Codestral
FrontierMistral AI•Released on 2025-01-14
Mistral's dedicated coding model. SOTA for Fill-in-the-Middle (FIM) use cases. 2x faster code generation than original. 256K context for large codebases. Excellent for autocomplete and code completion.
77
Overall Score
Voice of the community
sample 456“Codestral 25.01 is the clear leader for coding in its weight class. Perfect for IDE autocomplete.”
“For FIM and code completion, nothing beats Codestral at this price point.”
Core Specs
256K
Context Window
33K
Max Output
ReasoningOpen Sourcetext
Pros & Cons
Sentiment75% +18% ·7% −
Pros
- +SOTA for FIM/autocomplete
- +2x faster than original Codestral
- +256K context for large codebases
- +Very affordable ($0.3/$0.9)
- +Optimized for IDE integration
Cons
- −Code-only, not general purpose
- −No multimodal support
- −Not open source (unlike Mistral Large)
- −Less capable for complex reasoning
Pricing
Input (per 1M tokens)$0.30
Output (per 1M tokens)$0.90
Free trial available
Updated on 2026-03-07
Get Started
1Visit the provider's website
2Create an account
3Start using the model
Benchmarks
humanEval86.6%
mbpp78.2%
Reliability
Incidents (30d)0
Mistral API 托管