ALAlibaba/ Qwen
Qwen3 30B A3B Thinking 2507
alibaba/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...
Model information
Released
2025-08-28
Context window
82K
Max output
33K
Model parameters
31B
Weights
Open
Modalities
Input
Text
Output
Text
Identity
- Version
- qwen3-30b-a3b-thinking-2507
- Knowledge cutoff
- 2025-06-30
- License
- Apache-2.0
Resources
Capabilities
Open weightReasoningTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3-30b-a3b-thinking-2507 | openai_chat | 82K | 33K | ReasoningTool callStructuredTemperature | Reasoning required, Hugging Face: Qwen/Qwen3-30B-A3B-Thinking-2507 | input $0.2/M · output $2.4/M | Yes | ||
| Kilo Gateway | qwen/qwen3-30b-a3b-thinking-2507 | openai_chat | 82K | 33K | ReasoningTool callTemperature | - | input $0.2/M · output $2.4/M | Yes | ||
| Alibaba | qwen3-30b-a3b-thinking-2507 | custom | 82K | 33K | - | - | - | Yes |