ALAlibaba/ Qwen
Qwen3 VL 30B A3B Thinking
alibaba/qwen3-vl-30b-a3b-thinking
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
Model information
Released
2025-10-06
Context window
262K
Max output
33K
Model parameters
31B
Weights
Open
Modalities
Input
ImageText
Output
Text
Identity
- Version
- qwen3-vl-30b-a3b-thinking
- Knowledge cutoff
- 2025-03-31
- License
- Apache-2.0
Resources
Capabilities
Open weightReasoningStructuredTemperatureTool call
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter | qwen/qwen3-vl-30b-a3b-thinking | openai_chat | 262K | 33K | AttachmentsReasoningTool callStructuredTemperature | Reasoning required, Hugging Face: Qwen/Qwen3-VL-30B-A3B-Thinking | input $0.2/M · output $2.4/M | Yes | ||
| Kilo Gateway | qwen/qwen3-vl-30b-a3b-thinking | openai_chat | 262K | 33K | AttachmentsReasoningTool callStructuredTemperature | - | input $0.2/M · output $2.4/M | Yes | ||
| NovitaAI | qwen/qwen3-vl-30b-a3b-thinking | openai_chat | 262K | 33K | AttachmentsTool callStructuredTemperature | - | input $0.2/M · output $1/M | Yes | ||
| Alibaba | qwen3-vl-30b-a3b-thinking | custom | 262K | 33K | - | - | - | Yes |