Model Price Index
Updated 2026-07-14 · Changelog

Codestral

Mistral

Specialized 22B open-weight model trained for code generation and fill-in-the-middle tasks

$0.30

Input

$0.90

Output

per 1M tokens

Ratesper 1M tokens

Input$0.30
Output$0.90
Cache Read$0.03

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $34.50/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Also routable via OpenRouter at the same list price. OpenRouter adds a 5.5% platform fee on pay-as-you-go credits (verified 2026-07-08).

Specifications

API Model IDcodestral-latest
Context Window256K tokens
Max Output64K tokens
Modalitiestext
Capabilitiestool-use · streaming · json-mode · code

More Mistral Text / Chat Models

Mistral Large 3 · Mistral Medium 3.5 · Mistral Small 4 · Magistral Medium 1.2 · Magistral Small 1.2 · Devstral 2 · Devstral Small 2 · Ministral 3 3B ·