MiniMax M2.5 vs GPT-5.1-Codex
MiniMax M2.5 is cheaper on output tokens, while GPT-5.1-Codex offers a larger context window. Choose MiniMax M2.5 or GPT-5.1-Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | MiniMax M2.5 | GPT-5.1-Codex |
|---|---|---|
| Provider | MiniMax | OpenAI |
| Input / 1M tokens | $0.27 | $1.25 |
| Output / 1M tokens | $0.95 | $10.00 |
| Context window | 205K | 400K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Feb 2026 | Nov 2025 |
| LiveBench score | 60.3 | 69.3 |
| SWE-bench Verified score | 75.8 | 66.0 |
| Epoch Capabilities Index score | 147 | — |
| LMArena (Chatbot Arena) Elo score | 1359 | — |
| LMArena WebDev Elo score | 1386 | 1337 |
FAQ
Is MiniMax M2.5 or GPT-5.1-Codex cheaper?
MiniMax M2.5 is cheaper on output tokens ($0.95 vs $10.00 per 1M).
Which has the larger context window, MiniMax M2.5 or GPT-5.1-Codex?
GPT-5.1-Codex 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.