Qwen3 Next 80B A3B Thinking is cheaper than Qwen3 Coder Plus at $0.15/M vs $1/M input tokens.
| Spec | Qwen3 Coder Plus | Qwen3 Next 80B A3B Thinking |
|---|---|---|
| Input price | $1/M tokens | $0.15/M tokens |
| Output price | $5/M tokens | $1.5/M tokens |
| Context window | 128K tokens | 66K tokens |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | Sep 2025 | Sep 2025 |
Not enough votes to call it. On the specs, nothing separates them.
Qwen3 Next 80B A3B Thinking costs 3.3x less per token.
Reviewing agent-written code?See a Brief PR report
Qwen3 Next 80B A3B Thinking is cheaper on both: 6.7× input, 3.3× output.
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
Qwen3 Next 80B A3B Thinking uses 7.9x more emoji