Tencent Hunyuan Image · 3D · Image
Tencent Hunyuan Image · 3D · Introduction
Tencent Hunyuan image (3.5 Preview / 3.0, default output only, ≤3 reference images), Hunyuan World panorama (7680x3840, per call) and Hunyuan 3D (full asset / geometry, per call). Same endpoint as Hunyuan video; just use the matching sub-model.
How to call
- Submit:
POST /api/cqt/generator/hunyuan, returns a taskId. - Query:
GET /api/cqt/info/hunyuan?id=taskId, poll until status = succeeded.
Capability map
POSTText to ImageNEW
Generate images from a text description.
POSTReference to ImageNEW
Generate new images based on the subjects / style of reference images (image-to-image / multi-reference).
POSTPanoramaNEW
Hunyuan World panorama: generate a 7680x3840 360° panorama from text.
POST3D Model GenerationNEW
Generate a 3D model (GLB / OBJ / FBX files + preview images) from a text prompt or a single reference image.
💰 See the pricing page for prices →
Common Errors
| Code | msg | Meaning | How to fix |
|---|---|---|---|
| 400 | model must be one of: [...] | model is not a sub-model of this channel | Use a model from the sub-model table |
| 400 | <model> does not support ... / does not accept ... | The sub-model does not support this mode / resolution / parameter (e.g. resolution sent to a default-output-only model) | Adjust per the table; the error lists the supported tiers |
| 400 | at most N imageUrls allowed / numImages must be between 1 and N | Too many reference images or images requested | Reduce per the table |
| 500 | generation_failed | Generation failed; data.errorMsg has details (credits auto-refunded) | Adjust based on the error and retry; contact support if it persists |
Errors are returned as a bizCode, e.g. bizCode=451, msg=prompt_unsafe.
Tip: after saving your API Key via Authorize, every capability page supports "Try it".