Qwen2.5-VL 72B, not served here yet
Qwen2.5-VL 72B is Alibaba's 72B vision-language model: it reads text, charts and layouts in images and returns structured output, including object coordinates as JSON. OpenRelay does not serve it yet; tell us if you want it.
- Text and image in, text out
- Not served yet
- No public rate
Not served yet.
GET /v1/models lists Qwen2.5-VL 72B with status request_access, but nothing serves it: there is no backend behind the id and no public rate. A request tells us someone wants it.
openrelay/qwen2.5-vl-72bTell us you want Qwen2.5-VL 72B
Leave a work email. We email you if we start serving it, and nothing else goes to this list.
The spec sheet.
What Alibaba has published about the model, with the source on each row.
- On OpenRelay
- openrelay/qwen2.5-vl-72b: Text and image in, text out. Listed with status request_access, not served. GET /v1/models
- Parameters
- 72B, instruction-tuned Qwen model card
- Vision
- Reads text, charts, icons, graphics and layouts within images Qwen model card
- Localization
- Bounding boxes or points for objects, with stable JSON for coordinates and attributes Qwen model card
- Documents
- Structured output from scans of invoices, forms and tables Qwen model card
- License
- Qwen license (custom terms) Qwen model card
Qwen2.5-VL 72B, answered.
Can I call Qwen2.5-VL 72B through OpenRelay?
Not today. openrelay/qwen2.5-vl-72b appears on GET /v1/models with status request_access, but nothing serves it: a chat completions call returns 403 model_access_required. The form on this page tells us you want it.
What can it return besides text?
Coordinates. Qwen's model card describes bounding boxes or points for objects in an image, with JSON for coordinates and attributes, and structured output from invoices, forms and tables.