Codestral 2508 vs Auto model (Standard)
Codestral 2508 is cheaper on output tokens, while Auto model (Standard) offers a larger context window. Choose Codestral 2508 or Auto model (Standard) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Codestral 2508 | Auto model (Standard) |
|---|---|---|
| Provider | NanoGPT | NanoGPT |
| Input / 1M tokens | $0.30 | $10.00 |
| Output / 1M tokens | $0.90 | $19.99 |
| Context window | 256K | 1M |
| Parameters | — | — |
| Open weights | No | No |
| Released | Aug 2025 | Jun 2024 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.