Devstral 2 123B Instruct (2512) vs Qwen3 235B A22B Instruct 2507
Devstral 2 123B Instruct (2512) is cheaper on output tokens, while Qwen3 235B A22B Instruct 2507 offers a larger context window. Choose Devstral 2 123B Instruct (2512) or Qwen3 235B A22B Instruct 2507 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Devstral 2 123B Instruct (2512) | Qwen3 235B A22B Instruct 2507 |
|---|---|---|
| Provider | Scaleway | Scaleway |
| Input / 1M tokens | $0.40 | $0.75 |
| Output / 1M tokens | $2.00 | $2.25 |
| Context window | 256K | 260K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Jan 2026 | Jul 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.