All Models
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...
Available Providers (3)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Kilo Gateway | qwen/qwen3-30b-a3b-thinking-2507 | $0.05/MTok | $0.34/MTok | 32.8K | 6.6K | |
 SiliconFlow (China) | Qwen/Qwen3-30B-A3B-Thinking-2507 | $0.09/MTok | $0.30/MTok | 262K | 131K | |
 SiliconFlow | Qwen/Qwen3-30B-A3B-Thinking-2507 | $0.09/MTok | $0.30/MTok | 262K | 131K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output