# Hi3D 3D Part Splitter

> Split a 3D model into parts with Hi3D.


## Overview

- **Endpoint**: `https://fal.run/hitem3d/hi3d/split`
- **Model ID**: `hitem3d/hi3d/split`
- **Category**: 3d-to-3d
- **Kind**: inference
**Tags**: 3d-to-3d



## Pricing

Your request will cost **$0.4** per generation.

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`mesh_url`** (`string`, _required_):
  URL of the input model to split. GLB, STL and OBJ formats are supported, up to 200MB.
  - Examples: "https://raw.githubusercontent.com/KhronosGroup/glTF-Sample-Models/master/2.0/DamagedHelmet/glTF-Binary/DamagedHelmet.glb"

- **`model`** (`ModelEnum`, _optional_):
  Split model type: 'character' splits humanoid models using a template with optional joints; 'general' splits any model by granularity level. Default value: `"character"`
  - Default: `"character"`
  - Options: `"character"`, `"general"`

- **`part`** (`PartEnum`, _optional_):
  Character split template (used when model is 'character'): 'a' 6 parts, 'b' 5 parts, 'c' 4 parts excluding head, 'd' 4 parts including head, 'e' 3 parts, 'f' 2 parts. Default value: `"a"`
  - Default: `"a"`
  - Options: `"a"`, `"b"`, `"c"`, `"d"`, `"e"`, `"f"`

- **`joint`** (`JointEnum`, _optional_):
  Joint type added between character parts (used when model is 'character'). Default value: `"ball"`
  - Default: `"ball"`
  - Options: `"none"`, `"ball"`, `"dovetail"`

- **`level`** (`LevelEnum`, _optional_):
  Split granularity (used when model is 'general'). Default value: `"medium"`
  - Default: `"medium"`
  - Options: `"low"`, `"medium"`, `"high"`

- **`export_format`** (`ExportFormatEnum`, _optional_):
  File format of the generated model. Character split currently supports only 'glb'. Default value: `"glb"`
  - Default: `"glb"`
  - Options: `"glb"`, `"obj"`, `"stl"`, `"fbx"`, `"usdz"`

- **`enable_safety_checker`** (`boolean`, _optional_):
  If set to true, inputs are checked for safety before processing. Default value: `true`
  - Default: `true`



**Required Parameters Example**:

```json
{
  "mesh_url": "https://raw.githubusercontent.com/KhronosGroup/glTF-Sample-Models/master/2.0/DamagedHelmet/glTF-Binary/DamagedHelmet.glb"
}
```

**Full Example**:

```json
{
  "mesh_url": "https://raw.githubusercontent.com/KhronosGroup/glTF-Sample-Models/master/2.0/DamagedHelmet/glTF-Binary/DamagedHelmet.glb",
  "model": "character",
  "part": "a",
  "joint": "ball",
  "level": "medium",
  "export_format": "glb",
  "enable_safety_checker": true
}
```


### Output Schema

The API returns the following output format:

- **`model_mesh`** (`File`, _required_):
  Generated 3D model file.

- **`thumbnail`** (`File`, _optional_):
  Preview image of the generated model, when available.



**Example Response**:

```json
{
  "model_mesh": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/hitem3d/hi3d/split \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "mesh_url": "https://raw.githubusercontent.com/KhronosGroup/glTF-Sample-Models/master/2.0/DamagedHelmet/glTF-Binary/DamagedHelmet.glb"
   }'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "hitem3d/hi3d/split",
    arguments={
        "mesh_url": "https://raw.githubusercontent.com/KhronosGroup/glTF-Sample-Models/master/2.0/DamagedHelmet/glTF-Binary/DamagedHelmet.glb"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("hitem3d/hi3d/split", {
  input: {
    mesh_url: "https://raw.githubusercontent.com/KhronosGroup/glTF-Sample-Models/master/2.0/DamagedHelmet/glTF-Binary/DamagedHelmet.glb"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/hitem3d/hi3d/split)
- [API Documentation](https://fal.ai/models/hitem3d/hi3d/split/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=hitem3d/hi3d/split)

### fal.ai Platform

- [Platform Documentation](https://fal.ai/docs/documentation)
- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python)
- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript)

### Other agent-readable surfaces

This file covers one model. To find anything else:

- [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs
- [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page
- [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`