Part of 786+ curated AI tools on AISO
Codestral 25.08 logo

Codestral 25.08

Mistral's low-latency code completion model — FIM, 80+ languages, 256k context

0
paidDR 86Premier (proprietary) model. API pricing: $0.3/M input tokens, $0.9/M output tokens. Access via Mistral La Plateforme API. No open-weights release — API only. Free tier available on mistral.ai for limited personal use.View full pricing →

Visit Codestral 25.08

https://mistral.ai/news/codestral-25-08

About Codestral 25.08

Mistral's dedicated code completion model, updated August 2025. Optimized for low-latency, high-frequency coding tasks — fill-in-the-middle (FIM), inline completion, code correction, and test generation. Supports 80+ programming languages. 256k context window. API: $0.3/M input, $0.9/M output. Integrates natively with VS Code, JetBrains, Jupyter, neovim, and Emacs.

Key Features

Fill-in-the-middle (FIM) support for inline IDE code completion
256k token context window for large codebases
80+ programming language support
Low-latency inference optimized for real-time completion
Code correction and bug-fix generation
Test generation from function signatures and docstrings
Native integrations: VS Code (Continue.dev), JetBrains, Jupyter, neovim, Emacs
Model ID: codestral-latest / codestral-25-08
$0.3/M input · $0.9/M output
Successor to Codestral 25.01 with improved FIM accuracy and multi-language performance

Codestral 25.08 Pros & Cons

Pros

  • +Purpose-built for code completion: FIM support is first-class, not bolted on to a general model
  • +256k context window handles large files and multi-file code sessions without chunking
  • +Low-latency design makes it viable for real-time keystroke-level IDE completion
  • +Wide language support (80+) covers mainstream and niche languages without switching models
  • +IDE integrations (VS Code, JetBrains, Jupyter) lower the barrier to adoption
  • +$0.3/M input is significantly cheaper than general-purpose frontier models for high-volume completion workloads

⚠️ Cons

  • Premier (proprietary) model — no open weights, no self-hosting option
  • Coding-only: not suitable for general reasoning, chat, or multimodal tasks
  • Mistral hasn't published detailed benchmark comparisons vs Codestral 25.01 on release notes
  • For agentic software engineering (multi-step tasks), Devstral 2 is a better fit than Codestral

Who Is Codestral 25.08 Best For?

👤Developers building IDE plugins or editor extensions that need real-time code completion
👤Teams replacing GitHub Copilot with a self-managed API integration
👤High-volume code completion pipelines where per-token cost matters
👤Polyglot projects that span many languages and need consistent completion quality across all of them

Tags

mistralllmapicodingcode-completionfill-in-the-middleidedeveloper-tools
🏷️

Is this your tool?

Claim your listing to get a Featured badge, edit your description, and stand out from competitors. All plans include a permanent dofollow backlink to your site.

Claim Now →

📬 Get the best new AI tools delivered weekly

One concise email with fresh launches, trending picks, and featured standouts.

Alternatives to Codestral 25.08

View all Codestral 25.08 alternatives →