Qwen: Qwen3 30B A3B Thinking 2507
qwen
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...
- Context window
- 131,072 tokens
- Input cost
- $0.08 / 1M
- Output cost
- $0.40 / 1M
- Latency (p50)
- —