Qwen3.8 27B API pricing
Updated
Among the 15 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Qwen3.8 27B is Chutes at USD 0.039 per 1M input tokens and USD 1.25 per 1M output tokens. The median across 15 standard prices is USD 0.40 / USD 3. Alibaba Cloud's own API charges USD 0.50 / USD 3.
What does Alibaba Cloud charge for Qwen3.8 27B?
- Input
- USD 0.50
- Cached input
- USD 0.10
- Output
- USD 3
- Blended 3:1
- USD 1.125
USD per 1M tokens on Alibaba Cloud Model Studio, model qwen3.8-27b, standard tier. Source, checked 2026-11-14.
Is a host cheaper than Alibaba Cloud? Yes. Chutes charges USD 0.039 input and USD 1.25 output per 1M tokens, 70% below Alibaba Cloud's own USD 0.50 / USD 3 on the 3:1 blend.
Qwen3.8 27B model facts
Facts from Qwen's model card for Qwen/Qwen3.8-27B and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (Qwen/Qwen3.8-27B) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 18 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | Qwen model card metadata, checked 2026-11-16Quote“license: apache-2.0” |
| Total parameters | 27B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 27B” |
| Context length | 262,144 tokens natively, extensible up to 1,000,000 | Qwen model card, checked 2026-11-16Quote“Context Length: 262,144 natively and extensible up to 1,000,000 tokens.” |
| Input and output | Text, images and video in; text out | Qwen model card, checked 2026-11-16Quote“a native vision-language model that understands images and videos” |
| Tool calling | Not found on Qwen's model card when we read it | checked 2026-11-16 |
| First published on Hugging Face (not necessarily the release date) | 2026-08-05 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-08-05T08:22:59.000Z"” |
Qwen3.8 27B price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 4.7× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Chutes cheapestQwen/Qwen3.8-27B-TEENotes and source quoteRuns on confidential TEE compute. “Qwen3.8-27B Qwen/Qwen3.8-27B-TEE $0.0039 per 1M tokens $0.039 per 1M tokens $1.25 per 1M tokens 262K” | USD 0.039 | USD 0.0039 | USD 1.25 | USD 0.3417 | 262,144 | FP8 | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | DeepInfra promoQwen/Qwen3.8-27BNotes and source quotePromotional price, 25% off list (list 0.2 in / 2.5 out). “$0.15 in $1.875 out $0.038 cached / 1M tokens” | USD 0.15 | USD 0.0375 | USD 1.875 | USD 0.5813 | 262,144 | not stated | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Hyperbolicqwen3.8-27bNotes and source quoteContext shown on page as "196K" (rounded); stored as the decimal value. “Qwen3.8 27B qwen3.8-27b Alibaba · 196K context · Text $0.20 $2.00 $0.02” | USD 0.20 | USD 0.02 | USD 2 | USD 0.65 | 196,000 | not stated | Hyperbolic page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | AkashML promoQwen/Qwen3.8-27BNotes and source quoteLabelled "Limited Trial" on AkashML. “Price (per 1M Tokens) Input Output Cache Read QWEN3.8 27B $0.225 $1.98 $0.05” | USD 0.225 | USD 0.05 | USD 1.98 | USD 0.6638 | 262,144 | not stated | AkashML page checked 2026-11-15 re-checked 2026-11-16 |
| 5 | Crusoe Cloudqwen/Qwen3.8-27BNotes and source quote“Qwen3.8 27B text, image $0.25 $2.00 $0.15” | USD 0.25 | USD 0.15 | USD 2 | USD 0.6875 | 262,144 | not stated | Crusoe Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 6 | NscaleNotes and source quote“| Qwen3.8-27B | Qwen | $0.20 | $2.50 |” | USD 0.20 | not published | USD 2.50 | USD 0.775 | not stated | not stated | Nscale page checked 2026-11-15 re-checked 2026-11-16 |
| 7 | CoreWeave ForgeQwen/Qwen3.8-27BNotes and source quote“Qwen3.8 27B $0.40 $3.00 $0.15” | USD 0.40 | USD 0.15 | USD 3 | USD 1.05 | 262,144 | not stated | CoreWeave Forge page checked 2026-11-15 re-checked 2026-11-16 |
| 8 | FeatherlessQwen/Qwen3.8-27BNotes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.4 / CACHED $0.15 / OUTPUT $3” | USD 0.40 | USD 0.15 | USD 3 | USD 1.05 | 262,144 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 9 | Novita AIqwen/qwen3.8-27bNotes and source quote“Qwen3.8 27B 977K $0.42 /Mt · Cache Read $0.085 /Mt $3 /Mt” | USD 0.42 | USD 0.085 | USD 3 | USD 1.065 | 1,000,000 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 10 | Cerebrasqwen-3.8-27bNotes and source quoteDeveloper (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). “Qwen 3.8 27B ~1,850 tokens/s $0.99/M tokens $1.49/M tokens” | USD 0.99 | USD 0.99 | USD 1.49 | USD 1.115 | 131,072 | not stated | Cerebras page checked 2026-11-14 re-checked 2026-11-16 |
