Codestral 2508
MistralMistral'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)
| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.30 | $0.90 | $0.45 | - |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 256K
- max output
- 205K
- cache read /1M
- $0.03
- Family
- mistral
- Modalities
- text · file
- Features
- json · tools
Live pricing, updated 2026-11-03.
| Model | In | Out | Ctx |
|---|---|---|---|
| Mistral Small 4 | $0.15 | $0.6 | 262K |
| Saba | $0.2 | $0.6 | 33K |
| Mistral Small 3.1 24B | $0.351 | $0.555 | 128K |
| Codestral 2508 · this model | $0.3 | $0.9 | 256K |
| Mistral Large 3 2512 | $0.5 | $1.5 | 262K |
| Devstral 2 2512 | $0.4 | $2 | 262K |