# Tripo P2 Text to 3D

> Tripo P2 generates 3D models from a text prompt, with optional PBR textures, adjustable face counts, and triangle or quad mesh topology.


## Overview

- **Endpoint**: `https://fal.run/tripo3d/p2/text-to-3d`
- **Model ID**: `tripo3d/p2/text-to-3d`
- **Category**: text-to-3d
- **Kind**: inference
**Tags**: 3d, text-to-3d, 3d-generation, low-poly, pbr, tripo



## Pricing

Billing is calculated per generated 3D model. Each request costs **$1.00** without textures, **$1.10** with fast or standard textures, **$1.20** with detailed textures, or **$1.30** with extreme textures. PBR enables textures and uses the selected texture rate. Quad topology adds no extra charge. For example, **10 models** with standard textures cost **$11.00**. To generate without textures, set both texture and pbr to false.

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:


- **`prompt`** (`string`, _required_):
  Text description of the 3D object to generate. Maximum 1024 characters.
  - Examples: "A low-poly wooden chair"

- **`negative_prompt`** (`string`, _optional_):
  Text describing features to avoid in the generated model.

- **`image_seed`** (`integer`, _optional_):
  Seed for the internal text-to-image step.

- **`model_seed`** (`integer`, _optional_):
  Seed for geometry generation reproducibility.

- **`face_limit`** (`integer`, _optional_):
  Maximum number of faces for the generated mesh. Quad meshes support up to 25,000 faces.
  - Range: `48` to `50000`

- **`texture`** (`boolean`, _optional_):
  Whether to generate textures for the model. Default value: `true`
  - Default: `true`

- **`pbr`** (`boolean`, _optional_):
  Whether to generate PBR material maps. Enabling PBR also enables textures. Default value: `true`
  - Default: `true`

- **`texture_seed`** (`integer`, _optional_):
  Seed for texture generation reproducibility.

- **`texture_quality`** (`TextureQualityEnum`, _optional_):
  Texture quality level. Default value: `"standard"`
  - Default: `"standard"`
  - Options: `"fast"`, `"standard"`, `"detailed"`, `"extreme"`

- **`texture_version`** (`Enum`, _optional_):
  Texture model version. The fast quality requires v3.5-20260815.
  - Options: `"v3.5-20260815"`, `"v3.0-20250812"`, `"v2.5-20250123"`

- **`delight`** (`boolean`, _optional_):
  Remove baked-in lighting before texturing with v3.5-20260815. Default value: `true`
  - Default: `true`

- **`auto_size`** (`boolean`, _optional_):
  Auto-scale the model to real-world dimensions in meters.
  - Default: `false`

- **`export_uv`** (`boolean`, _optional_):
  Whether to generate UV coordinates for the model. Default value: `true`
  - Default: `true`

- **`export_orientation`** (`Enum`, _optional_):
  Optional forward axis for the exported model.
  - Options: `"+x"`, `"-x"`, `"-y"`, `"+y"`

- **`quad`** (`boolean`, _optional_):
  Generate quad mesh topology instead of triangles.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "prompt": "A low-poly wooden chair"
}
```

**Full Example**:

```json
{
  "prompt": "A low-poly wooden chair",
  "texture": true,
  "pbr": true,
  "texture_quality": "standard",
  "delight": true,
  "export_uv": true
}
```


### Output Schema

The API returns the following output format:

- **`model_mesh`** (`File`, _required_):
  Generated 3D model file. May be GLB or FBX depending on Tripo output.

- **`model_urls`** (`ModelUrls`, _required_):
  URLs for different 3D model variants.

- **`rendered_image`** (`File`, _optional_):
  Preview render of the generated 3D model.



**Example Response**:

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


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/tripo3d/p2/text-to-3d \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
     "prompt": "A low-poly wooden chair"
   }'
```

### 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(
    "tripo3d/p2/text-to-3d",
    arguments={
        "prompt": "A low-poly wooden chair"
    },
    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("tripo3d/p2/text-to-3d", {
  input: {
    prompt: "A low-poly wooden chair"
  },
  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/tripo3d/p2/text-to-3d)
- [API Documentation](https://fal.ai/models/tripo3d/p2/text-to-3d/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=tripo3d/p2/text-to-3d)

### 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`