_m":1.25,"cached_input_per_m":null,"output_per_m":6.25,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Amazon Nova Premier\t$1.25\t$6.25 (Geo Cross-region inference and in-region, Region: US East (Ohio), \"Flex Tier\" table)","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-premier-v1","name":"Nova Premier 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Premier","tier":"priority","input_per_m":4.375,"cached_input_per_m":null,"output_per_m":21.875,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-15","quote":"Amazon Nova Premier\t$4.375\t$21.875 (Geo Cross-region inference and in-region, Region: US East (Ohio), \"Priority Tier\" table)","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-pro-v1","name":"Nova Pro 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Pro","tier":"standard","input_per_m":0.8,"cached_input_per_m":null,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Standard Tier ... Amazon Nova Pro\t$0.80\t$3.20","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-pro-v1","name":"Nova Pro 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Pro","tier":"batch","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Batch ... Amazon Nova Pro\t$0.40\t$1.60","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-pro-v1","name":"Nova Pro 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Pro","tier":"flex","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Flex Tier ... Amazon Nova Pro\t$0.40\t$1.60","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-pro-v1","name":"Nova Pro 1.0","maker":"Amazon","provider_model_id":"Amazon Nova Pro","tier":"priority","input_per_m":1.4,"cached_input_per_m":null,"output_per_m":5.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Priority Tier ... Amazon Nova Pro\t$1.40\t$5.60","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"amazon-nova","provider_name":"Amazon Nova (Bedrock)","provider_kind":"maker","maker_api":true,"model":"nova-pro-v1","name":"Nova Pro 1.0 (latency optimized)","maker":"Amazon","provider_model_id":"Amazon Nova Pro (w/ latency optimized inference)","tier":"fast","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Amazon Nova Pro (w/ latency optimized inference)\t$1.00\t$4.00","notes":"Bedrock \"Geo Cross-region inference and in-region\" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Latency-optimized inference row in the Standard Tier table. Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o1","name":"o1 (2024-12-17)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":15,"cached_input_per_m":7.5,"output_per_m":60,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o1 2024-12-17 Global\tInput: $15 | Cached Input: $7.50 | Output: $60","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o1-mini","name":"o1-mini (2024-09-12)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.1,"cached_input_per_m":0.55,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o1-mini 2024-09-12 Global\tInput: $1.10 | Cached Input: $0.55 | Output: $4.40","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o3","name":"o3 (2025-04-16)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":8,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o3 2025-04-16 Global\tInput: $2 | Cached Input: $0.50 | Output: $8","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":8,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"o3 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.00$8.00$0.50","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":"o3","tier":"standard","input_per_m":2,"cached_input_per_m":0.5,"output_per_m":8,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| o3 | $2.00 | $8.00 | $0.50 |","notes":""},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o3","name":"o3 (2025-04-16)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o3 2025-04-16 Global\tInput: $1 | Output: $4","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":"o3","tier":"batch","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| o3 | $1.00 | $4.00 | - |","notes":"Batch API (asynchronous)."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":null,"tier":"flex","input_per_m":1,"cached_input_per_m":0.25,"output_per_m":4,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"o3 — Processing modePrompt lengthInputOutputCache read: Flex Mode All prompts$1.00$4.00$0.25","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":"o3","tier":"flex","input_per_m":1,"cached_input_per_m":0.25,"output_per_m":4,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| o3 | $1.00 | $4.00 | $0.25 |","notes":"Flex processing."},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":null,"tier":"fast","input_per_m":3.5,"cached_input_per_m":0.875,"output_per_m":14,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"o3 — Processing modePrompt lengthInputOutputCache read: Fast Mode All prompts$3.50$14.00$0.875","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"o3","name":"o3","maker":"OpenAI","provider_model_id":"o3","tier":"fast","input_per_m":3.5,"cached_input_per_m":0.875,"output_per_m":14,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| o3 | $3.50 | $14.00 | $0.875 |","notes":"Fast mode (formerly Priority processing)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o3-deep-research","name":"o3 Deep Research","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":10,"cached_input_per_m":2.5,"output_per_m":40,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o3-deep research Global\tInput: $10 | Cached Input: $2.50 | Output: $40","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o3-mini","name":"o3-mini (2025-01-31)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.1,"cached_input_per_m":0.55,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o3 mini 2025-01-31 Global\tInput: $1.10 | Cached Input: $0.55 | Output: $4.40","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o3-mini","name":"o3-mini (2025-01-31)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.55,"cached_input_per_m":null,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o3 mini 2025-01-31 Global\tInput: $0.55 | Output: $2.20","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"o3-pro","name":"o3 Pro","maker":"OpenAI","provider_model_id":"o3-pro","tier":"standard","input_per_m":20,"cached_input_per_m":null,"output_per_m":80,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| o3-pro | $20.00 | $80.00 | - |","notes":""},{"provider":"openai","provider_name":"OpenAI","provider_kind":"maker","maker_api":true,"model":"o3-pro","name":"o3 Pro","maker":"OpenAI","provider_model_id":"o3-pro","tier":"batch","input_per_m":10,"cached_input_per_m":null,"output_per_m":40,"context":null,"precision":null,"source_url":"https://developers.openai.com/api/docs/pricing","checked":"2026-11-14","quote":"| o3-pro | $10.00 | $40.00 | - |","notes":"Batch API (asynchronous)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o4-mini","name":"o4-mini (2025-04-16)","maker":"OpenAI","provider_model_id":null,"tier":"standard","input_per_m":1.1,"cached_input_per_m":0.28,"output_per_m":4.4,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o4-mini 2025-04-16 Global\tInput: $1.10 | Cached Input: $0.28 | Output: $4.40","notes":"Azure OpenAI Global (global standard) deployment."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"o4-mini","name":"o4-mini (2025-04-16)","maker":"OpenAI","provider_model_id":null,"tier":"batch","input_per_m":0.55,"cached_input_per_m":null,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/azure-openai/","checked":"2026-11-14","quote":"o4-mini 2025-04-16 Global\tInput: $0.55 | Output: $2.20","notes":"Azure OpenAI Global deployment, \"Pricing with Batch API (1M Tokens)\" column."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"palmyra-vision-7b","name":"Palmyra Vision 7B","maker":"Writer","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Palmyra Vision 7B $0.15 $0.60","notes":"On-demand table; the page names no region for Writer prices."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"palmyra-x4","name":"Palmyra X4","maker":"Writer","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":null,"output_per_m":10,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Palmyra X4 $2.50 $10.00","notes":"On-demand table; the page names no region for Writer prices."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"palmyra-x5","name":"Palmyra X5","maker":"Writer","provider_model_id":null,"tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Palmyra X5 $0.60 $6.00","notes":"On-demand table; the page names no region for Writer prices."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3-medium-128k-instruct","name":"Phi-3-medium-128k-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.17,"cached_input_per_m":null,"output_per_m":0.68,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3-medium-128k-instruct\t128K\t$0.17\t$0.68","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3-medium-4k-instruct","name":"Phi-3-medium-4k-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.17,"cached_input_per_m":null,"output_per_m":0.68,"context":4096,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3-medium-4k-instruct\t4K\t$0.17\t$0.68","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"4K\" (stored as 4096)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3-mini-128k-instruct","name":"Phi-3-mini-128k-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.13,"cached_input_per_m":null,"output_per_m":0.52,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3-mini-128k-instruct\t128K\t$0.13\t$0.52","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3-mini-4k-instruct","name":"Phi-3-mini-4k-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.13,"cached_input_per_m":null,"output_per_m":0.52,"context":4096,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3-mini-4k-instruct\t4K\t$0.13\t$0.52","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"4K\" (stored as 4096)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3-small-128k-instruct","name":"Phi-3-small-128k-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3-small-128k-instruct\t128K\t$0.15\t$0.60","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3-small-8k-instruct","name":"Phi-3-small-8k-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":8192,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3-small-8k-instruct\t8K\t$0.15\t$0.60","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"8K\" (stored as 8192)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3.5-mini-instruct","name":"Phi-3.5-mini-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.13,"cached_input_per_m":null,"output_per_m":0.52,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3.5-mini-instruct\t128K\t$0.13\t$0.52","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-3.5-moe-instruct","name":"Phi-3.5-MoE-instruct","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.16,"cached_input_per_m":null,"output_per_m":0.64,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-3.5-MoE-instruct\t128K\t$0.16\t$0.64","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-4","name":"Phi-4","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.5,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-4\t128K\t$0.125\t$0.50","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"phi-4","name":"phi-4","maker":"Microsoft","provider_model_id":"microsoft/phi-4","tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.14,"context":16384,"precision":"bfloat16","source_url":"https://deepinfra.com/microsoft/phi-4","checked":"2026-11-14","quote":"$0.07 in $0.14 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"phi-4","name":"phi-4","maker":"Microsoft","provider_model_id":"microsoft/phi-4","tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.14,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/microsoft/phi-4","checked":"2026-11-15","quote":"PRICING: INPUT $0.07 / OUTPUT $0.14","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"phi-4","name":"phi-4","maker":"Microsoft","provider_model_id":"microsoft/phi-4","tier":"flex","input_per_m":0.056,"cached_input_per_m":null,"output_per_m":0.112,"context":16384,"precision":"bfloat16","source_url":"https://deepinfra.com/microsoft/phi-4","checked":"2026-11-14","quote":"Flex (0.8×) $0.056 $0.112","notes":"Flex service tier (0.8× standard)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-4-mini","name":"Phi-4-mini","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-4-mini\t128K\t$0.075\t$0.30","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-4-mini-reasoning\t128K\t$0.075\t$0.30","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-4-multimodal","name":"Phi-4-multimodal, text and image","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.32,"context":131072,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-4-multimodal, text and image\t128K\t$0.08\t$0.32","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"128K\" (stored as 131072)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-4-reasoning","name":"Phi-4-reasoning","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.5,"context":32768,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-4-reasoning\t32K\t$0.125\t$0.50","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"32K\" (stored as 32768)."