qwen/qwen3-30b-a3b-thinking-2507
Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| AtlasCloudfp8 | $0.080 | $0.400 | 131K | 100% |
| Alibaba | $0.130 | $1.56 | 82K | — |
Qwen3 30B A3B Thinking 2507 costs $0.080 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 39th cheapest of 298 paid models.
Qwen3 30B A3B Thinking 2507 scores 22.4 on the Artificial Analysis Intelligence Index, ranking 111th of 180 benchmarked models, with a GPQA Diamond score of 71%.
Qwen3 30B A3B Thinking 2507 generates around 134 tokens per second with 499ms time-to-first-token (p50), the 34th fastest tracked model.
Qwen3 30B A3B Thinking 2507 supports a 131K-token context window and can output up to 131K tokens. It accepts text input.