Model prices / Mistral AI / Codestral 25.08
Codestral 25.08
Mistral AI · released 2025-07-30
The official API price of Codestral 25.08 is $0.3 per 1M input tokens and $0.9 per 1M output tokens (as of 2026-11-12). Context window: 256K tokens, up to 8.2K output tokens per request. 11 providers sell it, none below the official price.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| MistralOfficialcodestral-2508 | $0.3 | $0.9 | $0.03 | Official | Official docs |
EEden AImistral/ | $0.3 | $0.9 | $0.03 | Official docs | |
 Vertexcodestral-2 | $0.3 | $0.9 | — | Official docs | |
KKilo Gatewaymistralai/ | $0.3 | $0.9 | $0.03 | Official docs | |
 DevPass (LLM Gateway)codestral-2508 | $0.3 | $0.9 | — | Official docs | |
LLLM Gatewaymistral/ | $0.3 | $0.9 | — | Official docs | |
NNanoGPTmistralai/ | $0.3 | $0.9 | $0.15 | Official docs | |
 OpenRoutermistralai/ | $0.3 | $0.9 | $0.03 | Official docs | |
LLowRouterauto/ | $0.3138 | $0.9413 | $0.0314 | Official docs | |
 AI/ML APImistralai/ | $0.3174 | $0.9522 | $0.03174 | Official docs | |
EEden AImistral/ | $0.33 | $0.99 | $0.033 | Official docs | |
CCortecscodestral-2508 | $0.368 | $1.103 | $0.037 | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Mistral code model for low-latency completion, fill-in-the-middle, and code generation
Description from models.dev.
Specs
- Type
- Text
- Context
- 256K
- Max output
- 8.2K
- Input
- Text, PDF
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- No
- Released
- 2025-07-30
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.