},{"provider":"azure","provider_name":"Microsoft Azure (Azure OpenAI + Foundry Models)","provider_kind":"host","maker_api":false,"model":"phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","maker":"Microsoft","provider_model_id":null,"tier":"standard","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.5,"context":32768,"precision":null,"source_url":"https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/","checked":"2026-11-14","quote":"Phi-4-reasoning-plus\t32K\t$0.125\t$0.50","notes":"Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: \"32K\" (stored as 32768)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"phonellm-mini-alpha-2","name":"PhoneLLM Mini Alpha 2","maker":"Daily","provider_model_id":"@cf/daily-co/phonellm-mini-alpha-2","tier":"standard","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.24,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/daily-co/phonellm-mini-alpha-2 $0.060 per M input tokens $0.240 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"pixtral-large-2502","name":"Pixtral Large (25.02)","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Pixtral Large (25.02) $2.00 $6.00 N/A N/A","notes":"Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","maker":"Qwen","provider_model_id":"@cf/qwen/qwen2.5-coder-32b-instruct","tier":"standard","input_per_m":0.66,"cached_input_per_m":null,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/qwen/qwen2.5-coder-32b-instruct $0.660 per M input tokens $1.000 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen-2.5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen2.5-Coder-32B-Instruct","tier":"standard","input_per_m":0.68,"cached_input_per_m":null,"output_per_m":1.2,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen2.5-Coder-32B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.68 / OUTPUT $1.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen-flash","name":"Qwen-Flash","maker":"Qwen","provider_model_id":"qwen-flash","tier":"standard","input_per_m":0.05,"cached_input_per_m":0.01,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen-flash Currently equivalent to qwen-flash-2025-07-28 50% batch inference discount context caching discount International 0<Token≤256K $0.05 $0.4","notes":"International (Singapore) deployment. Prompts up to 256K tokens; 256K–1M: 0.25 input, 2 output. The page marks this model \"50% batch inference discount\" (batch bills input and output at 50% of the real-time price); no separate batch price is listed. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen-max","name":"Qwen-Max","maker":"Qwen","provider_model_id":"qwen-max","tier":"standard","input_per_m":1.6,"cached_input_per_m":0.32,"output_per_m":6.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen-max 50% batch inference discount International Non-Thinking mode only No tiered pricing $1.6 $6.4","notes":"International (Singapore) deployment. Non-thinking mode only. The page marks this model \"50% batch inference discount\" (batch bills input and output at 50% of the real-time price); no separate batch price is listed. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen-mt-flash","name":"Qwen-MT Flash","maker":"Qwen","provider_model_id":"qwen-mt-flash","tier":"standard","input_per_m":0.16,"cached_input_per_m":null,"output_per_m":0.49,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen-mt-flash International $0.16 $0.49","notes":"International (Singapore) deployment. Translation model."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen-mt-lite","name":"Qwen-MT Lite","maker":"Qwen","provider_model_id":"qwen-mt-lite","tier":"standard","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.36,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen-mt-lite International $0.12 $0.36","notes":"International (Singapore) deployment. Translation model."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen-mt-plus","name":"Qwen-MT Plus","maker":"Qwen","provider_model_id":"qwen-mt-plus","tier":"standard","input_per_m":2.46,"cached_input_per_m":null,"output_per_m":7.37,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen-mt-plus International $2.46 $7.37","notes":"International (Singapore) deployment. Translation model."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen-mt-plus","name":"Qwen MT Plus","maker":"Qwen","provider_model_id":"qwen/qwen-mt-plus","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":0.75,"context":16384,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen MT Plus 16K $0.25 /Mt $0.75 /Mt","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen-plus","name":"Qwen-Plus","maker":"Qwen","provider_model_id":"qwen-plus","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.08,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen-plus Currently equivalent to qwen-plus-2025-12-01 International 0<Token≤256K $0.4 $1.2 $4","notes":"International (Singapore) deployment. Output price is non-thinking mode; thinking-mode output is 4. Prompts up to 256K tokens; 256K–1M token prompts: 1.2 input, 3.6 output (12 thinking). Alias currently points to qwen-plus-2025-12-01. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen2.5-72b-instruct","name":"Qwen2.5-72B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen2.5-72B-Instruct","tier":"standard","input_per_m":0.36,"cached_input_per_m":null,"output_per_m":0.4,"context":32768,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct","checked":"2026-11-14","quote":"$0.36 in $0.40 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen2.5-72b-instruct","name":"Qwen2.5-72B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen2.5-72B-Instruct","tier":"standard","input_per_m":0.37,"cached_input_per_m":null,"output_per_m":0.4,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen2.5-72B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.37 / OUTPUT $0.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen2.5-72b-instruct","name":"Qwen2.5-72B-Instruct","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.59,"cached_input_per_m":null,"output_per_m":0.59,"context":32768,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen2.5-72B-Instruct 33K $0.59 $0.59","notes":"Context shown as 33K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen2.5-72b-instruct","name":"Qwen2.5-72B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen2.5-72B-Instruct","tier":"flex","input_per_m":0.288,"cached_input_per_m":null,"output_per_m":0.32,"context":32768,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct","checked":"2026-11-14","quote":"Flex (0.8×) $0.288 $0.32","notes":"Flex service tier (0.8× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen2.5-7b-instruct","name":"Qwen2.5-7B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen2.5-7B-Instruct","tier":"standard","input_per_m":0.17,"cached_input_per_m":0.136,"output_per_m":0.2,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen2.5-7B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.17 / CACHED $0.136 / OUTPUT $0.2","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen2.5-7b-instruct","name":"Qwen2.5-7B-Instruct","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.05,"context":32768,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen2.5-7B-Instruct 33K $0.05 $0.05","notes":"Context shown as 33K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen2.5-7b-instruct","name":"Qwen 2.5 7B","maker":"Qwen","provider_model_id":"e2ee-qwen-2-5-7b-p","tier":"standard","input_per_m":0.05,"cached_input_per_m":null,"output_per_m":0.13,"context":32000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 2.5 7B | `e2ee-qwen-2-5-7b-p` | $0.05 | $0.13 | — | — | E2EE |","notes":"End-to-end encrypted (E2EE) tier, runs in a TEE."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"qwen2.5-7b-instruct-turbo","name":"Qwen2.5 7B Instruct Turbo","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Qwen2.5 7B Instruct Turbo $0.30 $0.30","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen2.5-vl-72b-instruct","name":"Qwen2.5-VL 72B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.8,"cached_input_per_m":0.4,"output_per_m":1,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen2.5-VL 72B $0.80 $1.00 $0.40","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-14b","name":"Qwen3-14B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-14B","tier":"standard","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.24,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-14B","checked":"2026-11-14","quote":"$0.12 in $0.24 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-14b","name":"Qwen3-14B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-14B","tier":"standard","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.24,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-14B","checked":"2026-11-15","quote":"PRICING: INPUT $0.12 / OUTPUT $0.24","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-14b","name":"Qwen3-14B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.28,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-14B 131K $0.07 $0.28","notes":"Context shown as 131K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-14b","name":"Qwen3-14B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-14B","tier":"flex","input_per_m":0.096,"cached_input_per_m":null,"output_per_m":0.192,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-14B","checked":"2026-11-14","quote":"Flex (0.8×) $0.096 $0.192","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-14b","name":"Qwen3-14B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-14B","tier":"priority","input_per_m":0.18,"cached_input_per_m":null,"output_per_m":0.36,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-14B","checked":"2026-11-14","quote":"Priority (1.5×) $0.18 $0.36","notes":"Priority service tier (1.5× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b","name":"Qwen3-235B-A22B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B","tier":"standard","input_per_m":0.455,"cached_input_per_m":null,"output_per_m":1.82,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-235B-A22B","checked":"2026-11-15","quote":"PRICING: INPUT $0.455 / OUTPUT $1.82","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b","name":"Qwen3 235B A22B FP8","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-FP8","tier":"standard","input_per_m":0.17,"cached_input_per_m":null,"output_per_m":1.09,"context":32768,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-235b-a22b-fp8/a013cb9e-9e7c-4ab2-9b15-d4a86fe4827c","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.17 Output $1.09","notes":"No cache-read price published."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3-235B-A22B-Instruct-2507","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","tier":"standard","input_per_m":0.09,"cached_input_per_m":null,"output_per_m":0.55,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-235B-A22B-Instruct-2507","checked":"2026-11-14","quote":"$0.09 in $0.55 out / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507 FP8","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507-FP8","tier":"standard","input_per_m":0.0875,"cached_input_per_m":0.0175,"output_per_m":0.35,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-235b-a22b-instruct-2507-fp8/b464533f-fe7c-4c2b-849b-8d913169584f","checked":"2026-11-15","quote":"Price (per 1M tokens) 75% off Input $0.0875 $0.35 Output $0.35 $1.40 Cache Read $0.0175 $0.07 Cache Write -","notes":"Promotional price, 75% off list (list 0.35 in / 1.4 out / 0.07 cached)."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","maker":"Qwen","provider_model_id":"qwen3-235b-a22b-instruct-2507","tier":"standard","input_per_m":0.22,"cached_input_per_m":null,"output_per_m":0.88,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Qwen3-235B-A22B-Instruct-2507 Input $0.22 … Output $0.88","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3 235B-A22B (2507)","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":0.05,"output_per_m":0.8,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3 235B-A22B (2507) $0.14 $0.80 $0.05","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen 3 235B A22B Instruct 2507","maker":"Qwen","provider_model_id":"qwen3-235b-a22b-instruct-2507","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.75,"context":128000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3 235B A22B Instruct 2507 | `qwen3-235b-a22b-instruct-2507` | $0.15 | $0.75 | — | — | Private |","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","maker":"Qwen","provider_model_id":"qwen3-235b-a22b-instruct-2507","tier":"batch","input_per_m":0.11,"cached_input_per_m":null,"output_per_m":0.44,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Qwen3-235B-A22B-Instruct-2507 Batch Input $0.11 … Batch Output $0.44","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3-235B-A22B-Instruct-2507","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","tier":"flex","input_per_m":0.072,"cached_input_per_m":null,"output_per_m":0.44,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-235B-A22B-Instruct-2507","checked":"2026-11-14","quote":"Flex (0.8×) $0.072 $0.44","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-2507","name":"Qwen3-235B-A22B-Instruct-2507","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","tier":"priority","input_per_m":0.135,"cached_input_per_m":null,"output_per_m":0.825,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-235B-A22B-Instruct-2507","checked":"2026-11-14","quote":"Priority (1.5×) $0.135 $0.825","notes":"Priority service tier (1.5× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507","tier":"standard","input_per_m":0.45,"cached_input_per_m":null,"output_per_m":3.5,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-235B-A22B-Thinking-2507","checked":"2026-11-15","quote":"PRICING: INPUT $0.45 / OUTPUT $3.