Mistral: Codestral 2508 (batch)
by Mistral AItext+file->text1 endpoint
Overview
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.
Capabilities
Text generation
Tool use / Function calling
Structured output
Prompt caching
Long context
File input
Top-P sampling
Stop sequences
Deterministic seed
Modalities
Input
TextFile
Output
Text
Technical Specifications
Context Window
256K tokens
Max Output
204.8K tokens
Knowledge Cutoff
2025-03-31
Tokenizer
Mistral
Supported Parameters
frequency_penaltymax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
Pricing
Per 1M tokens
Input$0.15
Output$0.45
Cache read$0.01
Added
August 1, 2025
Last synced 9/16/2026