Mistral Devstral Medium is cheaper than GPT-5.1-Codex-Mini at $0.4/M vs $1.5/M input tokens.
| Spec | Mistral Devstral Medium | GPT-5.1-Codex-Mini |
|---|---|---|
| Input price | $0.4/M tokens | $1.5/M tokens |
| Output price | $2/M tokens | $6/M tokens |
| Context window | — | 400K tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Jul 2025 | Nov 2025 |
Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: bigger model tier, newer, bigger context window, major provider backing.
Mistral Devstral Medium costs 3.0x less per token.
Mistral Devstral Medium is cheaper on both: 3.8× input, 3.0× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 8 Sep 2026.
Mistral Devstral Medium uses 5.1x more transitions