MiniMax M3 Thinking vs GPT-5.1-Codex-Max
MiniMax M3 Thinking is cheaper on output tokens, while MiniMax M3 Thinking offers a larger context window. Choose MiniMax M3 Thinking or GPT-5.1-Codex-Max based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | MiniMax M3 Thinking | GPT-5.1-Codex-Max |
|---|---|---|
| Provider | NanoGPT | OpenAI |
| Input / 1M tokens | $0.23 | $1.25 |
| Output / 1M tokens | $0.96 | $10.00 |
| Context window | 512K | 400K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Jun 2026 | Nov 2025 |
| LiveBench score | 70.0 | 74.4 |
FAQ
Is MiniMax M3 Thinking or GPT-5.1-Codex-Max cheaper?
MiniMax M3 Thinking is cheaper on output tokens ($0.96 vs $10.00 per 1M).
Which has the larger context window, MiniMax M3 Thinking or GPT-5.1-Codex-Max?
MiniMax M3 Thinking has the larger context window (512K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.