MiniMax M1 has a larger context window than Qwen3 235B A22B (1.0M tokens vs 33K tokens).
| Spec | MiniMax M1 | Qwen3 235B A22B |
|---|---|---|
| Input price | $0.3/M tokens | — |
| Output price | $1.65/M tokens | — |
| Context window | 1.0M tokens | 33K tokens |
| Parameters | 456B (45.9B active) | 235B (22B Active) |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Jun 2025 | Apr 2025 |
Not enough votes to call it. On the specs, MiniMax M1 has the edge: newer, bigger context window.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Qwen3 235B A22B uses 3.4x more transitions