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507 FP8","maker":"Qwen","provider_model_id":"Qwen/Qwen3-235B-A22B-Thinking-2507-FP8","tier":"standard","input_per_m":0.35,"cached_input_per_m":null,"output_per_m":4.2,"context":131072,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-235b-a22b-thinking-2507-fp8/8beab62a-79de-4d64-adf9-4abe6d96e7f3","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.35 Output $4.20","notes":"No cache-read price published."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3-235b-a22b-thinking-2507","name":"Qwen 3 235B A22B Thinking 2507","maker":"Qwen","provider_model_id":"qwen3-235b-a22b-thinking-2507","tier":"standard","input_per_m":0.45,"cached_input_per_m":null,"output_per_m":3.5,"context":128000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3 235B A22B Thinking 2507 | `qwen3-235b-a22b-thinking-2507` | $0.45 | $3.50 | — | — | Private |","notes":""},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b","name":"Qwen3 30B A3B (fp8)","maker":"Qwen","provider_model_id":"@cf/qwen/qwen3-30b-a3b-fp8","tier":"standard","input_per_m":0.051,"cached_input_per_m":null,"output_per_m":0.335,"context":null,"precision":"fp8","source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/qwen/qwen3-30b-a3b-fp8 $0.051 per M input tokens $0.335 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-30B-A3B","tier":"standard","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.5,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-30B-A3B","checked":"2026-11-14","quote":"$0.12 in $0.50 out / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-30B-A3B","tier":"standard","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.25,"context":40946,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/qwen3-30b-a3b/e8c203de-a4af-4026-a5db-cbbfc0b82fa7","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.08 Output $0.25","notes":"No cache-read price published."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-30B-A3B","tier":"flex","input_per_m":0.096,"cached_input_per_m":null,"output_per_m":0.4,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-30B-A3B","checked":"2026-11-14","quote":"Flex (0.8×) $0.096 $0.40","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b","name":"Qwen3-30B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-30B-A3B","tier":"priority","input_per_m":0.18,"cached_input_per_m":null,"output_per_m":0.75,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-30B-A3B","checked":"2026-11-14","quote":"Priority (1.5×) $0.18 $0.75","notes":"Priority service tier (1.5× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b-instruct-2507","name":"Qwen3-30B-A3B-Instruct-2507","maker":"Qwen","provider_model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","tier":"standard","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.45,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-30B-A3B-Instruct-2507","checked":"2026-11-15","quote":"PRICING: INPUT $0.125 / OUTPUT $0.45","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-30b-a3b-instruct-2507","name":"Qwen3-30B-A3B-Instruct-2507","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.09,"cached_input_per_m":null,"output_per_m":0.3,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-30B-A3B-Instruct-2507 262K $0.09 $0.3","notes":"Context shown as 262K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3 32B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 32B $0.15 $0.60","notes":"Standard tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3-32B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-32B","tier":"standard","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.28,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-32B","checked":"2026-11-14","quote":"$0.08 in $0.28 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3-32B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-32B","tier":"standard","input_per_m":0.102,"cached_input_per_m":0.0816,"output_per_m":0.493,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-32B","checked":"2026-11-15","quote":"PRICING: INPUT $0.102 / CACHED $0.0816 / OUTPUT $0.493","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3 32B FP8","maker":"Qwen","provider_model_id":"Qwen/Qwen3-32B-FP8","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.6,"context":32768,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-32b-fp8/ae9cad4b-9b87-4b80-99e2-4a73f5715a87","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.10 Output $0.60","notes":"No cache-read price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3-32B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.14,"cached_input_per_m":null,"output_per_m":0.57,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-32B 131K $0.14 $0.57","notes":"Context shown as 131K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3 32B","maker":"Qwen","provider_model_id":null,"tier":"batch","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 32B $0.075 $0.30","notes":"Batch tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3 32B","maker":"Qwen","provider_model_id":null,"tier":"flex","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 32B $0.075 $0.30","notes":"Flex tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3-32B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-32B","tier":"flex","input_per_m":0.064,"cached_input_per_m":null,"output_per_m":0.224,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-32B","checked":"2026-11-14","quote":"Flex (0.8×) $0.064 $0.224","notes":"Flex service tier (0.8× standard)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3 32B","maker":"Qwen","provider_model_id":null,"tier":"priority","input_per_m":0.2625,"cached_input_per_m":null,"output_per_m":1.05,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 32B $0.2625 $1.05","notes":"Priority tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-32b","name":"Qwen3-32B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-32B","tier":"priority","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.42,"context":40960,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-32B","checked":"2026-11-14","quote":"Priority (1.5×) $0.12 $0.42","notes":"Priority service tier (1.5× standard)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-8b","name":"Qwen3-8B","maker":"Qwen","provider_model_id":"Qwen/Qwen3-8B","tier":"standard","input_per_m":0.117,"cached_input_per_m":null,"output_per_m":0.455,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-8B","checked":"2026-11-15","quote":"PRICING: INPUT $0.117 / OUTPUT $0.455","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-8b","name":"Qwen3-8B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.06,"cached_input_per_m":null,"output_per_m":0.06,"context":131072,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-8B 131K $0.06 $0.06","notes":"Context shown as 131K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen3-Coder-480B-A35B-Instruct-Turbo","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.1,"output_per_m":1,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","checked":"2026-11-14","quote":"$0.30 in $1.00 out $0.10 cached / 1M tokens","notes":"DeepInfra Turbo variant (quantized)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen3-Coder-480B-A35B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","tier":"standard","input_per_m":0.38,"cached_input_per_m":0.076,"output_per_m":1.55,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-Coder-480B-A35B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.38 / CACHED $0.076 / OUTPUT $1.55","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","tier":"standard","input_per_m":0.9,"cached_input_per_m":0.18,"output_per_m":4.5,"context":262128,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen-qwen3-coder-480b-a35b-instruct-fp8/1fd8ead2-d150-4101-bc14-e46cd81d4a1e","checked":"2026-11-15","quote":"Price ≤ 32k token Input $0.90 Output $4.50 Cache Read $0.18 Cache Write - 32k - 128k token Input $1.62 Output $8.10 > 128k token Input $2.70 Output $13.50","notes":"Long-prompt tier: prompts over 32,000 tokens cost 1.62 in / 8.1 out."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen3 Coder 480B A35B","maker":"Qwen","provider_model_id":"qwen3-coder-480b-a35b-instruct","tier":"standard","input_per_m":0.22,"cached_input_per_m":0.022,"output_per_m":1.8,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Qwen3-Coder-480B-A35B-Instruct Input $0.22 … Output $1.80 … Cache Hit $0.022","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen3-Coder-480B-A35B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-Coder-480B-A35B 262K $0.25 $nan $1.0","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen 3 Coder 480B Turbo","maker":"Qwen","provider_model_id":"qwen3-coder-480b-a35b-instruct-turbo","tier":"standard","input_per_m":0.35,"cached_input_per_m":0.04,"output_per_m":1.5,"context":256000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3 Coder 480B Turbo | `qwen3-coder-480b-a35b-instruct-turbo` | $0.35 | $1.50 | $0.04 | — | Private |","notes":""},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen3 Coder 480B A35B","maker":"Qwen","provider_model_id":"qwen3-coder-480b-a35b-instruct","tier":"batch","input_per_m":0.11,"cached_input_per_m":null,"output_per_m":0.9,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Qwen3-Coder-480B-A35B-Instruct Batch Input $0.11 … Batch Output $0.90","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-coder","name":"Qwen3-Coder-480B-A35B-Instruct-Turbo","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","tier":"flex","input_per_m":0.24,"cached_input_per_m":0.08,"output_per_m":0.8,"context":262144,"precision":"fp4","source_url":"https://deepinfra.com/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","checked":"2026-11-14","quote":"Flex (0.8×) $0.24 $0.80 $0.08","notes":"Flex service tier (0.8× standard). DeepInfra Turbo variant (quantized)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 Coder 30B A3B $0.15 $0.60","notes":"Standard tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder-30B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","tier":"standard","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":0.45,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-Coder-30B-A3B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.125 / OUTPUT $0.45","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder-30B-A3B-Instruct","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.07,"cached_input_per_m":null,"output_per_m":0.28,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-Coder-30B-A3B-Instruct 262K $0.07 $0.28","notes":"Context shown as 262K."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B","maker":"Qwen","provider_model_id":null,"tier":"batch","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 Coder 30B A3B $0.075 $0.30","notes":"Batch tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B","maker":"Qwen","provider_model_id":null,"tier":"flex","input_per_m":0.075,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 Coder 30B A3B $0.075 $0.30","notes":"Flex tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B","maker":"Qwen","provider_model_id":null,"tier":"priority","input_per_m":0.2625,"cached_input_per_m":null,"output_per_m":1.05,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 Coder 30B A3B $0.2625 $1.05","notes":"Priority tier pricing table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3-coder-flash","name":"Qwen3 Coder Flash","maker":"Qwen","provider_model_id":"qwen3-coder-flash","tier":"standard","input_per_m":0.3,"cached_input_per_m":0.06,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3-coder-flash Currently equivalent to qwen3-coder-flash-2025-07-28 International 0<Token≤32K $0.3 $1.5","notes":"International (Singapore) deployment. Prompts up to 32K tokens; 32K–128K: 0.5 input, 2.5 output; 128K–256K: 0.8 input, 4 output; 256K–1M: 1.6 input, 9.6 output. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-coder-next","name":"Qwen3 Coder Next","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 Coder Next $ 0.50 $ 1.