Codestral
Mistral AICode Models
86.2
Performance
★ 4.6
Rating
289
Reviews
ReasoningSmallCode AssistantProprietary
About
Mistral AI's dedicated code generation model optimized for code completion, generation, and debugging across 80+ programming languages.
Strengths
Among the top models for code completion and generation on HumanEval. Optimized for IDE integration with fill-in-the-middle support. Supports 80+ programming languages. Fast inference for real-time coding assistance.
Specifications
- Context window
- 32,000
- Parameters
- —
Pricing
- Input cost
- $0.20 / 1M
- Output cost
- $0.60 / 1M
$0.20 input / $0.60 output per 1M tokens
Speed & Latency
- 130
- tokens/sec
- 150ms
- time to first token
- 300 RPM
- rate limits
Available On
Mistral APIHuggingFaceVS CodeJetBrains
Features
code completionfill in the middlestreamingmulti language
Performance Trend
Benchmark score trends over time for the top 5 benchmarks.
Loading history...
Benchmarks
Scores from various benchmark tests; higher is better.
