MiniMax M2.5 is cheaper than Qwen3 Coder Plus at $0.3/M vs $1/M input tokens.
| Spec | MiniMax M2.5 | Qwen3 Coder Plus |
|---|---|---|
| Input price | $0.3/M tokens | $1/M tokens |
| Output price | $1.2/M tokens | $5/M tokens |
| Context window | 205K tokens | 128K tokens |
| Weights | Open | Closed |
| Free API (OpenRouter) | No | No |
| Released | Feb 2026 | Sep 2025 |
| SWE-bench Verified | 80.2% | 69.6% |
Not enough votes to call it. On the specs, MiniMax M2.5 has the edge: newer, bigger context window.
MiniMax M2.5 costs 4.2x less per token.
MiniMax M2.5 is cheaper on both: 3.3× input, 4.2× output.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Qwen3 Coder Plus uses 8.0x more emoji