Plain-English Summary
A unified Qwen model for understanding images and creating or editing visual content.
Qwen VLo
A unified Qwen model for understanding images and creating or editing visual content.
Qwen VLo
General LLM
Preview
Open weights: No / not announced
API: Preview
Technical Notes
Preview multimodal model combining vision-language understanding with image generation and editing in one workflow.
Best For
Multimodal creative assistants, visual analysis, iterative image editing
Watch Out For
Preview availability; detailed limits and licensing may change.
Model Specs
- Maker
- Alibaba Cloud / Qwen
- Country
- China
- Family
- Qwen VLo
- Type
- General LLM
- Release date
- 2025-06-26
- Date confidence
- Exact
- Status
- Preview
- Context window
- Varies
- Max output
- Not listed
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Unified vision-language generation model
- Reasoning
- Yes
- Tool calling
- Endpoint dependent
- Structured output
- Limited
- API available
- Preview
- Open weights
- No / not announced
- Self-hostable
- No
- License
- Proprietary preview
- Inputs
- Text, image
- Outputs
- Text, image
- Approx. price
- See provider pricing
- How to access
- Provider website
- Model / API ID
- qwen-vlo
- Knowledge cutoff
- Not publicly disclosed
- Fine-tuning
- Prompting and reference images
- Completeness
- 81 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source