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-coder-next","name":"Qwen3-Coder-Next","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Coder-Next","tier":"standard","input_per_m":0.16,"cached_input_per_m":0.036,"output_per_m":1.15,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-Coder-Next","checked":"2026-11-15","quote":"PRICING: INPUT $0.16 / CACHED $0.036 / OUTPUT $1.15","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3-coder-next","name":"Qwen3-Coder-Next","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.12,"cached_input_per_m":0.07,"output_per_m":0.8,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3-Coder-Next $0.12 $0.80 $0.07","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b","name":"Qwen 3 Next 80b","maker":"Qwen","provider_model_id":"qwen3-next-80b","tier":"standard","input_per_m":0.35,"cached_input_per_m":null,"output_per_m":1.9,"context":256000,"precision":"fp16","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3 Next 80b | `qwen3-next-80b` | $0.35 | $1.90 | — | — | Private |","notes":"Venice does not say whether this is the Instruct or Thinking variant."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 Next 80B A3B $ 0.15 $ 1.20","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\"."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","tier":"standard","input_per_m":0.09,"cached_input_per_m":null,"output_per_m":1.1,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-Next-80B-A3B-Instruct","checked":"2026-11-14","quote":"$0.09 in $1.10 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","tier":"standard","input_per_m":0.125,"cached_input_per_m":null,"output_per_m":1.15,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-Next-80B-A3B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.125 / OUTPUT $1.15","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","maker":"Qwen","provider_model_id":"qwen3-next-80b-a3b-instruct","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Qwen3-Next-80B-Instruct Input $0.15 … Output $1.20","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.07,"output_per_m":1.1,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3-Next 80B $0.10 $1.10 $0.07","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","tier":"flex","input_per_m":0.072,"cached_input_per_m":null,"output_per_m":0.88,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-Next-80B-A3B-Instruct","checked":"2026-11-14","quote":"Flex (0.8×) $0.072 $0.88","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Next-80B-A3B-Instruct","tier":"priority","input_per_m":0.135,"cached_input_per_m":null,"output_per_m":1.65,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-Next-80B-A3B-Instruct","checked":"2026-11-14","quote":"Priority (1.5×) $0.135 $1.65","notes":"Priority service tier (1.5× standard)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","maker":"Qwen","provider_model_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":1.5,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-next-80b-a3b-thinking/8b9dceb5-a0cb-498f-9d2f-bab1f2451972","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.15 Output $1.50","notes":"No cache-read price published."},{"provider":"google-vertex","provider_name":"Google Cloud Vertex AI","provider_kind":"host","maker_api":false,"model":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","maker":"Qwen","provider_model_id":"qwen3-next-80b-a3b-thinking","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":1.2,"context":null,"precision":null,"source_url":"https://cloud.google.com/model-garden/partner-models/pricing","checked":"2026-11-14","quote":"Qwen3-Next-80B-Thinking Input $0.15 … Output $1.20","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3-omni-flash","name":"Qwen3 Omni Flash","maker":"Qwen","provider_model_id":"qwen3-omni-flash","tier":"standard","input_per_m":0.43,"cached_input_per_m":null,"output_per_m":1.66,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3-omni-flash International Non-Thinking and Thinking modes $0.43 $3.81 $0.78 $1.66 $3.06 $15.11","notes":"International (Singapore) deployment. Omni-modal model. Text input 0.43 (audio 3.81, image/video 0.78); text output 1.66 for text-only input, 3.06 for multimodal input; text plus audio output bills audio only, at 15.11."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3-vl-235b-a22b","name":"Qwen3 VL 235B","maker":"Qwen","provider_model_id":"qwen3-vl-235b-a22b","tier":"standard","input_per_m":0.21,"cached_input_per_m":0.1,"output_per_m":1.9,"context":128000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen3 VL 235B | `qwen3-vl-235b-a22b` | $0.21 | $1.90 | $0.10 | — | Private |","notes":"Venice does not say whether this is the Instruct or Thinking variant."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.53,"cached_input_per_m":null,"output_per_m":2.66,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Qwen3 VL 235B A22B $ 0.53 $ 2.66","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\". Listed as \"Qwen3 VL 235B A22B\"; mapped to the Instruct variant."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL-235B-A22B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.11,"output_per_m":0.88,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-VL-235B-A22B-Instruct","checked":"2026-11-14","quote":"$0.20 in $0.88 out $0.11 cached / 1M tokens","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL 235B-A22B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.21,"cached_input_per_m":0.1,"output_per_m":1.9,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3-VL 235B-A22B $0.21 $1.90 $0.10","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL-235B-A22B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","tier":"flex","input_per_m":0.16,"cached_input_per_m":0.088,"output_per_m":0.704,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-VL-235B-A22B-Instruct","checked":"2026-11-14","quote":"Flex (0.8×) $0.16 $0.704 $0.088","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL-235B-A22B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-235B-A22B-Instruct","tier":"priority","input_per_m":0.3,"cached_input_per_m":0.165,"output_per_m":1.32,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-VL-235B-A22B-Instruct","checked":"2026-11-14","quote":"Priority (1.5×) $0.30 $1.32 $0.165","notes":"Priority service tier (1.5× standard)."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b","name":"Qwen3 VL 30B A3B","maker":"Qwen","provider_model_id":"e2ee-qwen3-vl-30b-a3b-p","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":0.9,"context":128000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen3 VL 30B A3B | `e2ee-qwen3-vl-30b-a3b-p` | $0.25 | $0.90 | — | — | E2EE |","notes":"End-to-end encrypted (E2EE) tier, runs in a TEE. Venice does not say whether this is the Instruct or Thinking variant."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL-30B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.6,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-VL-30B-A3B-Instruct","checked":"2026-11-14","quote":"$0.15 in $0.60 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL-30B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.5,"context":131072,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3-VL-30B-A3B-Instruct","checked":"2026-11-15","quote":"PRICING: INPUT $0.15 / OUTPUT $0.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","maker":"Qwen","provider_model_id":"qwen/qwen3-vl-30b-a3b-instruct","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.7,"context":131072,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3 VL 30B A3B Instruct 128K $0.2 /Mt $0.7 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL-30B-A3B-Instruct","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.29,"cached_input_per_m":null,"output_per_m":1,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-VL-30B-A3B-Instruct 262K $0.29 $1.0","notes":"Context shown as 262K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL-30B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","tier":"flex","input_per_m":0.12,"cached_input_per_m":null,"output_per_m":0.48,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-VL-30B-A3B-Instruct","checked":"2026-11-14","quote":"Flex (0.8×) $0.12 $0.48","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-instruct","name":"Qwen3-VL-30B-A3B-Instruct","maker":"Qwen","provider_model_id":"Qwen/Qwen3-VL-30B-A3B-Instruct","tier":"priority","input_per_m":0.225,"cached_input_per_m":null,"output_per_m":0.9,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3-VL-30B-A3B-Instruct","checked":"2026-11-14","quote":"Priority (1.5×) $0.225 $0.90","notes":"Priority service tier (1.5× standard)."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-vl-30b-a3b-thinking","name":"Qwen3-VL-30B-A3B-Thinking","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.29,"cached_input_per_m":null,"output_per_m":1,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-VL-30B-A3B-Thinking 262K $0.29 $1.0","notes":"Context shown as 262K."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-vl-32b-instruct","name":"Qwen3-VL-32B-Instruct","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.6,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-VL-32B-Instruct 262K $0.2 $0.6","notes":"Context shown as 262K."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-vl-32b-thinking","name":"Qwen3-VL-32B-Thinking","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":1.5,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-VL-32B-Thinking 262K $0.2 $1.5","notes":"Context shown as 262K."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3-vl-8b-instruct","name":"Qwen3-VL 8B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":0.12,"output_per_m":0.75,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3-VL 8B $0.25 $0.75 $0.12","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3-vl-8b-instruct","name":"Qwen3-VL-8B-Instruct","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.18,"cached_input_per_m":null,"output_per_m":0.68,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3-VL-8B-Instruct 262K $0.18 $0.68","notes":"Context shown as 262K."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3-vl-plus","name":"Qwen3 VL Plus","maker":"Qwen","provider_model_id":"qwen3-vl-plus","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3-vl-plus context caching discount International Non-Thinking and Thinking modes 0<Token≤32K $0.2 $1.6","notes":"International (Singapore) deployment. Vision-language model. Prompts up to 32K tokens; 32K–128K: 0.3 input, 2.4 output; 128K–256K: 0.6 input, 4.8 output. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-122b-a10b","name":"Qwen3.5-122B-A10B","maker":"Qwen","provider_model_id":"qwen3.5-122b-a10b","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-122b-a10b International 0<Token≤256K $0.4 $3.2 $3.2","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-122B-A10B","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":3.2,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-5-122b-a10b/b0c97d0a-6272-499b-a12c-e860cbb66d6d","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.40 Output $3.20","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","maker":"Qwen","provider_model_id":"qwen/qwen3.5-122b-a10b","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":3.2,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.5 122B A10B 256K $0.4 /Mt $3.2 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.5-122b-a10b","name":"Qwen3.5-122B-A10B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.26,"cached_input_per_m":null,"output_per_m":2.08,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.5-122B-A10B 262K $0.26 $2.08","notes":"Context shown as 262K."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":"qwen3.5-27b","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-27b International 0<Token≤256K $0.3 $2.4 $2.4","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-27B-TEE","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":1.75,"context":262144,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Qwen3.5-27B Qwen/Qwen3.5-27B-TEE $0.02 per 1M tokens $0.20 per 1M tokens $1.75 per 1M tokens 262K","notes":"Runs on confidential TEE compute."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-27B","tier":"standard","input_per_m":0.26,"cached_input_per_m":null,"output_per_m":2.6,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-27B","checked":"2026-11-14","quote":"$0.26 in $2.60 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-27B","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":2.4,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.5-27B","checked":"2026-11-15","quote":"PRICING: INPUT $0.3 / OUTPUT $2.4","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5 27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-27B","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":2.4,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-5-27b/b5ca6de9-fc59-4bb7-a0b6-646e4ca2bc72","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.30 Output $2.40","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5 27B","maker":"Qwen","provider_model_id":"qwen/qwen3.5-27b","tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":2.4,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.5 27B 256K $0.3 /Mt $2.4 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":2,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.5-27B 262K $0.25 $2.0","notes":"Context shown as 262K."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-27B","tier":"flex","input_per_m":0.208,"cached_input_per_m":null,"output_per_m":2.08,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-27B","checked":"2026-11-14","quote":"Flex (0.8×) $0.208 $2.08","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-27b","name":"Qwen3.5-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-27B","tier":"priority","input_per_m":0.39,"cached_input_per_m":null,"output_per_m":3.9,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-27B","checked":"2026-11-14","quote":"Priority (1.5×) $0.39 $3.90","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","maker":"Qwen","provider_model_id":"qwen3.5-35b-a3b","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":2,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-35b-a3b International 0<Token≤256K $0.25 $2 $2","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-35B-A3B","tier":"standard","input_per_m":0.14,"cached_input_per_m":0.05,"output_per_m":1,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-35B-A3B","checked":"2026-11-14","quote":"$0.14 in $1.00 out $0.05 cached / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-35B-A3B","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":2,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-5-35b-a3b/dda5db69-e0a0-444d-88b5-862d79c85a0f","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.25 Output $2.00","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","maker":"Qwen","provider_model_id":"qwen/qwen3.5-35b-a3b","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":2,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.5 35B A3B 256K $0.25 /Mt $2 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.05,"output_per_m":1,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3.5 35B-A3B $0.15 $1.00 $0.05","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.24,"cached_input_per_m":0.15,"output_per_m":1.8,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.5-35B-A3B 262K $0.24 $0.15 $1.8","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen 3.5 35B A3B","maker":"Qwen","provider_model_id":"qwen3-5-35b-a3b","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.05,"output_per_m":1,"context":256000,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3.5 35B A3B | `qwen3-5-35b-a3b` | $0.15 | $1.00 | $0.05 | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-35B-A3B","tier":"flex","input_per_m":0.112,"cached_input_per_m":0.04,"output_per_m":0.8,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-35B-A3B","checked":"2026-11-14","quote":"Flex (0.8×) $0.112 $0.80 $0.04","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-35B-A3B","tier":"priority","input_per_m":0.21,"cached_input_per_m":0.075,"output_per_m":1.5,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-35B-A3B","checked":"2026-11-14","quote":"Priority (1.5×) $0.21 $1.50 $0.075","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","maker":"Qwen","provider_model_id":"qwen3.5-397b-a17b","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3.6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-397b-a17b International 0<Token≤256K $0.6 $3.6 $3.6","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen 3.5","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-397B-A17B-TEE","tier":"standard","input_per_m":0.45,"cached_input_per_m":0.045,"output_per_m":3,"context":262144,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Qwen 3.5 Qwen/Qwen3.5-397B-A17B-TEE $0.045 per 1M tokens $0.45 per 1M tokens $3.00 per 1M tokens 262K","notes":"Runs on confidential TEE compute."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-397B-A17B","tier":"standard","input_per_m":0.45,"cached_input_per_m":0.22,"output_per_m":3,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-397B-A17B","checked":"2026-11-14","quote":"$0.45 in $3.00 out $0.22 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-397B-A17B","tier":"standard","input_per_m":0.55,"cached_input_per_m":null,"output_per_m":3.5,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.5-397B-A17B","checked":"2026-11-15","quote":"PRICING: INPUT $0.55 / OUTPUT $3.5","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-397B-A17B","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3.6,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-5-397b-a17b/29ac1bb2-9c03-4a7c-9178-fb438d0e1814","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.60 Output $3.60","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","maker":"Qwen","provider_model_id":"qwen/qwen3.5-397b-a17b","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3.6,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.5 397B A17B 256K $0.6 /Mt $3.6 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":0.3,"output_per_m":3.6,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3.5 397B-A17B $0.50 $3.60 $0.30","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-397B-A17B","tier":"flex","input_per_m":0.36,"cached_input_per_m":0.176,"output_per_m":2.4,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-397B-A17B","checked":"2026-11-14","quote":"Flex (0.8×) $0.36 $2.40 $0.176","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-397B-A17B","tier":"priority","input_per_m":0.675,"cached_input_per_m":0.33,"output_per_m":4.5,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.5-397B-A17B","checked":"2026-11-14","quote":"Priority (1.5×) $0.675 $4.50 $0.33","notes":"Priority service tier (1.5× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-9b","name":"Qwen3.5-9B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-9B","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.15,"context":262144,"precision":"bfloat16","source_url":"https://deepinfra.com/Qwen/Qwen3.5-9B","checked":"2026-11-14","quote":"$0.10 in $0.15 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.5-9b","name":"Qwen3.5-9B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-9B","tier":"standard","input_per_m":0.17,"cached_input_per_m":null,"output_per_m":0.25,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.5-9B","checked":"2026-11-15","quote":"PRICING: INPUT $0.17 / OUTPUT $0.25","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.5-9b","name":"Qwen3.5-9B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.15,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.5-9B 262K $0.1 $0.15","notes":"Context shown as 262K."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"qwen3.5-9b","name":"Qwen3.5 9B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.17,"cached_input_per_m":null,"output_per_m":0.25,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Qwen3.5 9B $0.17 $0.25","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-9b","name":"Qwen3.5-9B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-9B","tier":"flex","input_per_m":0.08,"cached_input_per_m":null,"output_per_m":0.12,"context":262144,"precision":"bfloat16","source_url":"https://deepinfra.com/Qwen/Qwen3.5-9B","checked":"2026-11-14","quote":"Flex (0.8×) $0.08 $0.12","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.5-9b","name":"Qwen3.5-9B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.5-9B","tier":"priority","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.225,"context":262144,"precision":"bfloat16","source_url":"https://deepinfra.com/Qwen/Qwen3.5-9B","checked":"2026-11-14","quote":"Priority (1.5×) $0.15 $0.225","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-flash-02-23","name":"Qwen3.5-Flash","maker":"Qwen","provider_model_id":"qwen3.5-flash-2026-02-23","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-flash-2026-02-23 International 0<Token≤1M $0.1 $0.4","notes":"International (Singapore) deployment. The qwen3.5-flash alias currently points to this snapshot (alias marked \"50% batch inference discount\"). Prompts up to 1M tokens. No cached price: the Context Cache page does not list this model for implicit cache in the International (Singapore) scope (checked 2026-11-15)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-omni-flash","name":"Qwen3.5 Omni Flash","maker":"Qwen","provider_model_id":"qwen3.5-omni-flash","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":2.2,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-omni-flash Currently equivalent to qwen3.5-omni-flash-2026-03-15 International $0.4 $3 $2.2 $11.9","notes":"International (Singapore) deployment. Omni-modal model. Text/image/video input 0.4 (audio input 3); text output 2.2 (text plus audio output bills audio only, at 11.9)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-omni-plus","name":"Qwen3.5 Omni Plus","maker":"Qwen","provider_model_id":"qwen3.5-omni-plus","tier":"standard","input_per_m":1.4,"cached_input_per_m":null,"output_per_m":8.3,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-omni-plus Currently equivalent to qwen3.5-omni-plus-2026-03-15 International $1.4 $11 $8.3 $44","notes":"International (Singapore) deployment. Omni-modal model. Text/image/video input 1.4 (audio input 11); text output 8.3 (text plus audio output bills audio only, at 44)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-plus-02-15","name":"Qwen3.5 Plus 2026-02-15","maker":"Qwen","provider_model_id":"qwen3.5-plus-2026-02-15","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-plus-2026-02-15 International 0<Token≤256K $0.4 $2.4 $2.4","notes":"International (Singapore) deployment. The qwen3.5-plus alias currently points to this snapshot. Prompts up to 256K tokens; 256K–1M token prompts: 0.5 input, 3 output. No cached price: the Context Cache page does not list this model for implicit cache in the International (Singapore) scope (checked 2026-11-15)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.5-plus-20260420","name":"Qwen3.5 Plus 2026-04-20","maker":"Qwen","provider_model_id":"qwen3.5-plus-2026-04-20","tier":"standard","input_per_m":0.4,"cached_input_per_m":null,"output_per_m":2.4,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.5-plus-2026-04-20 International 0<Token≤256K $0.4 $2.4 $2.4","notes":"International (Singapore) deployment. Prompts up to 256K tokens; 256K–1M token prompts: 0.5 input, 3 output. No cached price: the Context Cache page does not list this model for implicit cache in the International (Singapore) scope (checked 2026-11-15)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.6-27b","name":"Qwen3.6 27B","maker":"Qwen","provider_model_id":"qwen3.6-27b","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3.6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.6-27b International 0<Token≤256K $0.6 $3.6 $3.6","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-27B-TEE","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.025,"output_per_m":2,"context":262144,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Qwen3.6-27B Qwen/Qwen3.6-27B-TEE $0.025 per 1M tokens $0.25 per 1M tokens $2.00 per 1M tokens 262K","notes":"Runs on confidential TEE compute."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-27B","tier":"standard","input_per_m":0.32,"cached_input_per_m":null,"output_per_m":3.2,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.6-27B","checked":"2026-11-14","quote":"$0.32 in $3.20 out / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-27B","tier":"standard","input_per_m":0.32,"cached_input_per_m":0.064,"output_per_m":2.7,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.6-27B","checked":"2026-11-15","quote":"PRICING: INPUT $0.32 / CACHED $0.064 / OUTPUT $2.7","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6 27B","maker":"Qwen","provider_model_id":"qwen/qwen3.6-27b","tier":"standard","input_per_m":0.6,"cached_input_per_m":null,"output_per_m":3.6,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.6 27B 256K $0.6 /Mt $3.6 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6-27B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.3,"cached_input_per_m":null,"output_per_m":3.2,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.6-27B 262K $0.3 $3.2","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen 3.6 27B","maker":"Qwen","provider_model_id":"qwen3-6-27b","tier":"standard","input_per_m":0.325,"cached_input_per_m":null,"output_per_m":3.25,"context":256000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3.6 27B | `qwen3-6-27b` | $0.325 | $3.25 | — | — | Private |","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-27B","tier":"flex","input_per_m":0.256,"cached_input_per_m":null,"output_per_m":2.56,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.6-27B","checked":"2026-11-14","quote":"Flex (0.8×) $0.256 $2.56","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.6-27b","name":"Qwen3.6-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-27B","tier":"priority","input_per_m":0.48,"cached_input_per_m":null,"output_per_m":4.8,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.6-27B","checked":"2026-11-14","quote":"Priority (1.5×) $0.48 $4.80","notes":"Priority service tier (1.5× standard)."},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"QWEN3.6 35B A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.05,"output_per_m":0.9,"context":262144,"precision":null,"source_url":"https://akashml.com/models/qwen3.6-35b-a3b","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read QWEN3.6 35B A3B $0.10 $0.90 $0.05","notes":"Labelled \"Limited Trial\" on AkashML."