Back to all models
mistralai

Mistral: Codestral 2508 (batch)

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)

mistralai/codestral-2508:batch

Context Size

256K

Input Price

22,500 pts/M1,384 Ks/M

Output Price

67,500 pts/M4,151 Ks/M


Architecture

Text
File

Supported Parameters

frequency_penaltymax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Details

TokenizerMistral
Max Completion204,800 tokens
Provider Context256K tokens
ModeratedNo
CreatedAug 1, 2025