| 11 | Alibaba Cloud makerqwen3.8-27bNotes and source quoteInternational (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. “qwen3.8-27b context caching discount International Non-Thinking and Thinking modes 0<Token≤1M $0.5 $3” | USD 0.50 | USD 0.10 | USD 3 | USD 1.125 | not stated | not stated | Alibaba Cloud page checked 2026-11-14 re-checked 2026-11-16 |
| 12 | Cloudflare Workers AI@cf/qwen/qwen3.8-27bNotes and source quoteCloudflare publishes this USD per-token price alongside the neuron price. “@cf/qwen/qwen3.8-27b $0.450 per M input tokens $3.200 per M output tokens” | USD 0.45 | not published | USD 3.20 | USD 1.138 | not stated | not stated | Cloudflare Workers AI page checked 2026-11-14 re-checked 2026-11-16 |
| 13 | GMI CloudQwen/Qwen3.8-27BNotes and source quote“Price (per 1M tokens) Input $0.45 Output $3.20 Cache Read $0.25 Cache Write -” | USD 0.45 | USD 0.25 | USD 3.20 | USD 1.138 | 262,144 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 14 | Veniceqwen-3-8-27bNotes and source quoteBeta model. “| Qwen 3.8 27B (Beta) | `qwen-3-8-27b` | $0.45 | $3.20 | — | — | Private |” | USD 0.45 | not published | USD 3.20 | USD 1.138 | 262,144 | FP8 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 15 | Groqqwen/qwen3.8-27bNotes and source quotePreview model (evaluation use only per Groq). “qwen/qwen3.8-27b | 450 | $0.80 input$4.00 output | 250K TPM1K RPM | 131,072” | USD 0.80 | not published | USD 4 | USD 1.60 | 131,072 | not stated | Groq page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spot promoQwen/Qwen3.8-27BNotes and source quoteFlex service tier (0.8× standard). Promotional price, 25% off list (list 0.2 in / 2.5 out). “Flex (0.8×) $0.12 $1.50 $0.03” | USD 0.12 | USD 0.03 | USD 1.50 | USD 0.465 | 262,144 | not stated | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra priority promoQwen/Qwen3.8-27BNotes and source quotePriority service tier (1.5× standard). Promotional price, 25% off list (list 0.2 in / 2.5 out). “Priority (1.5×) $0.225 $2.8125 $0.0563” | USD 0.225 | USD 0.0563 | USD 2.8125 | USD 0.8719 | 262,144 | not stated | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | BroadNet Inference this site's ownerbroadnet/qwen3.8-27bSame model. Not ranked: BroadRouter is BroadNet's own site. Model page | USD 0.175 | USD 0.0435 | USD 2.17 | USD 0.6737 | 262,144 | not stated | pricing.json synced 2026-11-14 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Promo: the provider's page describes these prices as promotional or discounted (DeepInfra and AkashML). They rank as published, but can end without notice; the row's notes give the list price or end date where the page states one.
- Other tiers (flex / spot and priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Qwen3.8 27B cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Chutes | USD 24.11 | USD 25.58 | USD 129.00 |
| DeepInfra (promo) | USD 41.18 | USD 56.02 | USD 266.63 |
| Hyperbolic | USD 44.28 | USD 65.04 | USD 264.60 |
| AkashML (promo) | USD 46.44 | USD 71.10 | USD 315.45 |
| Crusoe Cloud | USD 53.10 | USD 82.80 | USD 477.00 |
| Nscale | USD 63.00 | USD 85.50 | USD 585.00 |
| CoreWeave Forge | USD 76.50 | USD 123.00 | USD 607.50 |
| Featherless | USD 76.50 | USD 123.00 | USD 607.50 |
| Novita AI | USD 73.71 | USD 121.68 | USD 513.45 |
| Cerebras | USD 115.92 | USD 259.95 | USD 1,916 |
| Alibaba Cloud (maker) | USD 77.40 | USD 136.20 | USD 558.00 |
| Cloudflare Workers AI | USD 98.10 | USD 156.00 | USD 1,098 |
| GMI Cloud | USD 87.30 | USD 141.60 | USD 792.00 |
| Venice | USD 98.10 | USD 156.00 | USD 1,098 |
| Groq | USD 144.00 | USD 252.00 | USD 1,800 |
| BroadNet Inference (this site's owner) | USD 47.71 | USD 65.08 | USD 309.11 |
For the support chatbot, the cheapest price (Chutes, USD 24.11 a month) saves USD 52.39 against the median (USD 76.50). For the coding agent the gap is USD 456.00 a month (78% lower).
Which Qwen3.8 27B provider is cheapest for your traffic?
Chutes has the lowest input price (USD 0.039) and the lowest output price (USD 1.25), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Chutes | USD 0.3417 cheapest | USD 0.3286 cheapest | USD 0.3181 cheapest |
| DeepInfra | USD 0.5813 | USD 0.5391 | USD 0.5053 |
| Hyperbolic | USD 0.65 | USD 0.5825 | USD 0.5285 |
| AkashML | USD 0.6638 | USD 0.5981 | USD 0.5456 |
| Crusoe Cloud | USD 0.6875 | USD 0.65 | USD 0.62 |
| Nscale (no cache price) | USD 0.775 | USD 0.775 | USD 0.775 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 9 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
10 of 15 providers publish a cached-input price below the input price: Chutes (90% off), DeepInfra (75% off), Hyperbolic (90% off), AkashML (78% off), Crusoe Cloud (40% off) and 5 more. Nscale, Cloudflare Workers AI, Venice and Groq publish none, so cached tokens there bill at the input price. Cerebras lists a cached price equal to its input price.
Context windows differ: 1,000,000 tokens at Novita AI; 262,144 tokens at Chutes, DeepInfra, AkashML and 5 more; 196,000 tokens at Hyperbolic; 131,072 tokens at Cerebras and Groq. Nscale, Alibaba Cloud and Cloudflare Workers AI do not state one. The cheapest row is not always the one that fits a long prompt.
Qwen3.8 27B on BroadNet Inference
BroadRouter is BroadNet's own site. BroadNet Inference serves this model as broadnet/qwen3.8-27b at USD 0.175 input, USD 0.0435 cached input and USD 2.17 output per 1M tokens, with a 262,144-token context. On the 3:1 blend, 4 standard prices above are lower, so pick BroadNet for other reasons: zero data retention and one OpenAI-compatible key for every BroadNet model.
What does Qwen3.8 27B cost in other languages?
The same text needs a different number of tokens in each language. With the Qwen3.8 27B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Qwen3.8 27B:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.0087 | Chutes |
| Arabic MSA | USD 0.012 | Chutes |
| Hindi | USD 0.016 | Chutes |
| Chinese | USD 0.023 | Chutes |
| Code | USD 0.011 | Chutes |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Published benchmark results
BroadNet did not run these benchmarks; results are as published by the Qwen model card and may use different settings.
| Benchmark | Result | Setting or note | Source |
|---|---|---|---|
| GPQA Diamond | 89.2 | not stated | Qwen model card, checked 2026-11-16 |
| LiveCodeBench v6 | 90.3 | not stated | Qwen model card, checked 2026-11-16 |
| SWE-bench Pro | 61.7 | not stated | Qwen model card, checked 2026-11-16 |
| Terminal Bench 2.1 (Terminus) | 73.0 | not stated | Qwen model card, checked 2026-11-16 |
| IFBench | 79.5 | not stated | Qwen model card, checked 2026-11-16 |
| OSWorld-Verified | 84.3 | not stated | Qwen model card, checked 2026-11-16 |
| OmniDocBench 1.5 | 91.1 | not stated | Qwen model card, checked 2026-11-16 |
Estimate your own bill
- LLM API cost calculator with Qwen3.8 27B preloaded: your traffic and cache rate, against any of 429 models.
- Qwen token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Qwen3.8 27B compare with other Qwen models?
The Qwen models whose cheapest standard price is closest to Qwen3.8 27B's (USD 0.3417 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Qwen3 Next 80B A3B Instruct | USD 0.09 | USD 1.10 | 262,144 | 5 |
| Qwen3.5 35B A3B | USD 0.14 | USD 1 | 262,144 | 7 |
| Qwen2.5-72B-Instruct | USD 0.36 | USD 0.40 | 32,768 | 3 |
| Qwen3 VL 235B A22B | USD 0.20 | USD 0.88 | 262,144 | 3 |
| Qwen-MT Plus | USD 0.25 | USD 0.75 | 16,384 | 2 |
| Qwen3-VL 8B | USD 0.18 | USD 0.68 | 262,144 | 2 |
Priced closest from other makers: DeepSeek-V4-Flash-Vision-Exp (DeepSeek, USD 0.3234) · MiniMax M2.7 (MiniMax, USD 0.3675) · DeepSeek R1 Distill Llama 70B (DeepSeek, USD 0.375).
