Mistral's dedicated code model. Optimized for code generation, completion, and review across 80+ languages.
Context Window
256K
tokens
Max Output
8K
tokens
Input Price
$0.3
per 1M tokens
Output Price
$0.9
per 1M tokens
Speed
195
tokens/sec
Released
Jan 2025
2025-01-14
Blended Cost
$0.60
per 1M tokens
Value Score
126.7
quality per $
Capabilities
ChatCode GenerationFunction Calling
Benchmarks
Quality Index
76
MMLU Pro
72.1
HumanEval (Coding)
92.5
MATH
67.8
Price vs Quality
Cheaper is left, more capable is up. 6 of 69 priced models are both cheaper and score at least as high. Self-host models are left off the price axis — their cost depends on the hardware you run them on, not on tokens.
Context Window in Context
Amazon Nova Pro300K
Qwen3.8 27B262K
▸ Codestral256K
Nemotron 3 Nano Omni256K
Qwen 3.6 Plus256K
Kimi K2.6256K
Hunyuan Hy3256K
Ling-3.0-Flash256K
Bar length is logarithmic — each full step is 10× the tokens. Shown against the models with the nearest context windows, not the directory extremes.
Codestral is a coding AI model by Mistral AI, released on January 14, 2025. It supports a context window of 256K tokens and can generate up to 8K output tokens.
At $0.3 per million input tokens and $0.9 per million output tokens, its blended cost of $0.60/1M tokens makes it one of the most affordable models available. Its value score of 126.7 reflects the balance of quality and cost.
Using Codestral with Swfte
Access Codestral through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Codestral in our AI Playground before integrating.
Deploy a model with Swfte Connect
One gateway, every provider, per-token cost visibility. Swap models without touching your code.