Alexey Shurov.
Free tool

Mistral API pricing per million tokens

On 25 September 2026, Mistral models on this list cost from $0.019 per million input tokens (Mistral Nemo) to $2.00 (Mistral Large 2407), and from $0.03 per million output tokens (Mistral Nemo) to $7.50 (Mistral Medium 3.5).

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens
ModelInputOutputCached inputBatch in / outContextYour monthListed
Mistral Medium 3.5$1.50$7.50$0.75 / $3.75262K$202.502026-04-30
Mistral Small 4$0.15$0.60$0.015$0.075 / $0.30262K$18.002026-03-16
Devstral 2 2512$0.40$2.00$0.04262K$54.002025-12-09
Ministral 3 14B 2512$0.20$0.20$0.02262K$15.002025-12-02
Ministral 3 8B 2512$0.15$0.15$0.015$0.075 / $0.075262K$11.252025-12-02
Ministral 3 3B 2512$0.10$0.10$0.01131K$7.502025-12-02
Mistral Large 3 2512$0.50$1.50$0.05$0.25 / $0.75262K$52.502025-12-01
Voxtral Small 24B 2507$0.10$0.30$0.0133K$10.502025-10-30
Mistral Medium 3.1$0.40$2.00$0.04$0.20 / $1.00131K$54.002025-08-13
Codestral 2508$0.30$0.90$0.03$0.15 / $0.45256K$31.502025-08-01
Mistral Small 3.2 24B$0.0938$0.25256K$9.382025-06-20
Mistral Medium 3$0.40$2.00$0.04131K$54.002025-05-07
Mistral Small 3.1 24B$0.351$0.555128K$29.392025-03-17
Saba$0.20$0.60$0.0233K$21.002025-02-17
Mistral Small 3$0.05$0.0833K$4.202025-01-30
Mistral Large 2407$2.00$6.00$0.20131K$210.002024-11-19
Mistral Nemo$0.019$0.03131K$1.592024-07-19
Mixtral 8x22B Instruct$2.00$6.00$0.2066K$210.002024-04-17
Mistral Large$2.00$6.00$0.20128K$210.002024-02-26

Compare Mistral with every other provider

Common questions

How much does the Mistral API cost?

On 25 September 2026, Mistral models on this list cost from $0.019 per million input tokens (Mistral Nemo) to $2.00 (Mistral Large 2407), and from $0.03 per million output tokens (Mistral Nemo) to $7.50 (Mistral Medium 3.5).

What is the cheapest Mistral model?

For a typical mix of three input tokens to every output token, the cheapest is Mistral Nemo at $0.019 per million input tokens and $0.03 per million output tokens.

What is the newest Mistral model on the list?

Mistral Medium 3.5, listed on 30 April 2026, at $1.50 per million input tokens and $7.50 per million output tokens.

Which Mistral model has the largest context window?

Mistral Medium 3.5, with 262K tokens of context.

Does Mistral offer batch pricing?

Yes, 6 of its models on this list show a batch price, with batch input at a median of 50 percent of the standard price. Batch suits work that can wait for its answer.

Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.

shurco.aiGuidesFree toolsSolutionsInsightsRSSllms.txt