3AM Marketer
AI

Mistral API Pricing: 2026 Model Token Costs Guide

A complete breakdown of Mistral API pricing across current models, including batch processing discounts and prompt cache rates.

$0.10 / 1M
Mistral Large 4$0.70
mistral-large-2512$0.50
Mistral Large 3$0.50
Mistral Medium 3.5$1.50
Input ($/1M tokens), from the entry's own table. 3 sources, checked 15 Nov 2026. Full table

Mistral API pricing ranges from $0.10 per million input tokens on Ministral 3 3B up to $0.70 per million input tokens on Mistral Large 4. Teams running offline workloads can reduce these base rates by 50% using batch endpoints, while repeat prompts benefit from a 10% rate for cached input tokens.123

The current Mistral API pricing structure

Mistral charges for model inference on a per-token basis, separating fees for prompt processing (input) from generation (output). The active catalogue spans small edge-oriented models, mid-tier general models, and flagship reasoning engines tracked in the LLM API pricing timeline.1

The price spread across these tiers is substantial. For 1 million input plus 1 million output tokens, Mistral Ministral 3 3B costs $0.20 and Mistral Large 4 costs $2.80, which is 14 times as much.1

Standard production model costs

The flagship tier recently shifted with the addition of Mistral Large 4 at $0.70 per million input tokens and $2.10 per million output tokens, as documented alongside other Mistral Large 4 release specs. That sits above earlier versions like Mistral Large 3 and mistral-large-2512, which ran at $0.50 input and $1.50 output per million tokens before Mistral retired them.1

ModelInput ($/1M tokens)Output ($/1M tokens)Data Captured
Mistral Large 4$0.70$2.102026-11-04
More on Mistral Large 4
Data Captured
2026-11-04
mistral-large-2512$0.50$1.502026-10-29
More on mistral-large-2512
Data Captured
2026-10-29
Mistral Large 3$0.50$1.502026-10-03
More on Mistral Large 3
Data Captured
2026-10-03
Mistral Medium 3.5$1.50$7.502026-10-03
More on Mistral Medium 3.5
Data Captured
2026-10-03
Mistral Small 4$0.15$0.602026-10-03
More on Mistral Small 4
Data Captured
2026-10-03
Ministral 3 14B$0.20$0.202026-10-03
More on Ministral 3 14B
Data Captured
2026-10-03
Ministral 3 8B$0.15$0.152026-10-03
More on Ministral 3 8B
Data Captured
2026-10-03
Ministral 3 3B$0.10$0.102026-10-03
More on Ministral 3 3B
Data Captured
2026-10-03
  • Large 42.1$
  • Large-25121.5$
  • Large 31.5$
  • Medium 3.57.5$
  • Small 40.6$
  • Min 14B0.2$
  • Min 8B0.15$
  • Min 3B0.1$
Comparison of output token pricing across current Mistral models in dollars per million tokens.1
  • Large 40.7$
  • Large-25120.5$
  • Large 30.5$
  • Medium 3.51.5$
  • Small 40.15$
  • Min 14B0.2$
  • Min 8B0.15$
  • Min 3B0.1$
Comparison of input token pricing across current Mistral models in dollars per million tokens.1

Operational cost-saving strategies

Mistral provides two native mechanisms to lower inference expenses on production applications: asynchronous batching and prompt caching.23

Batch processing allows running asynchronous inference on large inputs in parallel at a 50% discount. Cached tokens in the chat completion endpoint are billed at 10% of the standard input token price, reducing repetitive system prompt overhead.23

Technical requirements for batch processing

Taking advantage of the 50% batch discount requires routing jobs through specific payload limits. The batch processing service supports up to 1 million requests in a single batch file.3

Screenshot of the Mistral Batch Processing documentation showing the structure of a batch file for chat completions.
Screenshot of docs.mistral.ai, captured 2026-11-04

For lighter bulk queues, teams do not need to generate and upload dedicated file objects. Inline batching is supported for batches containing fewer than 10,000 requests, allowing developers to include the request body directly in the call.3

What we got wrong

Mistral Medium 3.5, Mistral Large 3 and mistral-large-2512 are no longer on Mistral's pricing pages. The price range and the cost comparison now use Mistral Large 4, the most expensive current model ($0.70 input, $2.10 output per million tokens).

Our pricing tracker records Medium 3.5 and Large 3 as removed from Mistral's pricing pages; Mistral's model page lists Large 4 at $0.70 per million input tokens and $2.10 per million output tokens.