Codestral 2508
Mistral's codestral-2508 is a code-focused AI model capable of tasks such as code completion, generation, and review. It is genuinely best at handling large codebases due to its extensive context window of 256,000 tokens.
Input
Output
Context
256K
Max Output
256K
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
More models by Mistral
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Codestral 2508
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Codestral 2508 advertises a context window of 256,000 tokens, with a maximum output of 256,000 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
Yes. Codestral 2508 is an open-weight model released under the Mistral AI Non Production License license, so the weights can be downloaded and self-hosted within that license's terms.
Codestral 2508 accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Codestral 2508 is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Codestral 2508 is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
Mistral has not published a parameter count for Codestral 2508, so the catalog cannot estimate its memory footprint. The capacity planner can size it from a parameter count you supply.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 21, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.