MiniMax M3 vs MiniMax M3 Thinking
Both have similar output pricing, while MiniMax M3 offers a larger context window. Choose MiniMax M3 or MiniMax M3 Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | MiniMax M3 | MiniMax M3 Thinking |
|---|---|---|
| Provider | MiniMax | NanoGPT |
| Input / 1M tokens | $0.30 | $0.30 |
| Output / 1M tokens | $1.20 | $1.20 |
| Context window | 1M | 512K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Jun 2026 | Jun 2026 |
| LiveBench score | 67.3 | 70.0 |
| LMArena (Chatbot Arena) Elo score | 1433 | — |
| LMArena WebDev Elo score | 1482 | — |
| LMArena Vision Elo score | 1253 | — |
| GPQA Diamond score | 90.9 | — |
| Epoch Capabilities Index score | 147 | — |
FAQ
Is MiniMax M3 or MiniMax M3 Thinking cheaper?
MiniMax M3 and MiniMax M3 Thinking have comparable output pricing.
Which has the larger context window, MiniMax M3 or MiniMax M3 Thinking?
MiniMax M3 has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.