---
title: Hunyuan 3D 3.1 Pro | Runware Docs
url: https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro
description: High-fidelity 3D asset generation with multi-view reconstruction and PBR materials
---
# Hunyuan 3D 3.1 Pro

![Hunyuan 3D 3.1 Pro](https://assets.runware.ai/covers/tencent-hunyuan-3d-3-1-pro.jpg)

Hunyuan 3D 3.1 Pro is a production-grade 3D generation model from Tencent that creates high-fidelity assets from text prompts or images. It uses enhanced 8-view reconstruction for improved spatial accuracy and reduced geometric artifacts, producing clean topology, watertight meshes, and PBR materials suitable for game development, 3D printing, and professional animation workflows.

- **Status**: live
- **ID**: `tencent:hunyuan-3d@3.1-pro`
- Try in Playground
- **Creator**: Tencent
- **Release Date**: February 10, 2026
- **Capabilities**: Text to 3D, Image to 3D, Checkpoint

## Pricing

$0.225 from, per run · ~2m 17s per request

**Rates** (per run)

- Geometry: `$0.225`
- Normal: `$0.375`
- Normal + EnableBPR: `$0.525`

**6 example generations**

- [image-to-3d-geometry-only](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro/examples#example-polar-telegraph-cabin-environment): `$0.375` (~2m 17s)
- [text-to-3d-geometry-only](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro/examples#example-pediatric-radiology-axolotl-mascot): `$0.375` (~1m 22s)
- [image-to-3d](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro/examples#example-electric-tufting-gun-ecommerce-model): `$0.525` (~2m 8s)
- [text-to-3d](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro/examples#example-runway-friction-tester-trailer): `$0.525` (~2m 16s)
- [text-to-3d-pbr](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro/examples#example-modern-beekeeping-smoker-product-model): `$0.675` (~3m 1s)
- [image-to-3d-pbr](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro/examples#example-wetland-ranger-muskrat-character-model): `$0.825` (~3m 34s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide exactly one of: `positivePrompt`, `inputs.images`.

---

When `settings.generateType` is `Geometry`, `settings.pbr` cannot be used.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `3dInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

3D output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-outputformat)

- **Type**: `string`
- **Default**: `GLB`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`GLB\`: Binary glTF format for 3D models, including geometry, textures, and PBR materials.

**Allowed values**: `GLB`

### [webhookURL](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [images](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-inputs-images)

- **Path**: `inputs.images`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `8`

Input images (UUID, URL, Data URI, or Base64). Single frontal image, or 8 images for multi-view (1 frontal + 7 angles: left, right, back, top, bottom, left\_front, right\_front).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `tencent:hunyuan-3d@3.1-pro`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-positiveprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `1024`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [faceCount](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-settings-facecount)

- **Path**: `settings.faceCount`
- **Type**: `integer`
- **Min**: `3000`
- **Max**: `1500000`
- **Default**: `500000`

Number of faces (polygons) in the generated 3D model.

### [generateType](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-settings-generatetype)

- **Path**: `settings.generateType`
- **Type**: `string`
- **Default**: `Normal`

Generation mode for 3D model creation.

**Allowed values**:

- `Normal` Generates a textured geometry model.
- `Geometry` Generates a texture-free white model.

### [pbr](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#request-settings-pbr)

- **Path**: `settings.pbr`
- **Type**: `boolean`

Enable PBR (Physically Based Rendering) material generation.

## Response Parameters

### [taskType](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `3dInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [cost](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

### [outputs](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-outputs)

- **Path**: `outputs.files`
- **Type**: `object (3 properties)`
- **Required**: true

Generated output artifacts.

#### [files](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-outputs-files)

- **Path**: `outputs.files`
- **Type**: `array of objects (2 properties)`
- **Required**: true
- **Min items**: `1`

Generated output files.

##### [uuid](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-outputs-files-uuid)

- **Path**: `outputs.files.uuid`
- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output file.

##### [url](https://runware.ai/docs/models/tencent-hunyuan-3d-3-1-pro#response-outputs-files-url)

- **Path**: `outputs.files.url`
- **Type**: `string`
- **Required**: true
- **Format**: `uri`

URL of the output file.

## Examples

### text-to-3d (text-to-3d)

[View 3D model](https://assets.runware.ai/examples/tencent-hunyuan-3d-3-1-pro/edb234e6-cf45-4b54-93ec-abf0d79b8232.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "979602a5-bb85-43b0-8dd8-89232e074a33",
  "model": "tencent:hunyuan-3d@3.1-pro",
  "positivePrompt": "Single complete towable runway friction-testing trailer, designed as a game-ready 3D prop for a contemporary airport operations simulator. Compact low rectangular chassis with rounded safety-orange fiberglass housing, matte white upper access lid, black rubber fenders, two road wheels, front tow bar and small jockey wheel. Include a visible lowered measuring wheel centered beneath the chassis, slim water-spray nozzle, recessed control panel with unlabeled buttons, steel latches, ventilation slots, red rear reflectors, coiled black utility cable and realistic bolts. Clean industrial design with modest operational wear, faint tire grime and edge scuffs. PBR materials: painted fiberglass, galvanized steel, rubber and clear indicator lenses. Accurate proportions, complete underside, clean silhouette, no logos, no lettering, no environment or separate objects.",
  "settings": {
    "faceCount": 500000,
    "generateType": "Normal",
    "pbr": false
  }
}
```

---

### image-to-3d (image-to-3d)

[View 3D model](https://assets.runware.ai/examples/tencent-hunyuan-3d-3-1-pro/4f872c78-46c9-4746-9d95-d9cdc730d2c9.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "91f66d00-1f2a-4d6f-8906-72b8babab39a",
  "model": "tencent:hunyuan-3d@3.1-pro",
  "settings": {
    "faceCount": 500000,
    "generateType": "Normal",
    "pbr": false
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/239bb5e1-4eae-458d-8c7b-3ab5668f9a07.jpg"
    ]
  }
}
```

