BroadRouter

Mistral Large 3 API pricing

Updated

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Mistral Large 3 is Amazon Bedrock at USD 0.50 per 1M input tokens and USD 1.50 per 1M output tokens. The median across 3 standard prices is USD 0.636 / USD 1.908. Each price is read from the provider's own pricing page.

Mistral AI · slug mistral-large-2512 · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

Does Mistral AI sell Mistral Large 3 directly?

Mistral AI publishes no price for Mistral Large 3 on its own API that we could find, so this page compares hosts only.

Mistral Large 3 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 83% above the cheapest.

Mistral Large 3 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Amazon Bedrock cheapest
Notes and source quote

Table headed "Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)".

“Mistral Large 3 $ 0.50 $ 1.50”
USD 0.50not publishedUSD 1.50USD 0.75not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
2IBM watsonx.ai
mistral-large-2512
Notes and source quote
“mistral-large-2512 Mistral AI USD 0.636 per 1M tokens input USD 1.908 per 1M tokens output”
USD 0.636not publishedUSD 1.908USD 0.954not statednot statedIBM watsonx.ai page
checked 2026-11-15
re-checked 2026-11-16
3Nscale
Mistral-Large-3-675B-Instruct-2512-NVFP4
Notes and source quote

Moves from serverless to dedicated models on 11 December 2026 per Nscale.

“| Mistral-Large-3-675B-Instruct-2512-NVFP4 | Mistral AI | $1.00 | $2.50 |”
USD 1not publishedUSD 2.50USD 1.375not statedNVFP4Nscale page
checked 2026-11-15
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Mistral Large 3 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.
Monthly cost of three workloads on Mistral Large 3, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Amazon BedrockUSD 72.00USD 142.50USD 1,035
IBM watsonx.aiUSD 91.58USD 181.26USD 1,317
NscaleUSD 135.00USD 277.50USD 2,025

For the support chatbot, the cheapest price (Amazon Bedrock, USD 72.00 a month) saves USD 19.58 against the median (USD 91.58). For the coding agent the gap is USD 281.52 a month (21% lower).

Which Mistral Large 3 provider is cheapest for your traffic?

Amazon Bedrock has the lowest input price (USD 0.50) and the lowest output price (USD 1.50), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

Mistral Large 3: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Amazon Bedrock (no cache price)USD 0.75 cheapestUSD 0.75 cheapestUSD 0.75 cheapest
IBM watsonx.ai (no cache price)USD 0.954USD 0.954USD 0.954
Nscale (no cache price)USD 1.375USD 1.375USD 1.375

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. 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.

None of the 3 providers publishes a cached-input discount for Mistral Large 3, so cache hits do not change the ranking.

No provider states a context window for Mistral Large 3 on its pricing page.

Estimate your own bill

The Mistral AI models whose cheapest standard price is closest to Mistral Large 3's (USD 0.75 blended):

Mistral AI models priced closest to Mistral Large 3
ModelCheapest inputCheapest outputMax contextProviders
Mistral Medium 3USD 0.40USD 2—2
Ministral 3 14BUSD 0.20USD 0.20262,1443
Mistral Small 3.1 24B InstructUSD 0.10USD 0.3032,7684
Ministral 3 8BUSD 0.15USD 0.15262,1442
Mistral Small 3.2 24B InstructUSD 0.075USD 0.20256,0004
Ministral 3 3BUSD 0.10USD 0.10262,1442

Priced closest from other makers: Qwen2.5 Coder 32B Instruct (Qwen, USD 0.745) · Kimi K2.6 (Moonshot AI, USD 0.7425) · GLM 4.6 (Z.ai, USD 0.76).

All 428 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 Mistral Large 3 API cost per token?

From USD 0.50 per 1M input tokens (USD 0.0000005 per token) and USD 1.50 per 1M output tokens (USD 0.0000015 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 0.636 input and USD 1.908 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Mistral Large 3?

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Amazon Bedrock, ranked on a blend of 3 input tokens to 1 output token (USD 0.75 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.

Does Mistral AI sell Mistral Large 3 on its own API?

Mistral AI publishes no price for Mistral Large 3 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Amazon Bedrock at USD 0.50 / USD 1.50 per 1M tokens.

Does Mistral Large 3 have cached input pricing?

None of the 3 standard prices includes a cached-input price, so budget repeated prompts at the full input price.

How much does a coding agent cost per month on Mistral Large 3?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,035 a month at Amazon Bedrock, USD 1,317 at the median price and USD 2,025 at Nscale. Try your own numbers.

Is Mistral Large 3 free to use through an API?

No provider in our data lists a free price for Mistral Large 3 as of 2026-11-15. 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.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity