Codestral

mistral

Our cutting-edge language model for coding released August 2025.

Try Now

Capabilities

Tool Use

PDF Input

Example Use Cases

Code completion or fill-in-the-middle needed

Low-latency code generation

Code correction or test generation

Technical Specifications

Context Window

256,000 tokens

Max Output

256,000 tokens

Cache Miss Cost

$0.30 per 1M tokens

Non-Reasoning Cost

$0.90 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus