Mistral AI
Mistral: Codestral 2508
mistralai/codestral-2508
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
Input
$0.3
/ 1M tokens
Output
$0.9
/ 1M tokens
Context window
256K
tokens
Limits
Context
256,000
tokens
Max output
204,800
80% of the context window
Model facts
Author
Mistral AI
Tokenizer
Mistral
Modality
Text + File -> Text
Knowledge cutoff
2025-03-31
Created
Aug 1, 2025
Default generation parameters
temperature
0.3
Publication status
Hugging Face: unavailableLicense: not publishedParameter count: not published
Modalities
Input · TextInput · FileOutput · Text
Generation controls
Frequency penaltyMax tokensPredictionPresence penaltyResponse formatSeedStopStructured outputsTemperatureTool choiceToolsTop p
Creative tasks
Category performance
UI components
Top 87%1016 Elo
46.7% win
3D
Top 85%1020 Elo
45.4% win
Data visualization
Top 89%1019 Elo
41.1% win
Code
Top 91%1009 Elo
38.5% win
Websites
Top 89%1014 Elo
37.8% win
Games
Top 94%969 Elo
36.3% win