MMistral · Released Aug 1, 2025
Codestral 2508
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…
- Released
- Aug 1 2025
- Context window
- 256K 205K out
- Input / 1M tokens
- $0.30
- Output / 1M tokens
- $0.90
Where to run it
10 providers compared
Cheapest: Mistral, NanoGPT, Kilo Gateway +4 more at $0.30 / $0.90 per 1M input / output tokens — 27% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Mistral | $0.30 | $0.90 | $0.03 | 256K | 205K | 100%24h | Cheapest |
| NanoGPTno tool calling | $0.30 | $0.90 | $0.15 | 256K | 33K | — | Cheapest |
| Kilo Gateway | $0.30 | $0.90 | $0.03 | 256K | 205K | — | Cheapest |
| LLM Gatewayno tool calling | $0.30 | $0.90 | — | 256K | 256K | — | Cheapest |
| Vertex | $0.30 | $0.90 | — | 128K | 8K | — | Cheapest |
| DevPass (LLM Gateway)no tool calling | $0.30 | $0.90 | — | 256K | 16K | — | Cheapest |
| Eden AI | $0.30 | $0.90 | $0.03 | 256K | 8K | — | Cheapest |
| LowRouter | $0.31 | $0.94 | $0.031 | 128K | 8K | — | +5% |
| Mistraleu | $0.33 | $0.99 | $0.033 | 256K | 205K | 100%24h | +10% |
| Cortecs | $0.37 | $1.10 | $0.037 | 256K | 256K | — | +23% |
| AI/ML API | $0.41 | $1.24 | $0.041 | 256K | 8K | — | +38% |
Value
Price vs. performance
Codestral 2508 Other Mistral Other labs Value frontier · Aider Polyglot vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
1 benchmark score
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Aider PolyglotSoftware engineering · Hard Exercism problems in many languages | 11.1% | #22of 26 | GPT-588.0% |
Specs
Details
- Model ID
mistralai/codestral-2508- Developer
- Mistral
- Release date
- Aug 1, 2025 ·
- Context window
- 256,000 tokens
- Max output
- 204,800 tokens
- API price
- $0.30 / $0.90 per 1M input / output tokens
- Providers
- 10
- Input types
- text, file
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.