modelgrep
M

Mistral: Codestral 2508

mistralai/codestral-2508

ToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
1101
3D
Speed
67
116th fastest
Latency
158ms
first token
Input price
$0.300
136th cheapest
Context
256K

How it compares

Faster than63%
of all ranked models
Cheaper than54%
of all ranked models

Overview

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)

Benchmarks

independent · via OpenRouter
Design Arena · Elo3,142 tournaments
3D
1101
UI Component
1074
Data Viz
1062
codecategories
1059
Website
1057
Game Dev
1036

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Mistral$0.300$0.900100%

Specifications

Context window256K
Max output
Knowledge cutoffMar 2025
Input modalitiestext, file
Output modalitiestext
Prompt caching
Cache read price$0.030/M
ModeratedNo

Codestral 2508 FAQ

How much does Codestral 2508 cost?

Codestral 2508 costs $0.300 per million input tokens and $0.900 per million output tokens via OpenRouter, making it 136th cheapest of 298 paid models.

How fast is Codestral 2508?

Codestral 2508 generates around 67 tokens per second with 158ms time-to-first-token (p50), the 116th fastest tracked model.

What is Codestral 2508's context window?

Codestral 2508 supports a 256K-token context window. It accepts text, file input.

Compare head-to-head