Mistral AIAuto-detectedCodestral 2508
Codestral 2508 is a Mistral AI proprietary model. It is not yet ranked: 1 independent result so far, and the index needs at least five across two categories. At $0.450 per million tokens blended it is cheaper than most ranked models. Output speed of 37 tokens per second puts it in the slowest quarter, with a first token in 0.3 s.
- Blended price
- $0.450/M
- $0.300 in · $0.900 out
- Output speed
- 37 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.29 s
- Context
- 128k
- Reasoning32
Versions
Mistral AI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Codestral 2405 | – | – | – |
| Codestral 2508this page | – | – | – |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| Kagi LLM Benchmark | 32.5%#122 | Kagi LLM Benchmark |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Mistral | 37 tok/s | 0.29 s | $0.300 | $0.900 | 256k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0004 | – | 8.4 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0041 | – | 16.5 s |
| Code edit | 6,000 / 1,500 | $0.0032 | – | 40.8 s |
| Agentic coding session | 60,000 / 4,000 | $0.022 | – | 1.8 min |
| Structured extraction | 2,000 / 200 | $0.0008 | – | 5.7 s |
See also
Data as of 10 Sept 2026. Compare with another model.