Codestral 2508
codestral-2508Mistral'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) Built by Mistral AI.
Prices updated
Input price
$0.30
per 1M tokens · Standard
Output price
$0.90
per 1M tokens · Standard
Input limit
256K
tokens
Output limit
205K
tokens
Input formats
Output formats
Codestral 2508 price history
2 price records since 9/25/2026
Codestral 2508 cost calculator
$11/month
Standard pricing
Overview
What is Codestral 2508?
Codestral 2508 is a text & reasoning and code & slms model from Mistral AI. 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) Its 256K context window and $0.30 input price make it a candidate for cost-sensitive, high-throughput applications.
Benchmarks
Codestral 2508 benchmarks & speed
How Codestral 2508 scores on standardized evaluations, and where it lands among every model we track.
1011
DesignArena Elo
Latency & design
- DesignArena win rate
- 38.5%
- Design battles judged
- 6,734
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Codestral 2508 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.30
Per 1M tokens
Cached input · Standard
$0.03
Per 1M tokens
Capabilities
Codestral 2508 Tools
Tools available when using Codestral 2508 through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Not supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Strengths and limitations
Strengths
- Low input cost at $0.30 per million tokens suits high-volume workloads.
- 256K context supports large documents, repositories and extended conversations.
- Supports text & reasoning and code & slms workloads in one model.
Limitations
- Generated tokens cost 3× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider