Codestral 2508

mistralai/codestral-2508

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)

InputFileText
OutputText
Input / Outputclub$0.318 / $0.954per 1M tokens · USD
Context window256Ktoken
Maximum output204.8Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.318/ 1M token
Cache readUS$0.0318/ 1M token
OutputUS$0.954/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
FileText
Output
Text
Context window
256,000 token
Maximum output
204,800 token

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is Codestral 2508, and who develops it?

Codestral 2508 is a model from mistralai. Its model ID on Vecbase is mistralai/codestral-2508. 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)

How much does Codestral 2508 cost on Vecbase?

For Codestral 2508, the Club plan lists USD 0.318 per 1 million input tokens and USD 0.954 per 1 million output tokens, as of 10/23/2026, 8:48:41 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in Codestral 2508’s context window?

Codestral 2508 has a context window of 256,000 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for Codestral 2508?

Codestral 2508 can generate up to 204,800 tokens per response. Your API or request settings may set a lower limit.

Can Codestral 2508 call tools in an agent workflow?

Yes. Codestral 2508 supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does Codestral 2508 support structured outputs?

Yes. Codestral 2508 supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does Codestral 2508 support?

Codestral 2508 accepts File and Text and produces Text.

Which providers make Codestral 2508 available through Vecbase?

Vecbase offers Codestral 2508 through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request Codestral 2508?

Use mistralai/codestral-2508 as the model identifier for Codestral 2508. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

What does an agent need to access Codestral 2508 through Vecbase?

To use Codestral 2508, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for Codestral 2508?

We do not yet have a confirmed release date for Codestral 2508.

Which models can I compare with Codestral 2508 on Vecbase?

You can compare Codestral 2508 with Devstral 2 2512 (mistralai/devstral-2512), Ministral 3 14B 2512 (mistralai/ministral-14b-2512), and Ministral 3 3B 2512 (mistralai/ministral-3b-2512). Check their capabilities and prices to find the best fit for your task.