Mistral
Codestral 2508
mistralai/codestral-2508
Input
$0.30
per 1M tokens
Output
$0.90
per 1M tokens
Cached input
$0.03
per 1M tokens
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
- Released
- Context window
- 256K tokens
- Max output
- 205K tokens
- Input
- text, file
- Output
- text
- Reasoning
- No
Price history
No price changes since we started tracking on .
Providers on OpenRouter
2 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| Mistralvendor's own | $0.30 | $0.90 | 256K | 100% | 100% |
| Mistraleuvendor's own | $0.33 | $0.99 | 256K | — | 100% |