mistralai
Mistral: Codestral 2508
mistralai/codestral-2508
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
mistralai/codestral-2508 is Mistral’s code-focused model, listed by OpenRouter for text and file inputs with text output and a large context window. Mistral presents Codestral 25.08 as optimized for fill-in-the-middle completion, code correction, test generation, and chat-based coding. Vendor-reported validation cites gains in accepted completions, retained suggestions, fewer runaway outputs, and improved FIM results, while OpenRouter’s design-arena data provides the only external measurements included in this pack.[1][2]
Strengths
- OpenRouter lists text and file inputs, text output, a large context window, tool calling, and structured-output controls.[1]
- Mistral positions the model for fast fill-in-the-middle completion, code repair, test drafting, and coding chat across many languages and tasks.[1][2]
- Mistral reports higher completion acceptance and retained code, fewer runaway outputs, better FIM results, and support for cloud, VPC, or on-prem deployment.[2]
Limitations
- No independent model card or broad coding benchmark was supplied; most capability and improvement claims come from Mistral or OpenRouter’s catalog.[1][2]
- OpenRouter’s supplied arena measurements cover design-oriented categories only, so they do not establish broader coding performance.[1]
- License terms, safety behavior, and hardware requirements are not specified; validate the intended workload and deployment before adoption.[1][2]
Where to use it
- Evaluate for latency-sensitive IDE autocomplete and multi-line fill-in-the-middle suggestions.[1][2]
- Pilot for code repair and test drafting where generated changes remain under human review.[1][2]
- Consider for organizations that need cloud, VPC, or on-prem coding assistance, after confirming licensing and operational fit.[2]
Sources
- [1] OpenRouter catalog · Mistral: Codestral 2508Sources checked: Nov 13, 2026
- [2] Model documentation · Mistral: Codestral 2508Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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)
Specifications
- Model ID
- mistralai/codestral-2508
- Creator
- mistralai
- Added to OpenRouter
- 01.08.2025
- Context length
- 256,000
- Modality
- text+file->text
- Input modalities
- text, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.300 / out $0.900
- Knowledge cutoff
- 31.03.2025
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | input: file |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Design Arena | models · codecategorieswin rate 38.5% · rank 130 | 998Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 41.1% · rank 117 | 1,015Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 36.3% · rank 132 | 958Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 46.7% · rank 122 | 1,008Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 37.8% · rank 134 | 1,006Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 45.4% · rank 118 | 1,003Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | 256,000 | $0.300 | $0.900 | — | — | 100% |
| Mistral | 256,000 | $0.330 | $0.990 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.