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","maker":"Qwen","provider_model_id":"qwen3.6-35b-a3b","tier":"standard","input_per_m":0.375,"cached_input_per_m":null,"output_per_m":2.25,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.6-35b-a3b International 0<Token≤256K $0.375 $2.25 $2.25","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.035,"output_per_m":0.89,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Qwen3.6 35B A3B $0.10 $0.89 $0.035","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.1,"output_per_m":0.95,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.6-35B-A3B","checked":"2026-11-14","quote":"$0.10 in $0.95 out $0.10 cached / 1M tokens","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"standard","input_per_m":0.186,"cached_input_per_m":0.032,"output_per_m":1.1138,"context":32768,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.6-35B-A3B","checked":"2026-11-15","quote":"PRICING: INPUT $0.186 / CACHED $0.032 / OUTPUT $1.1138","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"standard","input_per_m":0.248,"cached_input_per_m":null,"output_per_m":1.485,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-6-35b-a3b/9deb2533-b297-4af8-825f-cbdd67130ee2","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.248 Output $1.485","notes":"No cache-read price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","maker":"Qwen","provider_model_id":"qwen/qwen3.6-35b-a3b","tier":"standard","input_per_m":0.248,"cached_input_per_m":null,"output_per_m":1.485,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.6 35B A3B 256K $0.248 /Mt $1.485 /Mt","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":0.05,"output_per_m":1,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Qwen3.6 35B-A3B $0.15 $1.00 $0.05","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.24,"cached_input_per_m":0.15,"output_per_m":1.8,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.6-35B-A3B 262K $0.24 $0.15 $1.8","notes":"Context shown as 262K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen 3.6 35B A3B","maker":"Qwen","provider_model_id":"qwen3-6-35b-a3b","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":1,"context":256000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3.6 35B A3B (Beta) | `qwen3-6-35b-a3b` | $0.10 | $1.00 | — | — | Private |","notes":"Beta model."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"flex","input_per_m":0.08,"cached_input_per_m":0.08,"output_per_m":0.76,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.6-35B-A3B","checked":"2026-11-14","quote":"Flex (0.8×) $0.08 $0.76 $0.08","notes":"Flex service tier (0.8× standard)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-35B-A3B","tier":"priority","input_per_m":0.15,"cached_input_per_m":0.15,"output_per_m":1.425,"context":262144,"precision":"fp8","source_url":"https://deepinfra.com/Qwen/Qwen3.6-35B-A3B","checked":"2026-11-14","quote":"Priority (1.5×) $0.15 $1.425 $0.15","notes":"Priority service tier (1.5× standard)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.6-flash","name":"Qwen3.6 Flash","maker":"Qwen","provider_model_id":"qwen3.6-flash","tier":"standard","input_per_m":0.25,"cached_input_per_m":null,"output_per_m":1.5,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.6-flash Currently equivalent to qwen3.6-flash-2026-04-16 50% batch inference discount context caching discount International 0<Token≤256K $0.25 $1.5","notes":"International (Singapore) deployment. Prompts up to 256K tokens; 256K–1M: 1 input, 4 output. The page marks this model \"50% batch inference discount\" (batch bills input and output at 50% of the real-time price); no separate batch price is listed. No cached price: the Context Cache page does not list this model for implicit cache in the International (Singapore) scope (checked 2026-11-15)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.6-plus","name":"Qwen3.6 Plus","maker":"Qwen","provider_model_id":"qwen3.6-plus","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":3,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.6-plus Currently equivalent to qwen3.6-plus-2026-04-02 International 0<Token≤256K $0.5 $3 $3","notes":"International (Singapore) deployment. Prompts up to 256K tokens (same output price in thinking and non-thinking mode); 256K–1M token prompts: 2 input, 6 output. No cached price: the Context Cache page does not list this model for implicit cache in the International (Singapore) scope (checked 2026-11-15)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.6-plus","name":"Qwen3.6 Plus","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-Plus","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":3,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-6-plus/c6ce4ef6-245b-4226-99e0-b6ead0530368","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.50 Output $3.00","notes":"No cache-read price published."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"qwen3.6-plus","name":"Qwen3.6-Plus","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":3,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Qwen3.6-Plus $0.50 $3.00","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.6-plus-2026-04-02","name":"Qwen3.6 Plus 2026-04-02","maker":"Qwen","provider_model_id":"Qwen/Qwen3.6-Plus-2026-04-02","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":3,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-6-plus-2026-04-02/8d9958e3-5f8d-48b2-a918-f077385757f6","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.50 Output $3.00","notes":"No cache-read price published."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.7-flash","name":"Qwen3.7 Flash","maker":"Qwen","provider_model_id":"qwen3.7-flash","tier":"standard","input_per_m":0.03,"cached_input_per_m":0.006,"output_per_m":0.13,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.7-flash Currently equivalent to qwen3.7-flash-2026-07-15 50% batch inference discount context caching discount International 0<Token≤32K $0.030 $0.130","notes":"International (Singapore) deployment. Prompts up to 32K tokens; 32K–256K: 0.1 input, 0.4 output; 256K–1M: 0.2 input, 0.8 output. The page marks this model \"50% batch inference discount\" (batch bills input and output at 50% of the real-time price); no separate batch price is listed. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.7-max","name":"Qwen3.7 Max","maker":"Qwen","provider_model_id":"qwen3.7-max","tier":"standard","input_per_m":2.5,"cached_input_per_m":0.5,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.7-max Currently equivalent to qwen3.7-max-2026-05-20 context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $2.5 $7.5","notes":"International (Singapore) deployment. Alias currently points to qwen3.7-max-2026-05-20; prompts up to 1M tokens. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.7-max","name":"Qwen3.7-Max","maker":"Qwen","provider_model_id":"Qwen/Qwen3.7-Max","tier":"standard","input_per_m":2.5,"cached_input_per_m":0.5,"output_per_m":7.5,"context":256000,"precision":null,"source_url":"https://deepinfra.com/Qwen/Qwen3.7-Max","checked":"2026-11-14","quote":"$2.50 in $7.50 out $0.50 cached / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.7-max","name":"Qwen3.7 Max","maker":"Qwen","provider_model_id":"Qwen/Qwen3.7-Max","tier":"standard","input_per_m":2.5,"cached_input_per_m":0.25,"output_per_m":7.5,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-7-max/a1f45766-f68a-446d-8bff-513173e8044f","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $2.50 Output $7.50 Cache Read $0.25 Cache Write $3.125","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.7-max","name":"Qwen3.7 Max","maker":"Qwen","provider_model_id":"qwen/qwen3.7-max","tier":"standard","input_per_m":1.25,"cached_input_per_m":0.25,"output_per_m":3.75,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.7 Max 977K $1.25 /Mt · Cache Read $0.25 /Mt $3.75 /Mt","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"qwen3.7-max","name":"Qwen3.7-Max","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":2.5,"cached_input_per_m":0.5,"output_per_m":7.5,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Qwen3.7-Max $2.50 $0.50 (cached) $7.50","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.7-plus","name":"Qwen3.7 Plus","maker":"Qwen","provider_model_id":"qwen3.7-plus","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.08,"output_per_m":1.6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.7-plus Currently equivalent to qwen3.7-plus-2026-05-26 context caching discount International 0<Token≤256K List price $0.4 (Limited-time 20% off) List price $1.6 (Limited-time 20% off)","notes":"International (Singapore) deployment. List price for prompts up to 256K tokens (same output price in thinking and non-thinking mode); the page shows a limited-time 20% discount off this list price. 256K–1M token prompts: 1.2 input, 4.8 output. Alias currently points to qwen3.7-plus-2026-05-26. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"qwen3.7-plus","name":"Qwen3.7-Plus","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.32,"cached_input_per_m":null,"output_per_m":1.28,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Qwen3.7-Plus $0.32 $1.28","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","maker":"Qwen","provider_model_id":"qwen3.8-2.4t-a95b","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.8-2.4t-a95b context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $2 $6","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 1M tokens. Cached price not listed (Context Cache page: see the Model Studio console)."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"qwen3.8-2.4t-a95b","name":"Qwen3.8-2.4T-A95B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-2.4T-A95B","tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":1000000,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Qwen3.8-2.4T-A95B Qwen/Qwen3.8-2.4T-A95B $0.25 per 1M tokens $2.00 per 1M tokens $6.00 per 1M tokens 1.0M","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.8-2.4t-a95b","name":"Qwen3.8-2.4T-A95B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-2.4T-A95B","tier":"standard","input_per_m":1,"cached_input_per_m":null,"output_per_m":4,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.8-2.4T-A95B","checked":"2026-11-15","quote":"PRICING: INPUT $1 / OUTPUT $4","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","maker":"Qwen","provider_model_id":"qwen/qwen3.8-2.4t-a95b","tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.8 2.4T A95B 977K $2 /Mt · Cache Read $0.25 /Mt $6 /Mt","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"qwen3.8-2.4t-a95b","name":"Qwen3.8-2.4T-A95B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":1048576,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Qwen3.8-2.4T-A95B 1049K $2.0 $0.25 $6.0","notes":"Context shown as 1049K."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3.8-2.4t-a95b","name":"Qwen 3.8 2.4T","maker":"Qwen","provider_model_id":"qwen-3-8-2-4t-a95b","tier":"standard","input_per_m":2.5,"cached_input_per_m":0.3125,"output_per_m":7.5,"context":262144,"precision":null,"source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3.8 2.4T | `qwen-3-8-2-4t-a95b` | $2.50 | $7.50 | $0.3125 | — | Private |","notes":""},{"provider":"akashml","provider_name":"AkashML","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"QWEN3.8 27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"standard","input_per_m":0.225,"cached_input_per_m":0.05,"output_per_m":1.98,"context":262144,"precision":null,"source_url":"https://akashml.com/models/qwen3.8-27b","checked":"2026-11-15","quote":"Price (per 1M Tokens) Input Output Cache Read QWEN3.8 27B $0.225 $1.98 $0.05","notes":"Labelled \"Limited Trial\" on AkashML."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"qwen3.8-27b","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":3,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.8-27b context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $0.5 $3","notes":"International (Singapore) deployment. Open-weight model. Prompts up to 1M tokens. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 20% of the input price in the International (Singapore) scope."},{"provider":"cerebras","provider_name":"Cerebras","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen 3.8 27B","maker":"Qwen","provider_model_id":"qwen-3.8-27b","tier":"standard","input_per_m":0.99,"cached_input_per_m":0.99,"output_per_m":1.49,"context":131072,"precision":null,"source_url":"https://www.cerebras.ai/pricing","checked":"2026-11-14","quote":"Qwen 3.8 27B ~1,850 tokens/s $0.99/M tokens $1.49/M tokens","notes":"Developer (pay-as-you-go) tier. Cached input billed at the standard input rate. Paid context 131,072 tokens (inference-docs.cerebras.ai/models/qwen-3.8-27b)."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B-TEE","tier":"standard","input_per_m":0.039,"cached_input_per_m":0.0039,"output_per_m":1.25,"context":262144,"precision":"fp8","source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Qwen3.8-27B Qwen/Qwen3.8-27B-TEE $0.0039 per 1M tokens $0.039 per 1M tokens $1.25 per 1M tokens 262K","notes":"Runs on confidential TEE compute."