AI models · Mistral AI

Codestral 25.08

Codestral 25.08 came out in July 2025 and does one job: completing code as you type in your editor. It can fill in code in the middle of an existing file (fill-in-the-middle), which is exactly what IDE autocomplete needs. It does not have open weights. For autonomous coding with agents, Mistral's newer general models such as Medium 3.5 are the better choice today.

Strengths

  • A dedicated code completion model with its own fill-in-the-middle endpoint that inserts code between existing lines.
  • Well suited to quick code suggestions in the editor, where fast responses matter.
  • Cheap: $0.30 per million input tokens and $0.90 per million output tokens.

Weaknesses

  • No open weights, it is used under the commercial Mistral Premier license. You normally cannot run it on your own server.
  • Older (July 2025) than Mistral's current general models, which now handle coding agents as well.
  • Its 128K token context window is half that of Medium 3.5 and Small 4.
  • Text only.

Best for

  • code completion in the editor (IDE)
  • quick, low-latency code suggestions

Not ideal for

How to use it in Europe

Codestral is used through the Mistral API, usually via an editor plugin that calls the /v1/fim/completions endpoint. It is available across the EU, and data is processed in the EU by default. The weights are not public, so you normally cannot run it on your own server.

Price compared with similar models

0.3 1 3 10 30 Ministral 3 14B0.2 Llama 4 Scout0.24 Qwen3.8-Flash0.47 Claude Haiku 5.50.5 Nemotron 3.5 Super VL0.5 GPT-6 Luna0.5 GLM-5.3-Flash0.5 Mistral Small 40.6 Llama 4 Maverick0.65 Codestral 25.080.9 Beam 1.01 DeepSeek V4.1 Flash1.2 Muse Glimmer 30B1.2 Mistral Large 31.5 Qwen3.7-Plus1.6 Grok Build 0.12 Gemini 3.5 Flash-Lite2.5 Grok 4.32.5 Qwen3.8-27B3 Gemini 3.8 Flash3.75 DeepSeek V4 Pro3.96 Mistral Large 44.18 Muse Spark 1.34.25 Muse Spark Open4.25 GLM-5.34.4 GPT-6.1 Terra5 Qwen3.8-Max6 Qwen3.8-2.4T-A95B6 Grok 4.76 Mistral Medium 3.57.5 Claude Sonnet 5.510 Gemini 4 Carbon10 Gemini 4 Argon10 Kimi K3.1 Pro10 GPT-6.1 Sol10 Kimi K315 Claude Opus 5.520 Muse Wonder20 Claude Fable 5.150 GPT-6 Astra50
Output price in USD per 1M tokens (log scale). Lighter bars are open-weight models.

More models from this vendor

  • Mistral Large 4: Mistral's largest model, still in preview. Built for demanding tasks, long documents and security analysis with data kept in the EU.
  • Mistral Medium 3.5: Mistral's mid-size open-weight model and the default in the Vibe app. Good for everyday work and coding with data kept in the EU.
  • Mistral Small 4: Mistral's cheap, fast open model under Apache 2.0 for everyday tasks through the API or on your own server.
  • Ministral 3 14B: Mistral's small open model under Apache 2.0 that runs on a single GPU, even without an internet connection.
  • Mistral Large 3: Mistral's previous large model with open weights under Apache 2.0. Cheap in the API and suited to your own powerful server.

Similar models from other vendors

  • Grok Build 0.1 (xAI): A fast Grok coding model and the cheapest Grok on the API, built for agents that write and fix code on their own.
  • GLM-5.3 (Z.ai (Zhipu AI)): Z.ai's open model for agentic coding, also offered through Mistral's European API with data kept in the EU.

Sources

Prices and models change often. The data comes from official vendor pricing pages and documentation, and every page shows when it was last checked. Before a larger purchase, confirm the price with the vendor.

← All AI models

Not sure which model fits your business?

I can help you pick a model and plan based on what you actually need, set it up safely for company data and train your team to use it well. Let’s start with an intro consultation.

See pricing [email protected]