All Models
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 (5)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 ModelScope | Qwen/Qwen3-30B-A3B-Thinking-2507 | $0/MTok | $0/MTok | 262.1K | 32.8K | |
 OpenRouter | qwen/qwen3-30b-a3b-thinking-2507 | $0.08/MTok | $0.40/MTok | 131.1K | 131.1K | |
 LLM Gateway | qwen3-30b-a3b-thinking-2507 | $0.10/MTok | $0.10/MTok | 131.1K | 8.2K | |
 Clarifai | qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507 | $0.36/MTok | $1.30/MTok | 262.1K | 131.1K | |
 Qiniu | qwen3-30b-a3b-thinking-2507 | —/MTok | —/MTok | 126K | 32K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output