Trellis 3D / state-of-the-art 3D Generation Model & Trellis API!
The open source image to 3d modelsfrom the official research paper Structured 3D Latents for Scalable and Versatile 3D Generationis the state-of-the-art text to 3D and image to 3D generation AI model. And now PiAPI is providing the AI 3D model generator and the Trellis API for creators to use and supercharge their 3D workflow!
Our Pricing Plans
Pay-as-you-go access through PiAPI.
Text to 3Dtxt2model
$0.04 /generation
- Generate a 3D asset from a text prompt.
Image to 3Dimg2model
$0.04 /generation
- Turn a reference image into a textured 3D asset.
Features
Capabilities from the production model page.
Image to 3D Generation!
PiAPI will be the first to offer image to 3D Trellis 3D and Trellis API - simplifying 3D asset generation workflow of 3D artists around the world!
Text to 3D Generation
PiAPI will continually observe the latest research on 3D generation and deploy any model that shows any promising result in text-to-3D generation.
Asynchronous API Calls
The API will be designed to allow for asynchronous calls, allowing developers to "submit and forget" tasks, and fetch for the task when completed.
Accelerated Hardware Infrastructure
Our accelerated hardware infrastructure is specifically optimized for latent diffusion model inference work, ensuring workloads to be executed with maximum efficiency and minimum latency.
Custom Inference Frameworks
Our custom inference framwork used for latent diffusion model workloads focus on optimized runtime performance and resource management, preventing bottlenecks from traditional framework.
Bulk Generation Available
The perfect generation option for developers to populate their 3D projects with large quantity of custom 3D models from custom prompts and/or images. Contact us on Discord with your prompts and we will get back to you with a pricing and a timeline!
Simple and Flexibe Payment Plans
Our Pay-as-you-go option allows developers to test the API with free credits, and purchase credits for consumption, and manually or automatically top-up their credits as their usage varies.
Commercial Use
Given the commercial license of the Trellis model, all images generated from our API using that model will be available for commercial use as needed by the creators or 3D artists.
Get started
Create your API key
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Top up credits
Add credits on the billing page when you are ready to scale beyond the free tier.
Call the API
POST your first task following the API docs, then poll the task until the result is ready.
Iterate in the playground
Prototype prompts and settings in the the playground above before wiring them into your product.
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "Qubico/trellis",
"task_type": "text-to-3d",
"input": {
"prompt": "A stylized stone statue",
"ss_sampling_steps": 50,
"slat_sampling_steps": 50,
"ss_guidance_strength": 7.5,
"slat_guidance_strength": 3,
"seed": 0
}
}'
# → { "task_id": "9d5a…", "status": "pending" }curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'
# poll until status = completed
{
"data": {
"status": "completed",
"output": {
"model_file": "https://img.theapi.app/ephemeral/…"
}
}
}$ npm install -g piapi-cli $ piapi run trellis-3d-api \ prompt="A stylized stone statue" \ ss_sampling_steps=50 \ slat_sampling_steps=50 \ ss_guidance_strength=7.5 \ slat_guidance_strength=3 \ seed=0 ✓ Task completed! https://img.theapi.app/ephemeral/…
Frequently asked questions
What is the Trellis 3D Model?
The Trellis 3D Generation Model is developed by Microsoft's Trellis Research TeamIt is the most advanced 3D generation AI model in the market, dedicated to simplify creator's 3D workflow with the power of generative AI!
What is the Trellis 3D API?
The Trellis API are offered by PiAPI based on the Trellis model. Given our accelerated hardware infrastructure and custom-developed inference framework, PiAPI is able provide APIs for these two models at very market competitive costs while maintaining performance and minimizing latency!
What type of 3D model can I generate with the text to 3d model?
With the significant quality, users can use the picture to 3d model with various kinds using textual prompts or image prompts in their workflow!
What type of scenarios can Trellis be used for?
The photo to 3D model can be used in a variety of usecases. For example, if you are using Object AI to create your 2D images, you can use the AI tool to generate the corresponding 3D model; our 2D to 3D model AI generator can produce high quality 3D asset. Or if you are interested in 3D character creation, our AI generator could be used to create made up 3D characters. Or if you have a website for 3d assets trading, this tool could be used to populate the website with AI generated 3d models.
Can I use 3D models generated from the Trellis API for commercial purposes?
Given the Apache2.0 license of the Trellis 3D, all images generated from our API using that model will be available for commercial use as needed by 3D artists or creators!
More questions? See the API docs.
Our blog
Trellis 3D API



