Codestral 2508 is a code model created by Mistral that takes in and outputs text. It is an open-source model designed for tasks involving code generation and software engineering.
Input
Output
Context
256K
Max Output
256K
Parameters
-
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
Codestral 2508 has a context window of 256,000 tokens and a maximum output of 256,000 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Codestral 2508 is an open-weight model under the Mistral AI Non Production License license. You can download and self-host it within the license terms.
Mistral has not published a parameter count for Codestral 2508. The catalog does not estimate undisclosed sizes.
Strengths: 256K token context window. Each is computed from the model's stated facts and benchmark results.
Codestral 2508 accepts Text and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Codestral 2508 yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Codestral 2508, and Inferbase runs it on your account with the same routing and logs.
Mistral has not published a parameter count for Codestral 2508, so the catalog cannot compute its memory. The GPU planner can size it from a count you enter.
Start on the free plan with 5,000 requests a month, no card required.