Hunyuan 3D Rapid
tencent-hunyuan-3d-rapid
Tencent Hunyuan 3D Rapid supports fast 3D asset generation from text or images, with a lightweight parameter surface, PBR material switch, and multiple export formats.
Endpoints
Section titled “Endpoints”POST /v1/queue/tencent-hunyuan-3d-rapid # Create taskGET /v1/queue/tencent-hunyuan-3d-rapid/requests/{request_id}/status # Check statusGET /v1/queue/tencent-hunyuan-3d-rapid/requests/{request_id}/response # Get resultPUT /v1/queue/tencent-hunyuan-3d-rapid/requests/{request_id}/cancel # Cancel taskRequest parameters
Section titled “Request parameters”curl --location "https://odirouter.ai/model/v1/queue/tencent-hunyuan-3d-rapid" \ --header "Authorization: Bearer YOUR_API_KEY" \ --header "Content-Type: application/json" \ --data '{ "image_base64": "data:image/png;base64,BASE64_IMAGE_DATA", "result_format": "GLB", "enable_pbr": false }'Text-to-3D prompt. Exactly one of prompt, image_url, and image_base64 can be provided.
Maximum length: 200 UTF-8 characters
Base64 encoded input image. Exactly one of prompt, image_url, and image_base64 can be provided.
Both a data URI, such as data:image/png;base64,..., and raw Base64 image data are accepted.
Supported formats: jpg, png, jpeg, webp
Resolution: each side must be between 128 and 5000 pixels
Publicly accessible input image URL. Exactly one of prompt, image_url, and image_base64 can be provided.
Prefer image_base64 when possible because upstream image downloads can fail if Tencent cannot fetch the URL.
Supported formats: jpg, png, jpeg, webp
Resolution: each side must be between 128 and 5000 pixels
Target export format for the generated 3D asset or preview output. Tencent Cloud Rapid notes that selecting USDZ, MP4, or GIF may time out, and recommends input models below 500K faces.
OdiRouter supports GLB and OBJ outputs.
Options: OBJ, GLB, STL, USDZ, FBX, MP4, GIF
Whether to generate PBR materials for the output asset.
Options: true, false
Response parameters
Section titled “Response parameters”Final 3D asset URLs may use a .bin file name. Use the output metadata, such as metadata.format, to identify the actual model format.
{ "request_id": "mmsu_01hxyz...", "response_url": "https://odirouter.ai/model/v1/queue/tencent-hunyuan-3d-rapid/requests/mmsu_01hxyz.../response", "status_url": "https://odirouter.ai/model/v1/queue/tencent-hunyuan-3d-rapid/requests/mmsu_01hxyz.../status", "cancel_url": "https://odirouter.ai/model/v1/queue/tencent-hunyuan-3d-rapid/requests/mmsu_01hxyz.../cancel", "queue_position": 0}| Field | Type | Description |
|---|---|---|
request_id | string | Task ID used for all follow-up operations. |
response_url | string | URL to fetch the final result. |
status_url | string | URL to query task status. |
cancel_url | string | URL to cancel the task. |
queue_position | int | Current queue position. |