Context
256K tokens (~128 books)
Input $/1M
$0.30
Output $/1M
$0.90
Type
text
License
Open Source
Benchmarks
0 tested
Data as of
About
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
No benchmark data available yet.
Links
Research
Documentation
Community
Source Code
BenchGecko API
codestral-2508
Specifications
- Typetext
- Context256K tokens (~128 books)
- ReleasedAug 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002
Available On
Share & Export
Frequently Asked Questions
Codestral 2508 is an open-source text AI model by Mistral AI, released in August 2025. Context window: 256K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-10-05
- Codestral 2508 by Mistral AI. Not enough public benchmark scores to rank yet.
- List price $0.30 input · $0.90 output per 1M tokens (as of 2026-10-05).
- Sold by 2 providers (as of 2026-10-05): Mistral $0.30 in / $0.90 out · Mistral $0.33 in / $0.99 out. Every provider
How to cite · data as of 2026-10-05
Codestral 2508 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/codestral-2508
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP