tencent/hunyuan-3d/v3
Hunyuan 3d V3 is Tencent's image-to-3D AI model. Transform photographs into production-ready 3D meshes with accurate geometry and texture mapping.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runtencent/hunyuan-3d/v3Input Schema
8 parameters · 1 required · 7 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
image | string | Required | URL of image to use while generating the 3D model. |
enable_pbr | boolean | Optional | Whether to enable PBR material generation. Does not take effect when generate_type is Geometry. · Default: false |
face_count | integer | Optional | Target face count. Range: 40000-1500000 · Min: 40000 · Max: 1500000 · Default: 500000 |
polygon_type | string | Optional | Polygon type. Only takes effect when GenerateType is LowPoly. · Options: triangle, quadrilateral · Default: "triangle" trianglequadrilateral |
generate_type | string | Optional | Generation type. Normal: textured model. LowPoly: polygon reduction. Geometry: white model without texture. · Options: Normal, LowPoly, Geometry · Default: "Normal" NormalLowPolyGeometry |
back_image_url | string | Optional | Optional back view image URL for better 3D reconstruction. |
left_image_url | string | Optional | Optional left view image URL for better 3D reconstruction. |
right_image_url | string | Optional | Optional right view image URL for better 3D reconstruction. |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "tencent/hunyuan-3d/v3",
"image": "https://static.sandbase.ai/examples/tencent/hunyuan-3d/v3/input_image_0.png",
"enable_pbr": false,
"face_count": 500000,
"polygon_type": "triangle",
"generate_type": "Normal",
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Hunyuan3d V3
Hunyuan3d V3 occupies a clearly bounded position in a image production pipeline under the route tencent/hunyuan-3d/v3. It is best evaluated as a named workflow endpoint rather than as a generic substitute for neighboring versions: planners can assign the route to a specific brief, record the chosen revision, and keep approval history tied to one predictable integration surface from intake through delivery.
A practical rollout of Hunyuan3d V3 should begin with source-readiness checks, ownership of the submitted material, an agreed budget, and a written definition of the final v3 deliverable. Before automation is enabled, the acceptance pass should verify that the returned asset opens correctly, fits the intended downstream toolchain, satisfies the project’s review criteria, and can be reproduced from the stored request and route identity tencent/hunyuan-3d/v3.
Highlights
- Distinct output behavior. For Hunyuan3d V3, for Hunyuan3d V3, start with one image and add back, left, or right references for reconstruction In Hunyuan3d V3, this capability is applied through the exact tencent/hunyuan-3d/v3 workflow with image as a relevant request control; the image control exposes the corresponding choice in this route; the image control exposes the corresponding choice in this route.
- Creative control. For Hunyuan3d V3, for Hunyuan3d V3, select Normal, LowPoly, or Geometry according to the desired asset In Hunyuan3d V3, this capability is applied through the exact tencent/hunyuan-3d/v3 workflow with enable pbr as a relevant request control; the enable pbr control exposes the corresponding choice in this route; the enable pbr control exposes the corresponding choice in this route.
- Workflow fit. For Hunyuan3d V3, for Hunyuan3d V3, request between 40,000 and 1,500,000 faces In Hunyuan3d V3, this capability is applied through the exact tencent/hunyuan-3d/v3 workflow with face count as a relevant request control; the face count control exposes the corresponding choice in this route; the face count control exposes the corresponding choice in this route.
- Production detail. For Hunyuan3d V3, for Hunyuan3d V3, pBR is available outside Geometry, and polygon choice is specific to LowPoly In Hunyuan3d V3, this capability is applied through the exact tencent/hunyuan-3d/v3 workflow with polygon type as a relevant request control; the polygon type control exposes the corresponding choice in this route; the polygon type control exposes the corresponding choice in this route.
Pricing
| Configuration | Price |
|---|---|
| Per request | $0.375 |
When to Use
| Scenario | Why this model fits |
|---|---|
| Choose Hunyuan3d V3 | Use it when the required deliverable is specifically the image-to-3d result documented for tencent/hunyuan-3d/v3. |
| Match the source material | Select this route when your inputs naturally map to image, enable_pbr, face_count, polygon_type. |
| Use its distinguishing capability | For Hunyuan3d V3, start with one image and add back, left, or right references for reconstruction In Hunyuan3d V3, this capability is applied through the exact tencent/hunyuan-3d/v3 workflow with image as a relevant request control; the image control exposes the corresponding choice in this route |
| Plan repeatable production | For Hunyuan3d V3, select Normal, LowPoly, or Geometry according to the desired asset In Hunyuan3d V3, this capability is applied through the exact tencent/hunyuan-3d/v3 workflow with enable pbr as a relevant request control; the enable pbr control exposes the corresponding choice in this route |
| Confirm cost and delivery | Use the pricing combinations below and the output contract above when budgeting or automating Hunyuan3d V3 jobs. |
Prompt Guide
Build the request around the exact tencent/hunyuan-3d/v3 schema. Start with required fields, then add only the controls needed for the intended output; keep URLs reachable and enum values exactly as shown in Technical Specs.
{
"image": "https://static.sandbase.ai/examples/tencent/hunyuan-3d/v3/input_image_0.png",
"enable_pbr": false,
"face_count": 500000,
"polygon_type": "triangle"
}
Technical Specs
| Specification | Value |
|---|---|
| Model ID | tencent/hunyuan-3d/v3 |
| Execution mode | async |
| Required inputs | image |
| Request fields | image (string, required); enable_pbr (boolean, optional); face_count (integer, optional, min 40000, max 1500000); polygon_type (string, optional, options: triangle / quadrilateral); generate_type (string, optional, options: Normal / LowPoly / Geometry); back_image_url (string, optional); left_image_url (string, optional); right_image_url (string, optional) |
| Output | url (string); content_type (string) |