# Rodin by Hyper3D

> Generate a production-ready, textured 3D model (GLB, USDZ, FBX, OBJ, or STL) from a text prompt or one or more reference images.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/hyper3d/rodin`
- **Model ID**: `hyper3d/rodin`
- **Category**: image-to-3d
- **Kind**: inference
- **Tags**: 3d, image-to-3d, text-to-3d, mesh, hyper3d

## Pricing

- **Price**: $0.4 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/hyper3d/rodin` 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/hyper3d/rodin/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/hyper3d/rodin/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/hyper3d/rodin/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 | null`, _optional_):
  Random seed for reproducible generation. Leave unset for a random result.

- **`tier`** (`TierEnum`, _optional_):
  Generation tier: Regular for full generation, or Sketch for a faster rough pass.
  - Default: `"Regular"`
  - Options: `"Regular"`, `"Sketch"`

- **`TAPose`** (`boolean`, _optional_):
  Generate human-like models in a rig-friendly T/A pose.
  - Default: `false`

- **`prompt`** (`string`, _optional_):
  Text description of the 3D object to generate. Required for text-to-3D (provide this OR one or more input images).
  - Default: `""`

- **`quality`** (`QualityEnum`, _optional_):
  Generation quality; higher values yield denser geometry and richer textures at the cost of speed.
  - Default: `"medium"`
  - Options: `"high"`, `"medium"`, `"low"`, `"extra-low"`

- **`material`** (`MaterialEnum`, _optional_):
  Material type baked into the mesh: PBR (physically based) or Shaded.
  - Default: `"PBR"`
  - Options: `"PBR"`, `"Shaded"`

- **`use_hyper`** (`boolean`, _optional_):
  Enable enhanced geometry export for finer surface detail.
  - Default: `false`

- **`condition_mode`** (`ConditionModeEnum`, _optional_):
  How multiple input images are combined: concat treats them as different views of the same object; fuse blends features from distinct references. Only relevant when input_image_urls has more than one image.
  - Default: `"concat"`
  - Options: `"fuse"`, `"concat"`

- **`input_image_urls`** (`array<string>`, _optional_):
  One or more image URLs to reconstruct into a 3D model. Required for image-to-3D (provide these OR a text prompt). Multiple images are combined per the condition_mode setting.

- **`geometry_file_format`** (`GeometryFileFormatEnum`, _optional_):
  Export format of the generated 3D mesh.
  - Default: `"glb"`
  - Options: `"glb"`, `"usdz"`, `"fbx"`, `"obj"`, `"stl"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "tier": "Regular",
  "TAPose": false,
  "prompt": "",
  "quality": "medium",
  "material": "PBR",
  "use_hyper": false,
  "condition_mode": "concat",
  "input_image_urls": [
    "https://media.modelrunner.ai/AOPTjhPDbZLs8yy1Qtrht.png"
  ],
  "geometry_file_format": "glb"
}
```

**Output**

```json
"https://media.modelrunner.ai/DIV1atkZiOXiMzs1nzBjU.glb"
```
## 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/hyper3d/rodin \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "tier": "Regular",
  "TAPose": false,
  "prompt": "",
  "quality": "medium",
  "material": "PBR",
  "use_hyper": false,
  "condition_mode": "concat",
  "input_image_urls": [
    "https://media.modelrunner.ai/AOPTjhPDbZLs8yy1Qtrht.png"
  ],
  "geometry_file_format": "glb"
}')

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("hyper3d/rodin", {
  input: {
  "tier": "Regular",
  "TAPose": false,
  "prompt": "",
  "quality": "medium",
  "material": "PBR",
  "use_hyper": false,
  "condition_mode": "concat",
  "input_image_urls": [
    "https://media.modelrunner.ai/AOPTjhPDbZLs8yy1Qtrht.png"
  ],
  "geometry_file_format": "glb"
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "hyper3d/rodin",
        arguments={
  "tier": "Regular",
  "TAPose": false,
  "prompt": "",
  "quality": "medium",
  "material": "PBR",
  "use_hyper": false,
  "condition_mode": "concat",
  "input_image_urls": [
    "https://media.modelrunner.ai/AOPTjhPDbZLs8yy1Qtrht.png"
  ],
  "geometry_file_format": "glb"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/hyper3d/rodin)
- [OpenAPI Schema](https://modelrunner.ai/models/hyper3d/rodin/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/hyper3d/rodin/llms.txt)