About
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
Pricing
Input
$0.30
per 1M tokens
Output
$0.90
per 1M tokens
Blended
$0.45
per 1M tokens
Cheaper than 56% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.45
Monthly
$13.50
vs. Similar Models
Z.ai: GLM 4.6V
$0.450%
GLM-4.6V (Reasoning)
$0.45+0%
MiniMax: MiniMax M2
$0.45-1%
DeepSeek: DeepSeek V3.1 Terminus
$0.44-2%
Performance
Context Window
256K
tokens
Larger than 56% of models
Context Window Comparison
Kwaipilot: KAT-Coder-Pro V2
256KSame
Qwen: Qwen3.5 397B A17B
256KSame
Grok 4
256KSame