Mistral AI

Codestral 2508

mistralai/codestral-2508

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Codestral 2508

tools

Mistral AI mistralai/codestral-2508

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)

Input $/1M: $0.30
Output $/1M: $0.90
Context: 256K
Max output: 205K
Released: Aug 1, 2025
Modalities: textfile

Cached input reads $0.03 per 1M

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Codestral 2508
targets:
  - id: codestral-2508
    kind: llm
    name: Codestral 2508
    metadata:
      model: mistralai/codestral-2508          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 256000
    cost:
      usd_per_1k_tokens: 0.000600

Price among Mistral AI models

Input list price per million tokens; Codestral 2508 is the 7th cheapest of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.