Current code-specialist model for code completion / fill-in-the-middle and generation; named as the non-deprecated replacement for older Codestral versions in the models overview table. Primary source: docs.mistral.ai model card (https://docs.mistral.ai/models/model-cards/codestral-25-08) — verbatim
profile normalized against the 70-model field
Context window· 131K of 10M1%
Max output—
Output speed—
Affordability· $0.90 / Mtok out100%
Capability breadth· 1 of 119%
Capability switches · 1 of 11
Reasoning mode
Tool / function use
Streaming
JSON mode
Structured outputs
Prompt caching
Fine-tuning
Web search
Code execution
Vision input
Audio input
Specifications
Every value carries a primary source and a verification date.