Codestral 2508 Model Specs, Costs & Benchmarks (July 2026)
Codestral 2508, developed by Mistral, features a context window of 256K tokens. The model costs $0.30 per million tokens for input and $0.90 per million tokens for output. It was released on August 1, 2025, and has achieved impressive scores in various benchmarks.
Access Codestral 2508 & 210+ other AI models all in one platformTry Magica for free
Overview
 Codestral 2508 | |
|---|---|
Model Provider The organization behind this AI's development | Mistral |
Input Context Window Maximum input tokens this model can process at once | 256K tokens |
Output Token Limit Maximum output tokens this model can generate at once | Not specified tokens |
Release Date When this model first became publicly available | August 1, 2025 12 months ago August 1st, 2025 |
Knowledge Cutoff Latest training-data date reported by the provider | March 31, 2025 |
Pricing
| Codestral 2508 | |
|---|---|
Input Token Cost Cost per million input tokens | $0.30 per million tokens |
Output Token Cost Cost per million output tokens | $0.90 per million tokens |
Cache Read Cost Cost to reuse cached input tokens | $0.03 per million tokens |
Capabilities & Features
| Codestral 2508 | |
|---|---|
Input Types Supported input formats | textfile |
Output Types Supported output formats | text |
Tokenizer Text encoding system | Mistral |
Key Features Advanced capabilities | ✓ Function Calling✓ Structured Output |
Benchmarks
| Codestral 2508 | |
|---|---|
Best Design Arena Score Highest human-preference Elo score across design arenas | 1,078 Elo (#84 in 3D (45.5% win rate)) |
Compare This Model
See how Codestral 2508 compares with other top models
Compare Codestral 2508 with top models in each category:
🚀Programming
Best models for coding and development
🎨Creative & Roleplay
Models optimized for creative writing
📢Marketing
Content creation and marketing tasks
💻Technology
Technical analysis and explanations
🔬Science
Scientific research and analysis
🌐Translation
Multilingual translation tasks