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"@cf/qwen/qwen3.8-27b","tier":"standard","input_per_m":0.45,"cached_input_per_m":null,"output_per_m":3.2,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/qwen/qwen3.8-27b $0.450 per M input tokens $3.200 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"coreweave","provider_name":"CoreWeave Forge (formerly W&B Inference)","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.15,"output_per_m":3,"context":262144,"precision":null,"source_url":"https://coreweave.com/forge-pricing/inference-agents","checked":"2026-11-15","quote":"Qwen3.8 27B $0.40 $3.00 $0.15","notes":""},{"provider":"crusoe","provider_name":"Crusoe Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"qwen/Qwen3.8-27B","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.15,"output_per_m":2,"context":262144,"precision":null,"source_url":"https://www.crusoe.ai/cloud/pricing","checked":"2026-11-15","quote":"Qwen3.8 27B text, image $0.25 $2.00 $0.15","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.0375,"output_per_m":1.875,"context":262144,"precision":null,"source_url":"https://deepinfra.com/Qwen/Qwen3.8-27B","checked":"2026-11-14","quote":"$0.15 in $1.875 out $0.038 cached / 1M tokens","notes":"Promotional price, 25% off list (list 0.2 in / 2.5 out)."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"standard","input_per_m":0.4,"cached_input_per_m":0.15,"output_per_m":3,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/Qwen/Qwen3.8-27B","checked":"2026-11-15","quote":"PRICING: INPUT $0.4 / CACHED $0.15 / OUTPUT $3","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"standard","input_per_m":0.45,"cached_input_per_m":0.25,"output_per_m":3.2,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-8-27b/ed878143-66b2-4dbb-a2ee-c05667f8312a","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.45 Output $3.20 Cache Read $0.25 Cache Write -","notes":""},{"provider":"groq","provider_name":"Groq","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":"qwen/qwen3.8-27b","tier":"standard","input_per_m":0.8,"cached_input_per_m":null,"output_per_m":4,"context":131072,"precision":null,"source_url":"https://console.groq.com/docs/models","checked":"2026-11-14","quote":"qwen/qwen3.8-27b | 450 | $0.80 input$4.00 output | 250K TPM1K RPM | 131,072","notes":"Preview model (evaluation use only per Groq)."},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"qwen3.8-27b","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":2,"context":196000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"Qwen3.8 27B qwen3.8-27b Alibaba · 196K context · Text $0.20 $2.00 $0.02","notes":"Context shown on page as \"196K\" (rounded); stored as the decimal value."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8 27B","maker":"Qwen","provider_model_id":"qwen/qwen3.8-27b","tier":"standard","input_per_m":0.42,"cached_input_per_m":0.085,"output_per_m":3,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.8 27B 977K $0.42 /Mt · Cache Read $0.085 /Mt $3 /Mt","notes":""},{"provider":"nscale","provider_name":"Nscale","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://docs.nscale.com/docs/ai-services/models","checked":"2026-11-15","quote":"| Qwen3.8-27B | Qwen | $0.20 | $2.50 |","notes":""},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen 3.8 27B","maker":"Qwen","provider_model_id":"qwen-3-8-27b","tier":"standard","input_per_m":0.45,"cached_input_per_m":null,"output_per_m":3.2,"context":262144,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Qwen 3.8 27B (Beta) | `qwen-3-8-27b` | $0.45 | $3.20 | — | — | Private |","notes":"Beta model."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"flex","input_per_m":0.12,"cached_input_per_m":0.03,"output_per_m":1.5,"context":262144,"precision":null,"source_url":"https://deepinfra.com/Qwen/Qwen3.8-27B","checked":"2026-11-14","quote":"Flex (0.8×) $0.12 $1.50 $0.03","notes":"Flex service tier (0.8× standard). Promotional price, 25% off list (list 0.2 in / 2.5 out)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.8-27b","name":"Qwen3.8-27B","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-27B","tier":"priority","input_per_m":0.225,"cached_input_per_m":0.0563,"output_per_m":2.8125,"context":262144,"precision":null,"source_url":"https://deepinfra.com/Qwen/Qwen3.8-27B","checked":"2026-11-14","quote":"Priority (1.5×) $0.225 $2.8125 $0.0563","notes":"Priority service tier (1.5× standard). Promotional price, 25% off list (list 0.2 in / 2.5 out)."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.8-flash","name":"Qwen3.8 Flash","maker":"Qwen","provider_model_id":"qwen3.8-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.47,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.8-flash context caching discount International 0<Token≤1M $0.15 $0.47","notes":"International (Singapore) deployment. Prompts up to 1M tokens. Cached price not listed (Context Cache page: varies by region)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.8-flash","name":"Qwen3.8-Flash","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-Flash","tier":"standard","input_per_m":0.113,"cached_input_per_m":0.0141,"output_per_m":0.382,"context":1000000,"precision":null,"source_url":"https://deepinfra.com/Qwen/Qwen3.8-Flash","checked":"2026-11-14","quote":"$0.113 in $0.382 out $0.014 cached / 1M tokens","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.8-flash","name":"Qwen3.8 Flash","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-Flash","tier":"standard","input_per_m":0.16,"cached_input_per_m":0.016,"output_per_m":0.47,"context":1048575,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/qwen3-8-flash/e7cd2464-04a4-4b85-bfbb-8caedcdca20c","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.16 Output $0.47 Cache Read $0.016 Cache Write $0.20","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-flash","name":"Qwen3.8 Flash","maker":"Qwen","provider_model_id":"qwen/qwen3.8-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.016,"output_per_m":0.47,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.8 Flash 977K $0.15 /Mt · Cache Read $0.016 /Mt · Cache Write(5m) $0.2 /Mt $0.47 /Mt","notes":"Cache write (5m) 0.2 per 1M."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-flash","name":"Qwen3.8 Flash","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.47,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Qwen3.8 Flash $0.15 $0.47","notes":""},{"provider":"nscale","provider_name":"Nscale","provider_kind":"host","maker_api":false,"model":"qwen3.8-flash-next","name":"Qwen3.8-Flash-Next-FP8","maker":"Qwen","provider_model_id":"Qwen3.8-Flash-Next-FP8","tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.47,"context":null,"precision":"fp8","source_url":"https://docs.nscale.com/docs/ai-services/models","checked":"2026-11-15","quote":"| Qwen3.8-Flash-Next-FP8 | Qwen | $0.15 | $0.47 |","notes":"Retired from serverless on 11 December 2026 per Nscale."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.8-max","name":"Qwen3.8 Max","maker":"Qwen","provider_model_id":"qwen3.8-max","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.8-max context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $2 $6","notes":"International (Singapore) deployment. Prompts up to 1M tokens. Cached price not listed (Context Cache page: see the Model Studio console)."},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"qwen3.8-max","name":"Qwen3.8-Max","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-Max","tier":"standard","input_per_m":1.65,"cached_input_per_m":0.206,"output_per_m":4.951,"context":256000,"precision":null,"source_url":"https://deepinfra.com/Qwen/Qwen3.8-Max","checked":"2026-11-14","quote":"$1.65 in $4.951 out $0.206 cached / 1M tokens","notes":""},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"qwen3.8-max","name":"Qwen3.8-Max","maker":"Qwen","provider_model_id":null,"tier":"standard","input_per_m":2,"cached_input_per_m":0.2,"output_per_m":6,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Qwen3.8-Max — Processing modePrompt lengthInputOutputCache read: Standard All prompts$2.00$6.00$0.20","notes":"DigitalOcean-hosted."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-max","name":"Qwen 3.8 Max","maker":"Qwen","provider_model_id":"accounts/fireworks/models/qwen3p8-max","tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":null,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Qwen 3.8 Max | $2.00 / $0.25 / $6.00 | $3.00 / $0.375 / $9.00","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.8-max","name":"Qwen3.8 Max","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-Max","tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-8-max/8881dcb5-e26b-473c-aa5e-9f43054eecb9","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $2.00 Output $6.00 Cache Read $0.25 Cache Write $2.50","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-max","name":"Qwen3.8 Max","maker":"Qwen","provider_model_id":"qwen/qwen3.8-max","tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Qwen3.8 Max 977K $2 /Mt · Cache Read $0.25 /Mt · Cache Write(5m) $2.5 /Mt $6 /Mt","notes":"Cache write (5m) 2.5 per 1M."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"qwen3.8-max","name":"Qwen 3.8 Max","maker":"Qwen","provider_model_id":"accounts/fireworks/models/qwen3p8-max","tier":"priority","input_per_m":3,"cached_input_per_m":0.375,"output_per_m":9,"context":null,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Qwen 3.8 Max | Priority $3.00 / $0.375 / $9.00","notes":"Priority mode."},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.8-max-0902","name":"Qwen3.8 Max (0902)","maker":"Qwen","provider_model_id":"qwen3.8-max-0902","tier":"standard","input_per_m":2,"cached_input_per_m":null,"output_per_m":6,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.8-max-0902 context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $2 $6","notes":"International (Singapore) deployment. Prompts up to 1M tokens. Cached price not listed (Context Cache page: see the Model Studio console)."},{"provider":"chutes","provider_name":"Chutes","provider_kind":"host","maker_api":false,"model":"qwen3.8-max-0902","name":"Qwen3.8-Max-0902","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-Max-0902","tier":"standard","input_per_m":2,"cached_input_per_m":0.25,"output_per_m":6,"context":1000000,"precision":null,"source_url":"https://chutes.ai/pricing","checked":"2026-11-15","quote":"Qwen3.8-Max-0902 Qwen/Qwen3.8-Max-0902 $0.25 per 1M tokens $2.00 per 1M tokens $6.00 per 1M tokens 1.0M","notes":""},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"qwen3.8-max-0902","name":"Qwen3.8 Max 0902","maker":"Qwen","provider_model_id":"Qwen/Qwen3.8-Max-0902","tier":"standard","input_per_m":1.65,"cached_input_per_m":0.206,"output_per_m":4.951,"context":262144,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/qwen3-8-max-0902/b2d7b50b-eafe-4174-bbbf-9ea95f248bf8","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.65 Output $4.951 Cache Read $0.206 Cache Write $2.063","notes":""},{"provider":"alibaba","provider_name":"Alibaba Cloud Model Studio","provider_kind":"maker","maker_api":true,"model":"qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","maker":"Qwen","provider_model_id":"qwen3.8-omni-flash","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.016,"output_per_m":0.47,"context":null,"precision":null,"source_url":"https://www.alibabacloud.com/help/en/model-studio/model-pricing","checked":"2026-11-14","quote":"qwen3.8-omni-flash International $0.15 $0.016 $0.47","notes":"International (Singapore) deployment. Omni-modal model; text token prices."},{"provider":"cloudflare","provider_name":"Cloudflare Workers AI","provider_kind":"host","maker_api":false,"model":"qwq-32b","name":"QwQ 32B","maker":"Qwen","provider_model_id":"@cf/qwen/qwq-32b","tier":"standard","input_per_m":0.66,"cached_input_per_m":null,"output_per_m":1,"context":null,"precision":null,"source_url":"https://developers.cloudflare.com/workers-ai/platform/pricing/","checked":"2026-11-14","quote":"@cf/qwen/qwq-32b $0.660 per M input tokens $1.000 per M output tokens","notes":"Cloudflare publishes this USD per-token price alongside the neuron price."