Last updated: 16/04/2025

MistralOfficial Docs

Codestral

codestral-2411-rc5

active

Codestral

Codestral is a cutting-edge language model for coding, specializing in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction, and test generation. With a context window of 262,144 tokens, Codestral is a powerful tool for developers and engineers.

Supports a 262,144 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications. Supports tool use for advanced automation. Capable of generating structured output formats.

Additional Information

Notes

Context length of 262,144 tokens. Has aliases including codestral-2501, codestral-latest, and codestral-2412.

Model Timeline

Launch Date

11/1/2024

Last Updated

11/1/2024

Capabilities

Text

Input Pricing

$-/ KTok

Context: 262,144 tokens

Output Pricing

$-/ KTok

Max tokens: 262,144

Embeddings

Embeddings Pricing

$0.10/1k tokens

Additional Model Information

Tool Use

Yes

Structured Output

Yes

Reasoning

Yes

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop