# Tripo v2.5 Text-to-3D

> Generate a downloadable, textured 3D mesh (GLB) from a text prompt — no input photo, ready for games, AR, and product viewers.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/tripo3d/tripo/v2.5/text-to-3d`
- **Model ID**: `tripo3d/tripo/v2.5/text-to-3d`
- **Category**: text-to-3d
- **Kind**: inference
- **Tags**: tripo, tripo3d, text-to-3d, 3d, 3d-generation, mesh, glb

## Pricing

- **Price**: $0.3 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/tripo3d/tripo/v2.5/text-to-3d` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/tripo3d/tripo/v2.5/text-to-3d/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/tripo3d/tripo/v2.5/text-to-3d/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/tripo3d/tripo/v2.5/text-to-3d/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer`, _optional_):
  Random seed controlling geometry generation. Reuse the same seed to reproduce the same shape.

- **`prompt`** (`string`, _required_):
  Text description of the object, product, character, or prop to generate as a 3D model.

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

- **`face_limit`** (`integer`, _optional_):
  Caps the number of faces (triangles) on the output mesh. Leave unset to let mesh density adapt to the subject.

- **`image_seed`** (`integer`, _optional_):
  Random seed for the internal prompt-to-image step that drives generation.

- **`texture_seed`** (`integer`, _optional_):
  Random seed controlling texture generation. Reuse with the same seed to keep the shape but vary or reproduce textures.

- **`negative_prompt`** (`string`, _optional_):
  Attributes to steer the generation away from.

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A sleek white ceramic coffee mug with a simple round handle, studio lighting, plain background.",
  "auto_size": false
}
```

**Output**

```json
"https://media.modelrunner.ai/0KWMEEKi2p4KhIuPpS5JT.octet-stream"
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/tripo3d/tripo/v2.5/text-to-3d \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A sleek white ceramic coffee mug with a simple round handle, studio lighting, plain background.",
  "auto_size": false
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("tripo3d/tripo/v2.5/text-to-3d", {
  input: {
  "prompt": "A sleek white ceramic coffee mug with a simple round handle, studio lighting, plain background.",
  "auto_size": false
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "tripo3d/tripo/v2.5/text-to-3d",
        arguments={
  "prompt": "A sleek white ceramic coffee mug with a simple round handle, studio lighting, plain background.",
  "auto_size": false
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/tripo3d/tripo/v2.5/text-to-3d)
- [OpenAPI Schema](https://modelrunner.ai/models/tripo3d/tripo/v2.5/text-to-3d/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/tripo3d/tripo/v2.5/text-to-3d/llms.txt)