Codestral

Available

A Mistral AI model with a 128K-token context window and tool calling. On the Mistral API since July 30, 2025.

Access details: Mistral API

The model ID to use in API requests.

codestral-2508

Updated Sep 23, 2026

Sources & notes

Capabilities & limits

Context window: 128K
Maximum output: Not published
Image input: Unsupported
Tool calling: Supported
Structured output: Supported

Pricing

USD / 1M tokens

Input: $0.30
Output: $0.90

Standard rates per million tokens. Discounts and long-context rates, where offered, are on Mistral AI's pricing page.

Full rate card 3 rates

All prices in USD.

Standard input

$0.30 per 1M tokens

Cached input

$0.03 per 1M tokens

Standard output

$0.90 per 1M tokens

Batch processing is billed at a 50% discount. Regional inference is billed at 1.1x standard list pricing for input, output, cached reads and cache writes. Priority Tier is an entitlement; the docs pricing page's Standard tab is recorded here.

Price history

Sep 13, 2026

Input $0.30 per million tokens

Sep 23, 2026

Input $0.30 per million tokens

Sep 13, 2026

Output $0.90 per million tokens

Sep 23, 2026

Output $0.90 per million tokens

Technical details

Parameters: Not published
Active parameters: Not published
Architecture: Not published
Training / knowledge cutoff: Not published
Input modalities: Text
Output modalities: Text

From Mistral AI

Official announcement ↗

Release & lifecycle

First available: Jul 30, 2025
available: As of Sep 23, 2026