Compare Qwen3.8 27B with
- Qwen3.8 27B vs Qwen3.6 27B: API price side by side
- DeepSeek V4.1 Flash vs Qwen3.8 27B: API price side by side
- Gemma 4 31B vs Qwen3.8 27B: API price side by side
- GLM 5.3 vs Qwen3.8 27B: API price side by side
- gpt-oss-120b vs Qwen3.8 27B: API price side by side
- Qwen3.8 27B vs Llama 4 Maverick: API price side by side
- Qwen3.8 27B vs MiniMax M3: API price side by side
- Qwen3.8 27B vs DeepSeek V3.2: API price side by side
Also compared: vs Qwen3.6 27B · vs DeepSeek V4.1 Flash · vs Gemma 4 31B · vs GLM 5.3 · vs OpenAI GPT OSS 120B · vs Llama 4 Maverick 17B 128E Instruct FP8 · vs MiniMax M3 · vs DeepSeek V3.2 · vs Qwen3.8 2.4T A95B · vs DeepSeek-V4-Flash-Vision-Exp · vs GLM 4.5 Air · vs Step 3.7 Flash · vs MiniMax M3.1 Flash · vs GPT-5.6 Luna · vs Inkling 2 Small.
Every Qwen3.8 27B price comparison · All model-vs-model price comparisons
All 429 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Qwen3.8 27B API cost per token?
From USD 0.039 per 1M input tokens (USD 0.000000039 per token) and USD 1.25 per 1M output tokens (USD 0.00000125 per token) at the lowest standard prices we found. The median of 15 standard prices is USD 0.40 input and USD 3 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Qwen3.8 27B?
Among the 15 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Chutes, ranked on a blend of 3 input tokens to 1 output token (USD 0.3417 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is Qwen3.8 27B cheaper from a host than from Alibaba Cloud?
Yes. Chutes charges USD 0.039 input and USD 1.25 output per 1M tokens, 70% below Alibaba Cloud's own USD 0.50 / USD 3 on the 3:1 blend.
Does Qwen3.8 27B have cached input pricing?
11 of 15 standard prices include one. The lowest is USD 0.0039 per 1M at Chutes; the median is USD 0.10. Providers without one bill cached input at the input price. What cached input means.
What is the Qwen3.8 27B context window?
Up to 1,000,000 tokens. 11 standard prices come with less, down to 131,072 tokens (Cerebras, Groq, Hyperbolic, AkashML and 7 more). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Qwen3.8 27B?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 129.00 a month at Chutes, USD 585.00 at the median price and USD 1,916 at Cerebras. Try your own numbers.
Is there a batch, flex or priority price for Qwen3.8 27B?
Yes: flex / spot from DeepInfra at USD 0.12 / USD 1.50; priority from DeepInfra at USD 0.225 / USD 2.8125 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is Qwen3.8 27B free to use through an API?
No provider in our data lists a free price for Qwen3.8 27B as of 2026-11-15. BroadNet Inference serves it as broadnet/qwen3.8-27b to paid accounts only: the USD 5 starting credit does not cover it (rate card synced 2026-11-14). Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is Qwen3.8 27B open source, with open weights, and what is its licence?
Qwen publishes the weights on Hugging Face as Qwen/Qwen3.8-27B, in a public repository with no access gate. The licence, as the Qwen model card metadata states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Qwen's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.
How many parameters does Qwen3.8 27B have?
Total parameters, as the Qwen model card states them: 27B. (checked 2026-11-16; BroadNet did not verify these figures.)
Can I use Qwen3.8 27B on BroadNet Inference?
Yes. BroadNet Inference serves Qwen3.8 27B as broadnet/qwen3.8-27b at USD 0.175 input, USD 0.0435 cached and USD 2.17 output per 1M tokens (rate card synced 2026-11-14), with zero data retention. On the 3:1 blend, 4 standard prices on this page are lower. BroadRouter is BroadNet's own site. Qwen3.8 27B on BroadNet.
How do I call Qwen3.8 27B with the OpenAI SDK?
On BroadNet Inference, point the OpenAI SDK at https://inference.broadnet.ai/v1 with your BroadNet key and set the model to broadnet/qwen3.8-27b: client = OpenAI(base_url="https://inference.broadnet.ai/v1", api_key=...), then client.chat.completions.create(model="broadnet/qwen3.8-27b", messages=[...]). BroadRouter is BroadNet's own site. Setup notes for agents: llms.txt for Qwen3.8 27B on BroadNet.
How does Qwen3.8 27B score on benchmarks?
As published, the Qwen model card reports 89.2 on GPQA Diamond, 90.3 on LiveCodeBench v6 and 61.7 on SWE-bench Pro (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- AkashML: pricing (checked 2026-11-15)
- Alibaba Cloud: own API pricing (checked 2026-11-14)
- Cerebras: pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- Crusoe Cloud: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- Groq: pricing (checked 2026-11-14)
- Hyperbolic: pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- Nscale: pricing (checked 2026-11-15)
- Venice: pricing (checked 2026-11-15)
- BroadNet Inference rate card, pricing.json (synced 2026-11-14)