Codestral 2508
mistralai/codestral-2508
Mistral: Codestral 2508 is a text and file input, text output model. It has a context length of 256,000 tokens and supports tool use. The price is $0.30 per million input tokens and $0.90 per million output tokens.
- tool use
- structured outputs
At a glance
Specifications
What the API gives you
- Context window
- 256K tokens
- Max output
- 205K tokens
- Input price
- $0.30 / 1M tokens
- Output price
- $0.90 / 1M tokens
- Cache read
- $0.030 / 1M tokens
- Modalities
- text, file → text
- Knowledge cutoff
- Mar 31, 2025
- Released
- Jul 30, 2025
Measured evidence
Public benchmark record
- Design Arena Coding
- 835 Elo2026-10-21
- Design Arena UI
- 851 Elo2026-10-21
- Design Arena Website
- 809 Elo2026-10-21
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Frontend & UIProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 6 of 6 configured evaluation feeds currently have results.
- Best LLM for CodingProvisional evidence
16% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 7 of 7 configured evaluation feeds currently have results.
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.