Provider
Mistral API pricing: every model compared
Mistral offers 20 models through its API in our data, priced from $0.029 to $2 per million input tokens. The newest is Mistral Large 4, first listed on 2026-10-06.
- Models
- 20
- Cheapest input
- $0.029
- Priciest input
- $2
- Largest context
- 1,048,576
- With caching
- 15 of 20
- Open weights
- 11 of 20
Cheapest
Mistral NemoMistral$0.029 in · $0.03 outLine-up
Every Mistral model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Mistral Large 4 | $0.68 | $2.09 | 1,048,576 | 2026-10-06 |
| Mistral Medium 3.5 | $1.50 | $7.50 | 262,144 | 2026-04-30 |
| Mistral Small 4 | $0.15 | $0.60 | 262,144 | 2026-03-16 |
| Devstral 2 2512 | $0.40 | $2 | 262,144 | 2025-12-09 |
| Ministral 3 14B 2512 | $0.20 | $0.20 | 262,144 | 2025-12-02 |
| Ministral 3 3B 2512 | $0.10 | $0.10 | 131,072 | 2025-12-02 |
| Ministral 3 8B 2512 | $0.15 | $0.15 | 262,144 | 2025-12-02 |
| Mistral Large 3 2512 | $0.50 | $1.50 | 262,144 | 2025-12-01 |
| Voxtral Small 24B 2507 | $0.10 | $0.30 | 32,768 | 2025-10-30 |
| Mistral Medium 3.1 | $0.40 | $2 | 131,072 | 2025-08-13 |
| Codestral 2508 | $0.30 | $0.90 | 256,000 | 2025-08-01 |
| Mistral Small 3.2 24B | $0.0938 | $0.25 | 256,000 | 2025-06-20 |
| Mistral Medium 3 | $0.40 | $2 | 131,072 | 2025-05-07 |
| Mistral Small 3.1 24B | $0.351 | $0.555 | 128,000 | 2025-03-17 |
| Saba | $0.20 | $0.60 | 32,768 | 2025-02-17 |
| Mistral Small 3 | $0.05 | $0.08 | 32,768 | 2025-01-30 |
| Mistral Large 2407 | $2 | $6 | 131,072 | 2024-11-19 |
| Mistral Nemo | $0.029 | $0.03 | 131,072 | 2024-07-19 |
| Mixtral 8x22B Instruct | $2 | $6 | 65,536 | 2024-04-17 |
| Mistral Large | $2 | $6 | 128,000 | 2024-02-26 |
Prices in US dollars per 1M tokens, newest first. Release dates are when our source first listed the model.
Overview
Mistral’s pricing at a glance
The spread between Mistral’s cheapest and most expensive model is large: Mixtral 8x22B Instruct costs 69× more per input token than Mistral Nemo. Picking the smallest model that does the job well is usually the biggest saving available, ahead of any discount.
15 of 20 of the line-up has a cached-input price, which helps chatbots and agents that resend the same instructions. 6 of 20 can run through a batch API at a discount, for work that can wait up to a day. 11 of 20 accept images as input.
FAQ
Mistral API questions
How much does the Mistral API cost?
Mistral's 20 models range from $0.029 to $2 per million input tokens, and output costs more than input on almost every model. The exact bill depends on your token volumes, which you can estimate in the LLM cost calculator.
What is Mistral's cheapest model?
By blended price (three parts input to one part output) it is Mistral Nemo, at $0.029 input and $0.03 output per million tokens. The most expensive is Mixtral 8x22B Instruct.
Which Mistral model has the largest context window?
Mistral Large 4, with 1,048,576 tokens per request.
Does Mistral offer prompt caching or batch discounts?
In our data, 15 of 20 of Mistral's models have a published cached-input price and 6 of 20 have a published batch price. Both can cut costs substantially for repeated prompts or work that can wait.