VisionMultilingualGeneral
Qwen3-VL 30B
Vision and OCR inference for document and image understanding.
qwen3-vl-30bDesigned for your workflow
From input to useful output.
InputText & images
ModelQwen3-VL 30B
OutputText & structured answers
Explore these use cases
- 01Document & invoice understanding
- 02Chart interpretation
- 03Image descriptions
Model capabilities
Published catalog- Context window
- 33K
- Maximum output
- 4K
- Serving region
- Thailand · TH
- Streaming
- Supported
- Tool use
- Not listed
- Structured output
- Supported
- Reasoning
- Not listed
Catalog specifications describe the model configuration. Check service status before sending requests.
Build with this model
Send text and image content through the chat-completions endpoint. Review the vision example in the documentation for image formatting.
- API base URL
https://b300.powerchampion.ai/v1- Endpoint
- POST
/v1/chat/completions - Authentication
Authorization: Bearer YOUR_API_KEY