---

### text-to-3d-pbr (text-to-3d-pbr)

[View 3D model](https://assets.runware.ai/examples/tencent-hunyuan-3d-3-1-pro/a1183d31-1d1d-4ca9-95cd-d9894a239b1b.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "77429f53-42c5-4136-8026-e579a80d4027",
  "model": "tencent:hunyuan-3d@3.1-pro",
  "positivePrompt": "Create a production-ready 3D model of one contemporary handheld beekeeping smoker, fully assembled and mechanically plausible. Feature a cylindrical brushed stainless-steel fire chamber, a hinged conical spout lid, and a perforated butter-yellow powder-coated aluminum heat guard. Attach compact bellows at the rear with pale maple outer boards, a honey-brown vegetable-tanned leather gusset, small brass hinges and fasteners, and a matte black silicone air nozzle. Include realistic seams, folded edges, perforations, hardware, clearances, and subtle manufacturing details. Clean modern agricultural-tool design with softly rounded geometry. Distinct PBR materials with accurate metal roughness, painted finish, wood grain, leather texture, and silicone response. Centered upright product pose, complete geometry on every side, watertight clean topology. No branding, text, smoke, bees, stand, loose parts, or background props.",
  "settings": {
    "faceCount": 800000,
    "generateType": "Normal",
    "pbr": true
  }
}
```

---

### image-to-3d-pbr (image-to-3d-pbr)

[View 3D model](https://assets.runware.ai/examples/tencent-hunyuan-3d-3-1-pro/8e3a2230-27d8-4f19-b2b4-a4898121ca7f.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "41b37dd5-5261-470b-a07c-9f10015809cc",
  "model": "tencent:hunyuan-3d@3.1-pro",
  "settings": {
    "faceCount": 1000000,
    "generateType": "Normal",
    "pbr": true
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/de50a309-63d3-4ffe-b9c0-7aa382c960cc.jpg",
      "https://assets.runware.ai/assets/inputs/9900e311-d5b8-4226-b010-23567f65d0e6.jpg",
      "https://assets.runware.ai/assets/inputs/f4b266d1-495b-43bc-b82e-80d805e38332.jpg",
      "https://assets.runware.ai/assets/inputs/a973e88d-5d07-4f71-901b-c4fd8e10cfc3.jpg",
      "https://assets.runware.ai/assets/inputs/fd3127cc-d087-4c66-8caa-fa02d6505e9e.jpg",
      "https://assets.runware.ai/assets/inputs/5ea84a2e-52c9-4f2a-8515-30ff458f6863.jpg",
      "https://assets.runware.ai/assets/inputs/7f52f067-796a-4bfc-8d0e-27fc51f25b1c.jpg",
      "https://assets.runware.ai/assets/inputs/88830cbe-8175-49d0-ad99-521f8ea52c6b.jpg"
    ]
  }
}
```

---

### image-to-3d-geometry-only (image-to-3d-geometry-only)

[View 3D model](https://assets.runware.ai/examples/tencent-hunyuan-3d-3-1-pro/c0f5c3c5-7b28-4907-8e44-62367fa97a96.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "b5f25d55-23a2-42e5-ab9f-7b394ea3cb21",
  "model": "tencent:hunyuan-3d@3.1-pro",
  "settings": {
    "faceCount": 350000,
    "generateType": "Geometry"
  },
  "inputs": {
    "images": [
      "https://assets.runware.ai/assets/inputs/df75c798-ba6c-4455-8e87-da2ff65e2cde.jpg"
    ]
  }
}
```

---

### text-to-3d-geometry-only (text-to-3d-geometry-only)

[View 3D model](https://assets.runware.ai/examples/tencent-hunyuan-3d-3-1-pro/dafc01e4-407e-4e2c-875d-e7317d53d95d.glb)

```json
{
  "taskType": "3dInference",
  "taskUUID": "e3b77003-3841-4c70-825d-470b7faa48a6",
  "model": "tencent:hunyuan-3d@3.1-pro",
  "positivePrompt": "Single full-body axolotl mascot designed for a pediatric radiology program, standing upright in a relaxed animation-ready pose with arms held slightly away from the torso. Reassuring, curious personality expressed through a broad wedge-shaped head, gentle smile, raised brow forms, rounded cheeks, compact body, sturdy webbed feet, and a long counterbalancing tail with a pronounced fin ridge. Six large external gill branches create a memorable radial silhouette; sculpt each branch as a tapered organic form with bold ribbed fronds. Use clear interlocking body masses, softly defined joints, simplified digits, and subtle anatomical folds that read through geometry alone. Friendly stop-motion maquette art direction, appealing from every angle. One watertight character object, no clothing, accessories, pedestal, lettering, color-dependent details, or surface patterns.",
  "settings": {
    "faceCount": 300000,
    "generateType": "Geometry"
  }
}
```