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"ripple-65b-preview","name":"ricursiveAI/Ripple-65B-Preview","maker":"Ricursive AI","provider_model_id":"gmicloud/Ripple-65B-Preview","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.05,"output_per_m":0.6,"context":1000000,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/ricursiveai-ripple-65b-preview/abfc023e-35b7-4e9e-bb97-cef5db95f171","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.20 Output $0.60 Cache Read $0.05 Cache Write -","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"ripple-65b-preview","name":"Ripple-65B Preview","maker":"Ricursive AI","provider_model_id":null,"tier":"standard","input_per_m":0.2,"cached_input_per_m":0.02,"output_per_m":0.6,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Ripple-65B Preview $0.20 $0.02 (cached) $0.60","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"rnj-1-instruct","name":"Rnj-1 Instruct","maker":"Essential AI","provider_model_id":null,"tier":"standard","input_per_m":0.15,"cached_input_per_m":null,"output_per_m":0.15,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Rnj-1 Instruct $0.15 $0.15","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"seed-1.8","name":"Seed-1.8","maker":"ByteDance Seed","provider_model_id":"ByteDance/Seed-1.8","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.05,"output_per_m":2,"context":256000,"precision":null,"source_url":"https://deepinfra.com/ByteDance/Seed-1.8","checked":"2026-11-14","quote":"$0.25 in $2.00 out $0.05 cached / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"seed-2.0-code","name":"Seed-2.0-code","maker":"ByteDance Seed","provider_model_id":"ByteDance/Seed-2.0-code","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":3,"context":256000,"precision":null,"source_url":"https://deepinfra.com/ByteDance/Seed-2.0-code","checked":"2026-11-14","quote":"$0.50 in $3.00 out $0.10 cached / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"seed-2.0-mini","name":"Seed-2.0-mini","maker":"ByteDance Seed","provider_model_id":"ByteDance/Seed-2.0-mini","tier":"standard","input_per_m":0.1,"cached_input_per_m":0.02,"output_per_m":0.4,"context":256000,"precision":null,"source_url":"https://deepinfra.com/ByteDance/Seed-2.0-mini","checked":"2026-11-14","quote":"$0.10 in $0.40 out $0.02 cached / 1M tokens","notes":""},{"provider":"deepinfra","provider_name":"DeepInfra","provider_kind":"host","maker_api":false,"model":"seed-2.0-pro","name":"Seed-2.0-pro","maker":"ByteDance Seed","provider_model_id":"ByteDance/Seed-2.0-pro","tier":"standard","input_per_m":0.5,"cached_input_per_m":0.1,"output_per_m":3,"context":256000,"precision":null,"source_url":"https://deepinfra.com/ByteDance/Seed-2.0-pro","checked":"2026-11-14","quote":"$0.50 in $3.00 out $0.10 cached / 1M tokens","notes":""},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"seed-oss-36b-instruct","name":"Seed-OSS-36B-Instruct","maker":"ByteDance Seed","provider_model_id":null,"tier":"standard","input_per_m":0.21,"cached_input_per_m":null,"output_per_m":0.57,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Seed-OSS-36B-Instruct 262K $0.21 $0.57","notes":"Context shown as 262K."},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"skyfall-31b-v4.2","name":"Skyfall 31B v4.2","maker":"TheDrummer","provider_model_id":null,"tier":"standard","input_per_m":0.55,"cached_input_per_m":0.25,"output_per_m":0.8,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Skyfall 31B v4.2 $0.55 $0.80 $0.25","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"skyfall-36b-v2","name":"Skyfall 36B v2 (FP8)","maker":"TheDrummer","provider_model_id":null,"tier":"standard","input_per_m":0.55,"cached_input_per_m":0.25,"output_per_m":0.8,"context":null,"precision":"fp8","source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Skyfall 36B v2 (FP8) $0.55 $0.80 $0.25","notes":""},{"provider":"perplexity","provider_name":"Perplexity","provider_kind":"maker","maker_api":true,"model":"sonar","name":"Sonar","maker":"Perplexity","provider_model_id":"perplexity/sonar","tier":"standard","input_per_m":0.25,"cached_input_per_m":0.0625,"output_per_m":2.5,"context":null,"precision":null,"source_url":"https://docs.perplexity.ai/docs/agent-api/models","checked":"2026-11-15","quote":"`perplexity/sonar` | 0.25 | 2.50 | 0.0625","notes":"Agent API token rates; tool calls (web_search USD 0.0025 per invocation etc.) are billed separately per the pricing page."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"step-3.5-flash","name":"Step-3.5-Flash","maker":"StepFun","provider_model_id":"stepfun-ai/Step-3.5-Flash","tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/stepfun-ai/Step-3.5-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.1 / OUTPUT $0.3","notes":"Developer plan (per-token billing, from 50 USD a month in credits). No cached price published."},{"provider":"siliconflow","provider_name":"SiliconFlow","provider_kind":"host","maker_api":false,"model":"step-3.5-flash","name":"Step-3.5-Flash","maker":"StepFun","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":262144,"precision":null,"source_url":"https://www.siliconflow.com/pricing","checked":"2026-11-14","quote":"Step-3.5-Flash 262K $0.1 $0.3","notes":"Context shown as 262K."},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"step-3.7-flash","name":"Step-3.7-Flash","maker":"StepFun","provider_model_id":"stepfun-ai/Step-3.7-Flash","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":1.15,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/stepfun-ai/Step-3.7-Flash","checked":"2026-11-15","quote":"PRICING: INPUT $0.2 / CACHED $0.04 / OUTPUT $1.15","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"step-3.7-flash","name":"Step-3.7-Flash","maker":"StepFun","provider_model_id":"stepfun-ai/Step-3.7-Flash","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":1.15,"context":256000,"precision":"bf16","source_url":"https://console.gmicloud.ai/model/llm/stepfun-step-3-7-flash/824d96ea-74f3-42c1-aa61-c7a21c1e1449","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $0.20 Output $1.15 Cache Read $0.04 Cache Write -","notes":""},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"step-3.7-flash","name":"Step 3.7 Flash","maker":"StepFun","provider_model_id":"stepfun/step-3.7-flash","tier":"standard","input_per_m":0.2,"cached_input_per_m":0.04,"output_per_m":1.15,"context":262144,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Step 3.7 Flash 256K $0.2 /Mt · Cache Read $0.04 /Mt $1.15 /Mt","notes":""},{"provider":"featherless","provider_name":"Featherless","provider_kind":"host","maker_api":false,"model":"step-5-preview","name":"Step-5-Preview","maker":"StepFun","provider_model_id":"stepfun-ai/Step-5-Preview","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":2.7,"context":262144,"precision":"fp8","source_url":"https://featherless.ai/models/stepfun-ai/Step-5-Preview","checked":"2026-11-15","quote":"PRICING: INPUT $1 / CACHED $0.1 / OUTPUT $2.7","notes":"Developer plan (per-token billing, from 50 USD a month in credits)."},{"provider":"gmi-cloud","provider_name":"GMI Cloud","provider_kind":"host","maker_api":false,"model":"step-5-preview","name":"Step-5-Preview","maker":"StepFun","provider_model_id":"stepfun-ai/Step-5-Preview","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":2.7,"context":1048576,"precision":"fp8","source_url":"https://console.gmicloud.ai/model/llm/stepfun-step-5-preview/f2c4eeb4-8d4c-4b67-a4e5-82aba789412c","checked":"2026-11-15","quote":"Price (per 1M tokens) Input $1.00 Output $2.70 Cache Read $0.10 Cache Write -","notes":""},{"provider":"hyperbolic","provider_name":"Hyperbolic","provider_kind":"host","maker_api":false,"model":"step-5-preview","name":"Step 5 Preview","maker":"StepFun","provider_model_id":"step-5-preview","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":2.7,"context":1000000,"precision":null,"source_url":"https://www.hyperbolic.ai/inference","checked":"2026-11-14","quote":"Step 5 Preview step-5-preview StepFun · 1M context · Text $1.00 $2.70 $0.10","notes":"Context shown on page as \"1M\" (rounded); stored as the decimal value."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"step-5-preview","name":"Step 5 Preview","maker":"StepFun","provider_model_id":"stepfun/step-5-preview","tier":"standard","input_per_m":1,"cached_input_per_m":0.1,"output_per_m":2.7,"context":1000000,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"Step 5 Preview 977K $1 /Mt · Cache Read $0.1 /Mt $2.7 /Mt","notes":""},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"ternary-bonsai-27b","name":"Ternary Bonsai 27B","maker":"Prism ML","provider_model_id":null,"tier":"standard","input_per_m":0,"cached_input_per_m":null,"output_per_m":0,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Ternary Bonsai 27B Free Free","notes":"Listed as Free on the pricing page."},{"provider":"together","provider_name":"Together AI","provider_kind":"host","maker_api":false,"model":"tev1-4b-experimental","name":"Tev1 4B Experimental","maker":"Together AI","provider_model_id":"together/Tev1-4B-experimental","tier":"standard","input_per_m":0.042,"cached_input_per_m":null,"output_per_m":0,"context":null,"precision":null,"source_url":"https://www.together.ai/pricing","checked":"2026-11-14","quote":"Tev1 4B Experimental $0.042 $0.00","notes":"Classification/decision model (returns one option letter); output tokens free. Model page: https://www.together.ai/models/tev1-4b-experimental"},{"provider":"digitalocean","provider_name":"DigitalOcean Gradient (Serverless Inference)","provider_kind":"host","maker_api":false,"model":"trinity-large","name":"Trinity Large","maker":"Arcee AI","provider_model_id":null,"tier":"standard","input_per_m":0.25,"cached_input_per_m":0.06,"output_per_m":0.9,"context":null,"precision":null,"source_url":"https://docs.digitalocean.com/products/inference/details/pricing/","checked":"2026-11-14","quote":"Trinity Large — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.25$0.90$0.06","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"trinity-large-thinking","name":"Trinity Large (Thinking)","maker":"Arcee AI","provider_model_id":null,"tier":"standard","input_per_m":0.22,"cached_input_per_m":0.06,"output_per_m":0.85,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"Trinity Large (Thinking) $0.22 $0.85 $0.06","notes":""},{"provider":"parasail","provider_name":"Parasail","provider_kind":"host","maker_api":false,"model":"ui-tars-1.5-7b","name":"UI-TARS 1.5 7B","maker":"ByteDance","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":0.1,"output_per_m":0.2,"context":null,"precision":null,"source_url":"https://www.parasail.io/pricing","checked":"2026-11-14","quote":"UI-TARS 1.5 7B $0.10 $0.20 $0.10","notes":""},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"ultramarine-1-flash","name":"Ultramarine 1 Flash","maker":"Fireworks AI","provider_model_id":"accounts/fireworks/models/ultramarine-1-flash-us","tier":"standard","input_per_m":0.15,"cached_input_per_m":0.03,"output_per_m":0.5,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Ultramarine 1 Flash (US) | $0.15 / $0.03 / $0.50 | $0.1875 / $0.0375 / $0.625","notes":"US-only capacity model."},{"provider":"fireworks","provider_name":"Fireworks AI","provider_kind":"host","maker_api":false,"model":"ultramarine-1-flash","name":"Ultramarine 1 Flash","maker":"Fireworks AI","provider_model_id":"accounts/fireworks/models/ultramarine-1-flash-us","tier":"priority","input_per_m":0.1875,"cached_input_per_m":0.0375,"output_per_m":0.625,"context":1048576,"precision":null,"source_url":"https://docs.fireworks.ai/serverless/pricing","checked":"2026-11-14","quote":"Ultramarine 1 Flash (US) | Priority $0.1875 / $0.0375 / $0.625","notes":"Priority mode."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"venice-uncensored-1.2","name":"Venice Uncensored 1.2","maker":"Venice","provider_model_id":"venice-uncensored-1-2","tier":"standard","input_per_m":0.2,"cached_input_per_m":null,"output_per_m":0.9,"context":128000,"precision":"fp16","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Venice Uncensored 1.2 | `venice-uncensored-1-2` | $0.20 | $0.90 | — | — | Private |","notes":"Venice's own uncensored model."},{"provider":"venice","provider_name":"Venice","provider_kind":"host","maker_api":false,"model":"venice-uncensored-role-play","name":"Venice Role Play Uncensored","maker":"Venice","provider_model_id":"venice-uncensored-role-play","tier":"standard","input_per_m":0.5,"cached_input_per_m":null,"output_per_m":2,"context":128000,"precision":"fp8","source_url":"https://docs.venice.ai/pricing","checked":"2026-11-15","quote":"| Venice Role Play Uncensored | `venice-uncensored-role-play` | $0.50 | $2.00 | — | — | Private |","notes":"Venice's own uncensored role-play model."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"voxtral-mini-1.0","name":"Voxtral Mini 1.0","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.04,"cached_input_per_m":null,"output_per_m":0.04,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Voxtral Mini 1.0 $ 0.04 $ 0.04","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\". Speech-and-text model; token price as listed."},{"provider":"amazon-bedrock","provider_name":"Amazon Bedrock","provider_kind":"host","maker_api":false,"model":"voxtral-small-24b-2507","name":"Voxtral Small 1.0","maker":"Mistral AI","provider_model_id":null,"tier":"standard","input_per_m":0.1,"cached_input_per_m":null,"output_per_m":0.3,"context":null,"precision":null,"source_url":"https://aws.amazon.com/bedrock/pricing/","checked":"2026-11-14","quote":"Voxtral Small 1.0 $ 0.10 $ 0.30","notes":"Table headed \"Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)\". Speech-and-text model; token price as listed. Mapped to Voxtral Small 24B 2507."},{"provider":"novita","provider_name":"Novita AI","provider_kind":"host","maker_api":false,"model":"wizardlm-2-8x22b","name":"WizardLM 2 8x22B","maker":"Microsoft","provider_model_id":"microsoft/wizardlm-2-8x22b","tier":"standard","input_per_m":0.62,"cached_input_per_m":null,"output_per_m":0.62,"context":65535,"precision":null,"source_url":"https://novita.ai/pricing","checked":"2026-11-14","quote":"WizardLM 2 8x22B 64K $0.62 /Mt $0.62 /Mt","notes":""}]}