Mistral: Codestral 2508

By Mistralai

Released: 2025-08-01

Visit Website

API

LLM

RAG

Mistralai

Paid

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

16 Dec 2025Mistral: Mistral Small Creative

33k tokens context

9 Dec 2025Mistral: Devstral 2 2512 (free)

262k tokens context

9 Dec 2025Mistral: Devstral 2 2512

262k tokens context

2 Dec 2025Mistral: Ministral 3 14B 2512

262k tokens context

2 Dec 2025Mistral: Ministral 3 8B 2512

262k tokens context

2 Dec 2025Mistral: Ministral 3 3B 2512

131k tokens context

1 Dec 2025Mistral: Mistral Large 3 2512

262k tokens context

30 Oct 2025Mistral: Voxtral Small 24B 2507

32k tokens context

13 Aug 2025Mistral: Mistral Medium 3.1

131k tokens context

1 Aug 2025

Mistral: Codestral 2508Current

256k tokens context

10 Jul 2025Mistral: Devstral Medium

131k tokens context

10 Jul 2025Mistral: Devstral Small 1.1

131k tokens context

20 Jun 2025Mistral: Mistral Small 3.2 24B

131k tokens context

7 May 2025Mistral: Mistral Medium 3

131k tokens context

17 Mar 2025Mistral: Mistral Small 3.1 24B (free)

128k tokens context

17 Mar 2025Mistral: Mistral Small 3.1 24B

131k tokens context

17 Feb 2025Mistral: Saba

33k tokens context

30 Jan 2025Mistral: Mistral Small 3

33k tokens context

19 Nov 2024Mistral Large 2411

131k tokens context

19 Nov 2024Mistral Large 2407

131k tokens context

19 Nov 2024Mistral: Pixtral Large 2411

131k tokens context

17 Oct 2024Mistral: Ministral 8B

131k tokens context

17 Oct 2024Mistral: Ministral 3B

131k tokens context

10 Sept 2024Mistral: Pixtral 12B

33k tokens context

19 Jul 2024Mistral: Mistral Nemo

131k tokens context

27 May 2024Mistral: Mistral 7B Instruct

33k tokens context

27 May 2024Mistral: Mistral 7B Instruct v0.3

33k tokens context

17 Apr 2024Mistral: Mixtral 8x22B Instruct

66k tokens context

26 Feb 2024Mistral Large

128k tokens context

10 Jan 2024Mistral Tiny

33k tokens context

28 Dec 2023Mistral: Mistral 7B Instruct v0.2

33k tokens context

10 Dec 2023Mistral: Mixtral 8x7B Instruct

33k tokens context

28 Sept 2023Mistral: 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

Related Tools

FLUX

FLUX, from Black Forest Labs, is a family of high-quality open and commercial image generation models prized for photorealism and prompt adherence. Widely integrated across third-party tools and APIs, it has become a default backbone for image generation.

Claude Opus 5.5

Claude Opus 5.5, launched 22 September 2026, is Anthropic's current Opus-line flagship, replacing Opus 5. It performs at roughly the level of Claude Fable 5.1 on most work while costing 40% less to run than Opus 5, at $4 input / $20 output per million tokens (both 20% down, cache reads cut 60% to $0.20). It leads on Terminal-Bench 4.0, GDPval-AA v2.1 and Humanity's Last Exam, and is the first Opus model to ship with Fable-5.1-class cybersecurity, biology and distillation safeguards.

Claude Sonnet 5.5

Claude Sonnet 5.5, released 28 September 2026, is the second model in Anthropic's Claude 5.5 family and the faster, lower-cost complement to Claude Opus 5.5. It keeps Sonnet 5's $2 input / $10 output per million tokens ($0.20 cache reads) while generating output over 30% faster, and scores 70.6% on Terminal-Bench 4.0, above Opus 5.5's 66.4%. It has a 1M-token context window, 128K max output, adaptive thinking, and is the first Sonnet with cyber and anti-distillation classifiers.