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)
With CoreAI, you can start chatting with Mistral: Codestral 2508 (batch) instantly — no separate subscription needed. CoreAI lets you chat with Mistral: Codestral 2508 (batch) alongside 300+ other AI models from Mistral AI and other providers like OpenAI, Anthropic, Google, Meta, and more.
Mistral: Codestral 2508 (batch) holds the #204 spot for context size out of 371 chat models in the CoreAI catalog — 256K tokens, roughly 192,000 words or 384 pages of text in a single conversation. On price, it is the #102 cheapest of 120 budget-tier models by input cost. It joined the catalog on 2025-08-01.
Every model in this table is available on CoreAI — open the web app and run the same prompt through Mistral: Codestral 2508 (batch) and Mistral: Codestral 2508 side by side to judge with your own eyes.
A typical question (about 1,000 tokens in, 500 out) runs $0.00075 on Mistral: Codestral 2508 (batch)'s raw per-token rates; a heavy session with a 50K-token document costs about $0.019. On CoreAI you don't juggle these numbers — one subscription covers Mistral: Codestral 2508 (batch) and 300+ other models under a plan usage limit, with no API keys. See plans.
Mistral: Codestral 2508 (batch) handles 256K tokens of context — roughly 192,000 words, or about 384 pages of text in one conversation.
Mistral: Codestral 2508 (batch)'s underlying rates are $0.3 per 1M input tokens and $0.9 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.
No — Mistral: Codestral 2508 (batch) is text-only. If you need image understanding, its budget-tier peers with vision are listed in the comparison table above.
No — Mistral: Codestral 2508 (batch) answers directly without an extended reasoning phase, which usually means faster responses.
Open the CoreAI web app or the iOS/Android app, pick Mistral: Codestral 2508 (batch) in the model selector, and chat — no API key, no per-token billing. One subscription covers Mistral: Codestral 2508 (batch) and 300+ other models.
The closest alternatives on CoreAI are Mistral: Codestral 2508, Kwaipilot: KAT-Coder-Air V2.5, IBM: Granite 4.0 Micro — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.
Chat with Mistral: Codestral 2508 (batch) and 300+ other AI models — all in one app.