Getting Started

Getting Started

API

MCP Server

Quickstart

Complete step-by-step guide to your first 3D generation

Quickstart

Generate your first 3D model in under 5 minutes.

Create an API Key

  1. Sign in to your account
  2. Go to Settings β†’ API Keys
  3. Click Create Key, name it, and copy the key

Create a Generation Task

Send a POST request with your image and chosen model:

curl -X POST https://trellis2.app/api/v1/3d/generations \
  -H "Authorization: Bearer tr_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://example.com/chair.jpg",
    "model": "trellis2",
    "mode": "async"
  }'
import requests

response = requests.post(
    "https://trellis2.app/api/v1/3d/generations",
    headers={
        "Authorization": "Bearer tr_your_key",
        "Content-Type": "application/json"
    },
    json={
        "image_url": "https://example.com/chair.jpg",
        "model": "trellis2",
        "mode": "async"
    }
)

task = response.json()
task_id = task["id"]
print(f"Task created: {task_id}")
const response = await fetch('https://trellis2.app/api/v1/3d/generations', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer tr_your_key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    image_url: 'https://example.com/chair.jpg',
    model: 'trellis2',
    mode: 'async',
  }),
});

const task = await response.json();
console.log('Task created:', task.id);

Poll for the Result

import time

while True:
    resp = requests.get(
        f"https://trellis2.app/api/v1/tasks/{task_id}",
        headers={"Authorization": "Bearer tr_your_key"}
    )
    data = resp.json()

    if data["status"] == "completed":
        print(f"Model URL: {data['data']['model_url']}")
        break
    elif data["status"] == "failed":
        print(f"Error: {data['error']['message']}")
        break

    print(f"Progress: {data.get('progress', 0)}%")
    time.sleep(3)
while (true) {
  const resp = await fetch(`https://trellis2.app/api/v1/tasks/${task.id}`, {
    headers: { 'Authorization': 'Bearer tr_your_key' },
  });
  const data = await resp.json();

  if (data.status === 'completed') {
    console.log('Model URL:', data.data.model_url);
    break;
  } else if (data.status === 'failed') {
    console.error('Error:', data.error.message);
    break;
  }

  console.log(`Progress: ${data.progress}%`);
  await new Promise((r) => setTimeout(r, 3000));
}

Download Your Model

The completed task returns a model_url pointing to a downloadable GLB file:

curl -O https://r2.../model.glb

That's it! You've generated a 3D model from an image. See Available Models for all options.

Table of Contents

Quickstart
Create an API Key
Create a Generation Task
Poll for the Result
Download Your Model