# Mistral AI: Codestral 2508

> Mistral's code model, served directly by Mistral AI from Europe. Built for fast, frequent coding tasks such as code generation, refactoring and explanations, with tool calling, structured output and a 128k context.

- Model ID: `mistralai/codestral-2508`
- Maker: Mistral AI (`mistralai`)
- Context length: 131,072 tokens
- Input: text
- Output: text
- Capabilities: tool calling and structured output
- Price (EUR per 1M tokens): input 0.300876, output 0.902626
- Page: https://tokenlane.de/models/mistralai/codestral-2508

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| Mistral AI | FR, SE, NO, NL, BE | no | no |

## Usage

- Base URL: `https://api.tokenlane.de/v1` (OpenAI- and OpenRouter-compatible)
- Authentication: `Authorization: Bearer $TOKENLANE_API_KEY`
- Guide: https://tokenlane.de/docs/guides/text-and-chat.md?lang=en
- Machine-readable catalogue: `GET https://api.tokenlane.de/v1/models?output_modalities=all` (public, no key)
- Documentation index for agents: https://tokenlane.de/llms.txt

```bash
curl https://api.tokenlane.de/v1/chat/completions \
  -H "Authorization: Bearer $TOKENLANE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/codestral-2508","messages":[{"role":"user","content":"Hello"}]}'
```

_Catalogue snapshot: 2026-11-19T13:10:34.963Z_
