As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/codestral-2508/

# Codestral 25.08

Mistral AI, Codestral family. Status: current. Type: code model. Released: 2025-07-30.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Mistral API (FIM) | `codestral-2508` | https://api.mistral.ai/v1/fim/completions | https://docs.mistral.ai/models/model-cards/codestral-25-08 |
| Mistral API (chat) | `codestral-latest` | https://api.mistral.ai/v1/chat/completions |  |
| OpenRouter | `mistralai/codestral-2508` |  | https://openrouter.ai/mistralai/codestral-2508 |

## Pricing

- Input: $0.30 per 1M tokens
- Output: $0.90 per 1M tokens
- Unit as published: per 1M tokens (USD)
- Source: https://docs.mistral.ai/models/model-cards/codestral-25-08
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: text
- Context window: 128,000 tokens
- Max output: not published
- Open weights: no
- Licence: mistral-premier

## Where it stands

- Newer code models in the registry since its release: 6. The 5 newest:
  - Recursive Flint (2026-10-21) https://postcutoff.com/m/recursive-flint/
  - Mellum2.1 12B-A2.5B Thinking (2026-10-08) https://postcutoff.com/m/mellum2-1/
  - Leanstral 1.5 (2026-07-02) https://postcutoff.com/m/leanstral-1-5/
  - Kimi K2.7 Code (2026-06) https://postcutoff.com/m/kimi-k2-7-code/
  - Grok Build 0.1 (2026-05) https://postcutoff.com/m/grok-build-0-1/
- After it from Mistral AI: Leanstral 1.5 (2026-07-02) https://postcutoff.com/m/leanstral-1-5/
- Closed weights; access is hosted only. Licence: Mistral Premier.

## What stands out

- Low-latency fill-in-the-middle: Specialized for high-frequency FIM/autocomplete with a dedicated FIM endpoint, plus predicted outputs. Source: https://docs.mistral.ai/models/model-cards/codestral-25-08
- Predicted outputs and prefix mode: Supports predicted outputs (fast edits of known code) and assistant prefix, plus function calling and structured outputs. Source: https://docs.mistral.ai/models/model-cards/codestral-25-08

## Notes

Alias codestral-latest. Mistral's current code-completion model (Premier). OpenRouter lists 256K context; Mistral card says 128K.

IDE autocomplete / FIM and fast code generation.

```bash
curl https://api.mistral.ai/v1/fim/completions -H "Authorization: Bearer $MISTRAL_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"codestral-2508","prompt":"def fib(n):","suffix":"\nprint(fib(10))"}'
```

Sources: https://docs.mistral.ai/models/model-cards/codestral-25-08

Model page: https://postcutoff.com/m/codestral-2508/