# Tripo 3.1

> Run Tripo 3.1 by tripo online or via API. $0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits), no setup.

**URL:** https://inference.sh/apps/tripo/tripo-3-1
**Last updated:** 2026-10-28

---

Tripo 3.1 3D model generation from a text prompt, an image, or up to four views. PBR textures up to 8K, Ultra geometry, quad and smart low-poly topology, part segmentation.

- app: `tripo/tripo-3-1`
- maker: [tripo](https://inference.sh/apps/tripo.md)
- category: [3d](https://inference.sh/apps/category/3d.md)
- input → output: text → 3d, image → 3d
- tasks: [text to 3d](https://inference.sh/apps/tag/text-to-3d.md), [image to 3d](https://inference.sh/apps/tag/image-to-3d.md)
- price: $0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits)
- runs via: api, javascript and python sdk, belt cli, mcp

## tripo-3-1 API Guide

### About
tripo 3.1 3d model generation from a text prompt, an image, or up to four views. pbr textures up to 8k, ultra geometry, quad and smart low-poly topology, part segmentation.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @7eycb0nw pinned
result = client.run({
        "app": "tripo/tripo-3-1@7eycb0nw",
        "input": {
            "prompt": "a stylized ceramic teapot shaped like a snail"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @7eycb0nw pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "tripo/tripo-3-1@7eycb0nw",
        "input": {
            "prompt": "a stylized ceramic teapot shaped like a snail"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "tripo/tripo-3-1@7eycb0nw",
        "input": {
            "prompt": "a stylized ceramic teapot shaped like a snail"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "tripo/tripo-3-1@7eycb0nw",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **prompt** (string): What to make, for text to 3D. Used when no image is given.
- **negative_prompt** (string): What to keep out, for text to 3D.
- **image** (string): The object, or its front view when side views are given. JPEG or PNG.
- **left_image** (string): Left view of the object, for multiview. Needs image.
- **back_image** (string): Back view of the object, for multiview. Needs image.
- **right_image** (string): Right view of the object, for multiview. Needs image.
- **texture** (boolean): Texture the model. Off returns the bare mesh and costs less.
- **pbr** (boolean): Add PBR material maps. Turns texture on.
- **texture_quality** (string): fast and standard cost the same; detailed (HD) and extreme (8K) cost more.
- **geometry_quality** (string): detailed is Ultra geometry and costs 20 credits more.
- **face_limit** (integer): Maximum face count. Empty: chosen by Tripo. Up to 1.5M, 2M with detailed geometry, 150K with quad, 20K with smart_low_poly.
- **quad** (boolean): Quad mesh, delivered as FBX. Costs 5 credits more.
- **smart_low_poly** (boolean): Hand-crafted style low-poly topology. Costs 10 credits more.
- **generate_parts** (boolean): Split the model into editable parts. Needs texture and pbr off; costs 20 credits more.
- **auto_size** (boolean): Scale the model to real-world size in meters.
- **enable_image_autofix** (boolean): Let Tripo clean up a single input image first.
- **texture_alignment** (string): Align the texture to the input image, or to the geometry.
- **orientation** (string): align_image turns the model to match the image.
- **model_seed** (integer): Seed for the geometry.
- **texture_seed** (integer): Seed for the texture.
- **image_seed** (integer): Seed for the image Tripo draws from the prompt, for text to 3D.

#### Output
- **model** (string): The 3D model: GLB, or FBX for a quad mesh.
- **rendered_image** (string): A preview render of the model.

## other 3d apps

- [Tripo Auto Rig](https://inference.sh/apps/tripo/tripo-rig.md): $0.01/credit (rig check free, auto rig 25 credits, retarget 10 credits/animation)
- [Hunyuan 3D Auto Rigging](https://inference.sh/apps/tencent/hunyuan-3d-auto-rigging.md): $0.02/credit, 10 credits/call ($0.20/call)
- [Hunyuan 3D 3.1](https://inference.sh/apps/tencent/hunyuan-3d-3-1.md): $0.02/credit; Geometry 15cr, Normal 25cr, +10cr views/PBR/face-count
- [Rodin Gen-2.5](https://inference.sh/apps/hyper3d/rodin-gen-2-5.md): $0.58/credit; Extreme-High tier +0.5 credits, texture extreme-high +2 credits
- [Meshy 7.1](https://inference.sh/apps/meshy/meshy-7-1.md): $0.0127/Meshy credit (20 base + 10-15 texture + 5 hi-res geo)

## faq

### how much does Tripo 3.1 cost?

$0.01/credit, $0.10-$0.50/run (text: 10-40 credits, image/multiview: 20-50 credits). you pay per run from your inference shell credits. no subscription is required.

### how do I run Tripo 3.1 via api?

call tripo/tripo-3-1 with the javascript or python sdk, the rest api, or `belt app run tripo/tripo-3-1` from a terminal. the api reference on this page lists every input.

### who makes Tripo 3.1?

Tripo 3.1 is made by tripo and runs on inference shell. every tripo app is listed at https://inference.sh/apps/tripo.

### can my agent use Tripo 3.1?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Tripo 3.1?

other 3d apps on inference shell include Tripo Auto Rig, Hunyuan 3D Auto Rigging, Hunyuan 3D 3.1, Rodin Gen-2.5. they run through the same api, so switching is a one-line change.