Codestral 2508
Codestral 2508 (Mistral, 2025) is an chat model. 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)
by Mistral · 256K token context window
Best for
- low-latency chat and routing
- request routing and triage
- text classification
Ways to use Codestral 2508 in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Mistral API key. osFoundry discovers Codestral 2508 automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
Codestral 2508 vs similar models
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about Codestral 2508
How much does Codestral 2508 cost?
Codestral 2508 is metered at $ 0.300 /1M for input, and $ 0.900 /1M for output. Bring your own Mistral API key — osFoundry passes through provider pricing without markup.
Can I use Codestral 2508 commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of Codestral 2508?
Codestral 2508 supports a 256K token context window.
Can I run Codestral 2508 locally?
No — Codestral 2508 is hosted only and accessed via the Mistral API.
What is Codestral 2508 best at?
Codestral 2508 is well-suited to low-latency chat and routing, request routing and triage, text classification.
How do I use Codestral 2508 in osFoundry?
Paste your Mistral API key in the key dialog (or deploy the open weights for self-hostable models), assign Codestral 2508 to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Mistral on August 1, 2025. Source: https://openrouter.ai/mistralai/codestral-2508