curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "hunyuan-3d/v3.1/pro/image-to-3d",
"callback_url": "https://your-domain.com/callback",
"input": {
"image_urls": [
"https://example.com/object-front.png"
],
"generate_type": "Normal",
"enable_pbr": true,
"face_count": 500000
}
}
'{
"code": 200,
"data": {
"task_id": "<string>",
"status": "not_started",
"created_time": "2023-11-07T05:31:56Z"
}
}Hunyuan3D
Hunyuan 3D v3.1
Hunyuan 3D v3.1 Pro and Rapid text-to-3D and image-to-3D generation
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "hunyuan-3d/v3.1/pro/image-to-3d",
"callback_url": "https://your-domain.com/callback",
"input": {
"image_urls": [
"https://example.com/object-front.png"
],
"generate_type": "Normal",
"enable_pbr": true,
"face_count": 500000
}
}
'{
"code": 200,
"data": {
"task_id": "<string>",
"status": "not_started",
"created_time": "2023-11-07T05:31:56Z"
}
}- After submission, a
task_idwill be returned. If you provided acallback_url, when the task status becomesfinishedorfailed, a POST request will be sent to thecallback_url. - Regardless of whether
callback_urlis provided, you can retrieve the result through the unified Query 3D Task Status endpoint.
Hunyuan 3D v3.1
Hunyuan 3D v3.1 supports Pro and Rapid text-to-3D and image-to-3D models through four public model IDs.Available Models
- hunyuan-3d/v3.1/pro/image-to-3d - Generate a Pro 3D model from one front-view image, with optional extra view images
- hunyuan-3d/v3.1/pro/text-to-3d - Generate a Pro 3D model from a text prompt
- hunyuan-3d/v3.1/rapid/text-to-3d - Generate a faster Rapid 3D model from a text prompt
- hunyuan-3d/v3.1/rapid/image-to-3d - Generate a faster Rapid 3D model from one image
Required Parameters
- model: One of the four Hunyuan 3D v3.1 public model IDs
- input.prompt: Required for text-to-3D models
- input.image_urls: Required for image-to-3D models. Use exactly one image URL.
Optional Parameters
- generate_type: Pro models only.
NormalorGeometry - enable_pbr: Enable PBR material generation. Ignored for geometry-only generation
- face_count: Pro models only. Target face count between
40000and1500000; default is500000 - enable_geometry: Rapid models only. Generate a geometry-only white model without textures
- back_image_url, left_image_url, right_image_url, top_image_url, bottom_image_url, left_front_image_url, right_front_image_url: Pro image-to-3D only. Optional extra object views
- callback_url: Optional webhook URL for task completion notification
Pricing
Hunyuan 3D v3.1 is charged per generation. Optional features such as PBR materials, Pro image multi-view inputs, and custom face count may add extra credits when enabled.Output
The task result may include:model_glbor another returned 3D model filethumbnailmodel_urls:glb,obj,mtl,texture, and other formats when available- texture and material files when available
label, file_url, file_type, format, content_type, file_name, and file_size when available.
Notes
- Image-to-3D models accept exactly one required image in
image_urls. - Pro image-to-3D can also accept optional named extra view image URLs.
- The API returns asynchronous task status. Poll the unified 3D task status endpoint or use
callback_url.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json