Codestral 2508 (batch)

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)

ChatMistral256k tokens$0.327 / $0.9811 · 1M

mistralai/codestral-2508:batch

Context
256k tokens
Completion cap
204,800
Tools
Yes
JSON
Yes
Released
2025-08-01

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/codestral-2508:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Codestral 2508 (batch)?
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) Codestral 2508 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: mistralai/codestral-2508:batch.
Is Codestral 2508 (batch) free?
No. Input is $0.327 per 1M tokens and output is $0.9811 per 1M tokens on Geek Hub (markup included).
What is the context length of Codestral 2508 (batch)?
Codestral 2508 (batch) has a 256k tokens context window. It supports up to 204,800 completion tokens.
Does Codestral 2508 (batch) support tool calling and structured outputs?
Codestral 2508 (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Codestral 2508 (batch) released?
Codestral 2508 (batch) was released on 2025-08-01.

More models from Mistral