# Tripo H3.1 Text-to 3D — Atlas Cloud API

> Generate 3D models from text descriptions using Tripo H3.1.

This is the machine-readable API reference for **Tripo H3.1 Text-to 3D** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `tripo-h3.1/text-to-3d`
- **Built by**: TRIPO
- **Modality**: Image
- **Model page**: https://www.atlascloud.ai/models/tripo-h3.1/text-to-3d
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.1 per image
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_image` with `model: "tripo-h3.1/text-to-3d"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate image tripo-h3.1/text-to-3d -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `tripo-h3.1/text-to-3d`


## 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:

- **`model`** (`string`, _required_):
  model name
  - Default: `"tripo-h3.1/text-to-3d"`

- **`prompt`** (`string`, _required_):
  Text description of the 3D object to generate. Maximum 1024 characters.

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

- **`texture`** (`boolean`, _optional_):
  Generate textures for the model.
  - Default: `true`

- **`pbr`** (`boolean`, _optional_):
  Generate PBR (Physically Based Rendering) materials.
  - Default: `true`

- **`texture_quality`** (`string`, _optional_):
  Texture resolution level.
  - Default: `"standard"`
  - Options: "standard", "detailed"

- **`geometry_quality`** (`string`, _optional_):
  Geometry quality level.
  - Default: `"standard"`
  - Options: "standard", "detailed"

- **`face_limit`** (`integer`, _optional_):
  Target mesh face count. If unset, the model determines it adaptively.
  - Min: 1000
  - Max: 2000000

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

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

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

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

- **`quad`** (`boolean`, _optional_):
  Generate a quad mesh instead of triangles. Outputs FBX when enabled.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "tripo-h3.1/text-to-3d",
  "prompt": ""
}
```


**Full Example**:

```json
{
  "model": "tripo-h3.1/text-to-3d",
  "prompt": "",
  "negative_prompt": "",
  "texture": true,
  "pbr": true,
  "texture_quality": "standard",
  "geometry_quality": "standard",
  "face_limit": 1000,
  "model_seed": 0,
  "image_seed": 0,
  "texture_seed": 0,
  "auto_size": false,
  "quad": false
}
```


### Output Schema

The API returns the following output format:


- **`model`** (`string`, _optional_):
  model name
  - Default: `"tripo-h3.1/text-to-3d"`

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated 3D model files (GLB/FBX and variants), preview image last. Null when status is not completed.

- **`files`** (`array[object]`, _optional_):
  Structured per-output metadata (URL, type, content_type, file_name, file_size) for each generated 3D file.
  - Item properties:
    - **`url`** (`string`, _optional_):

    - **`type`** (`string`, _optional_):

    - **`content_type`** (`string`, _optional_):

    - **`file_name`** (`string`, _optional_):

    - **`file_size`** (`integer`, _optional_):


- **`thumbnail`** (`string`, _optional_):
  Preview render image URL of the generated 3D model.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "model": "tripo-h3.1/text-to-3d",
  "created_at": "",
  "id": "",
  "outputs": [
    ""
  ],
  "files": [
    {
      "url": "",
      "type": "",
      "content_type": "",
      "file_name": "",
      "file_size": 0
    }
  ],
  "thumbnail": "",
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tripo-h3.1/text-to-3d",
  "prompt": "",
  "negative_prompt": "",
  "texture": true,
  "pbr": true,
  "texture_quality": "standard",
  "geometry_quality": "standard",
  "face_limit": 1000,
  "model_seed": 0,
  "image_seed": 0,
  "texture_seed": 0,
  "auto_size": false,
  "quad": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/tripo-h3.1/text-to-3d)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Tripo H3.1 Text-to-3D

**Tripo H3.1 Text-to-3D** generates a textured 3D model from a text prompt. It produces a mesh (GLB, or FBX when quad topology is requested) with optional PBR materials, plus a preview render — ideal for rapid asset prototyping, game/AR content, and 3D design exploration.

#### 🌟 Key Features

##### 🧊 Text-to-3D
Generate a complete 3D mesh from a natural-language description of the object.

##### 🎨 Textures & PBR Materials
Optionally generate textures and Physically Based Rendering (PBR) materials for production-ready shading.

##### 🔺 Adaptive or Fixed Face Count
Let the model choose the mesh density adaptively, or cap it with `face_limit` for lighter assets.

##### 🔁 Reproducible Results
Pin `model_seed`, `image_seed`, and `texture_seed` to reproduce or iterate on a specific generation.

##### 📦 Multiple Output Formats
Receive GLB by default, or FBX when `quad` is enabled, alongside base and PBR model variants.

#### ⚙️ Parameters

| Parameter | Required | Description |
|---|---|---|
| `prompt` | ✅ | Text description of the 3D object to generate (max 1024 characters). |
| `negative_prompt` | ❌ | Features to avoid in the generated model. |
| `texture` | ❌ | Generate textures for the model (default: `true`). |
| `pbr` | ❌ | Generate PBR materials (default: `true`). |
| `texture_quality` | ❌ | Texture resolution level: `standard` (default) or `detailed`. |
| `geometry_quality` | ❌ | Geometry quality level: `standard` (default) or `detailed`. |
| `face_limit` | ❌ | Target mesh face count. Adaptive if unset. |
| `model_seed` | ❌ | Seed for geometry generation reproducibility. |
| `image_seed` | ❌ | Seed for the text-to-image step reproducibility. |
| `texture_seed` | ❌ | Seed for texture generation reproducibility. |
| `auto_size` | ❌ | Auto-scale the model to real-world dimensions in meters (default: `false`). |
| `quad` | ❌ | Generate a quad mesh instead of triangles; outputs FBX (default: `false`). |

#### 💲 Pricing

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/tripo-h3.1/text-to-3d · Docs: https://www.atlascloud.ai/docs