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
Mistral: Codestral 2508 — Mistral AI. Context window 256,000 tokens. API pricing (per 1M tokens): Input $0.3, Output $0.9. License: Open-Weights.
| Provider | Mistral AI |
|---|---|
| API model ID | mistralai/codestral-2508 |
| Tier | Frontier |
| Context window | 256,000 tokens |
| Max output | 204,800 tokens |
| License | Open-Weights |
| API pricing (per 1M tokens) · Input | $0.3 |
| API pricing (per 1M tokens) · Output | $0.9 |