Devstral 2 2512 vs GPT-5.1-Codex-Mini
Both have similar output pricing, while GPT-5.1-Codex-Mini offers a larger context window. Choose Devstral 2 2512 or GPT-5.1-Codex-Mini based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Devstral 2 2512 | GPT-5.1-Codex-Mini |
|---|---|---|
| Provider | Mistral | OpenAI |
| Input / 1M tokens | $0.40 | $0.25 |
| Output / 1M tokens | $2.00 | $2.00 |
| Context window | 262K | 400K |
| Parameters | — | — |
| Open weights | — | No |
| Released | — | Nov 2025 |
| LiveBench score | 38.8 | 60.8 |
| LMArena WebDev Elo score | 1196 | 1243 |
FAQ
Is Devstral 2 2512 or GPT-5.1-Codex-Mini cheaper?
Devstral 2 2512 and GPT-5.1-Codex-Mini have comparable output pricing.
Which has the larger context window, Devstral 2 2512 or GPT-5.1-Codex-Mini?
GPT-5.1-Codex-Mini has the larger context window (400K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.