AI Tools Review

Mistral: Codestral 2508

By Mistralai

Released: 2025-08-01

API
LLM
RAG
Mistralai
Paid
New

Mistralai Codestral 2508, developed by Mistral AI, features 256k-token context window. 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) Available at $0.3/1M tokens.

Visit Mistral: Codestral 2508

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

Mistralai Model Timeline

Mistral: Mistral Small Creative

33k tokens context

Mistral: Devstral 2 2512 (free)

262k tokens context

Mistral: Devstral 2 2512

262k tokens context

Mistral: Ministral 3 14B 2512

262k tokens context

Mistral: Ministral 3 8B 2512

262k tokens context

Mistral: Ministral 3 3B 2512

131k tokens context

Mistral: Mistral Large 3 2512

262k tokens context

Mistral: Voxtral Small 24B 2507

32k tokens context

Mistral: Mistral Medium 3.1

131k tokens context

Mistral: Codestral 2508Current

256k tokens context

Mistral: Devstral Medium

131k tokens context

Mistral: Devstral Small 1.1

131k tokens context

Mistral: Mistral Small 3.2 24B

131k tokens context

Mistral: Mistral Medium 3

131k tokens context

Mistral: Mistral Small 3.1 24B (free)

128k tokens context

Mistral: Mistral Small 3.1 24B

131k tokens context

Mistral: Saba

33k tokens context

Mistral: Mistral Small 3

33k tokens context

Mistral Large 2411

131k tokens context

Mistral Large 2407

131k tokens context

Mistral: Pixtral Large 2411

131k tokens context

Mistral: Ministral 8B

131k tokens context

Mistral: Ministral 3B

131k tokens context

Mistral: Pixtral 12B

33k tokens context

Mistral: Mistral Nemo

131k tokens context

Mistral: Mistral 7B Instruct

33k tokens context

Mistral: Mistral 7B Instruct v0.3

33k tokens context

Mistral: Mixtral 8x22B Instruct

66k tokens context

Mistral Large

128k tokens context

Mistral Tiny

33k tokens context

Mistral: Mistral 7B Instruct v0.2

33k tokens context

Mistral: Mixtral 8x7B Instruct

33k tokens context

Mistral: Mistral 7B Instruct v0.1

3k tokens context

Specifications

pricing$0.30 / $0.90 (per 1M)
context Window256k tokens

AI Evaluation

4.8
Expert Rating
Text4.9/5
Coding4.8/5

Optimized for programming tasks, this model excels at code generation, debugging, and software engineering workflows with solid benchmark performance.

Pros

  • 256k token context window
  • Strong code generation and debugging
  • Optimized for RAG workflows

Cons

  • May lack creative flair
  • API integration required