Mistral API: models and pricing
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on November 14, 2026· 230 models
20 Mistral chat models available by API, newest first, with price per million tokens, context and capabilities. Data as of 11/14/2026.
The cheapest Mistral API model is Mistral Nemo ($0.029 input and $0.030 output per million tokens). The newest is Mistral Large 4. Prices range from $0.029 to $2.00 per million input tokens. Data as of 11/14/2026.
Input price range
$0.029 – $2.00
per million input tokens
Cheapest model
Mistral Nemo
$0.029 / $0.030
≈ $0.56/month in the example
Newest model
Mistral Large 4
$0.700 / $2.10
≈ $18.90/month in the example
Cached input
$0.070 −90 %
per million tokens on Mistral Large 4; 16 models with cache price
Prices are input / output in USD per million tokens. Example: 10,000 requests a month of 1,500 input + 400 output tokens.
Mistral vs other AI APIs: the cheapest of each
The cheapest recent model of each provider, next to Mistral Nemo.
| Provider | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| Mistral | Mistral Nemo | $0.029 | $0.030 | |
| Qwen | Qwen3.7 Flash | $0.030 | $0.130 | Compare |
| DeepSeek | DeepSeek V4.1 Flash 1017 | $0.038 | $0.500 | Compare |
| Gemma 4 26B A4B | $0.068 | $0.225 | Compare | |
| OpenAI | GPT-6 Luna Pro | $0.100 | $0.500 | Compare |
| Anthropic | Claude Haiku 5.5 | $0.100 | $0.500 | Compare |
| Moonshot | Kimi K3 | $0.192 | $16.00 | Compare |
| xAI | Grok Build 0.1 | $1.00 | $2.00 | Compare |
| # | Model | Provider | Input $/1M | Output $/1M | Context | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| 1 | Mistral Large 4 | Mistral | $0.700 | $2.10 | 1 M | 10/06/2026 | |
| 2 | Mistral Medium 3.5 | Mistral | $1.50 | $7.50 | 262 K | 04/30/2026 | |
| 3 | Mistral Small 4 | Mistral | $0.150 | $0.600 | 262 K | 03/16/2026 | |
| 4 | Devstral 2 2512 | Mistral | $0.400 | $2.00 | 262 K | 12/09/2025 | |
| 5 | Ministral 3 8B 2512 | Mistral | $0.150 | $0.150 | 262 K | 12/02/2025 | |
| 6 | Ministral 3 3B 2512 | Mistral | $0.100 | $0.100 | 131 K | 12/02/2025 | |
| 7 | Ministral 3 14B 2512 | Mistral | $0.200 | $0.200 | 262 K | 12/02/2025 | |
| 8 | Mistral Medium 3.1 | Mistral | $0.400 | $2.00 | 131 K | 08/13/2025 | |
| 9 | Codestral 2508 | Mistral | $0.300 | $0.900 | 256 K | 07/30/2025 | |
| 10 | Voxtral Small 24B 2507 | Mistral | $0.100 | $0.300 | 33 K | 07/15/2025 | |
| 11 | Mistral Small 3.2 24B | Mistral | $0.100 | $0.300 | 256 K | 06/20/2025 | |
| 12 | Mistral Medium 3 | Mistral | $0.400 | $2.00 | 131 K | 05/07/2025 | |
| 13 | Mistral Small 3.1 24B | Mistral | $0.351 | $0.555 | 128 K | 03/17/2025 | |
| 14 | Saba | Mistral | $0.200 | $0.600 | 33 K | 02/17/2025 | |
| 15 | Mistral Small 3 | Mistral | $0.050 | $0.080 | 33 K | 01/30/2025 | |
| 16 | Mistral Large 2407 | Mistral | $2.00 | $6.00 | 131 K | 11/19/2024 | |
| 17 | Mistral Large 3 2512 | Mistral | $0.500 | $1.50 | 262 K | 11/01/2024 | |
| 18 | Mistral Nemo | Mistral | $0.029 | $0.030 | 131 K | 07/18/2024 | |
| 19 | Mixtral 8x22B Instruct | Mistral | $2.00 | $6.00 | 66 K | 04/17/2024 | |
| 20 | Mistral Large | Mistral | $2.00 | $6.00 | 128 K | 02/26/2024 |
More free tools
See allFrequently asked questions
How much does the Mistral API cost?
It depends on the model: from $0.029 to $2.00 per million input tokens. The cheapest is Mistral Nemo ($0.029 / $0.030); the newest is Mistral Large 4 ($0.700 / $2.10). Data as of 11/14/2026.
Is the Mistral API free?
No: the Mistral API is pay-as-you-go, billed per million tokens. The cheapest model, Mistral Nemo, costs $0.029 per million input tokens and $0.030 per million output tokens, so light use costs cents. Any free credits depend on Mistral's own offer.
Does the Mistral API charge less for cached input?
Yes, on 16 of its 20 models. For example, Mistral Large 4 charges $0.070 per million cached input tokens instead of $0.700: 90% less. The cache applies when you resend the same beginning of a prompt, like a long system prompt or a document.
How much does the Mistral API cost per month?
For 10,000 requests a month of 1,500 input tokens and 400 output tokens: Mistral Nemo costs about $0.56 and Mistral Large 4 about $18.90. Each model's page has a calculator for your own numbers.
How many Mistral models are available by API?
20 chat models in the catalog, as of 11/14/2026. Each one has its own sheet with pricing, context and capabilities.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.