What is the context window of Mistral: Codestral 2508?

Mistral: Codestral 2508 accepts up to 256,000 tokens (256K) of context per request.

How much does Mistral: Codestral 2508 cost per million tokens?

Through Wide Area Intelligence, Mistral: Codestral 2508 costs $0.33 per 1M input tokens and $0.99 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $1.32.

← model directory

mistralai

Mistral: Codestral 2508

Name: Mistral: Codestral 2508
Brand: mistralai
Price: 0.3300 USD

mistralai/codestral-2508

⚙ tool calling

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)

specs & pricing

Type: text
Provider: mistralai
Model ID: mistralai/codestral-2508
Capabilities: tools
Context window: 256K tokens
Input price: $0.33 / 1M tokens
Output price: $0.99 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$1.32

$0.33 for a million input tokens plus $0.99 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

cloud only

Mistral: Codestral 2508 is a hosted model, so it is always served from the cloud. Route easy traffic to an open model on your own hardware and keep this one for the requests that need it.

AI cost calculator →

/// initialize

Call Mistral: Codestral 2508 through one OpenAI-compatible endpoint.

Mix it with open models on your own hardware — the gateway routes each request to the cheapest place that can serve it.

Get an API key Try it in chat

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of Mistral: Codestral 2508?: Mistral: Codestral 2508 accepts up to 256,000 tokens (256K) of context per request.
How much does Mistral: Codestral 2508 cost per million tokens?: Through Wide Area Intelligence, Mistral: Codestral 2508 costs $0.33 per 1M input tokens and $0.99 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $1.32.

More from mistralai

← browse all models