# Hyper3D - Rodin V2.5 - Image to 3D API

> Image-to-3D with Rodin V2.5 using up to 5 reference images and a choice of quality tiers

Builds a 3D model from one to five images in `image_urls`, with an optional `prompt` up to 1024 characters. Six tiers run from Gen-2.5-Minimum to Gen-2.5-Extreme-High, with a default of High. Options include geometry format (glb, usdz, fbx, obj, stl), `material`, quad or triangle mesh sizes, `TAPose` for rig-friendly characters, and `hd_texture`.

- Model id: `hyper3d/rodin/v2.5`
- Made by: Hyper3D
- Category: Image to 3D
- Output: 3d
- Price: from $0.40 / request (cheapest run $0.40 (400 API credits))
- Run: `POST https://api.doitong.com/v1/run/hyper3d/rodin/v2.5`
- Quote: `POST https://api.doitong.com/v1/quote/hyper3d/rodin/v2.5`
- Docs page: https://doitong.com/developers/models/hyper3d/rodin/v2.5

## Pricing

Price: **from $0.40 / request** (the lowest tier; the quote prices your exact input). Billed once per request.

Price rules (the first rule that matches the input wins; a parameter you leave out counts as its default):

- When `addons.high_pack` = true: $1.20 (1200 API credits) / request

The full example input below costs $0.40 = 400 API credits (1 request × 400 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/hyper3d/rodin/v2.5` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | no | `` | ≤ 1024 characters | Guide generation with text, or let the model derive a prompt automatically from the images by leaving this empty in Image-to-3D mode. |
| `image_urls` | `images` | array of image URL | no |  | 1 – 5 items | Source image URLs, limited to 5 images and mandatory in Image-to-3D mode, for generating the model. |
| `tier` |  | enum (string) | no | `Gen-2.5-High` | `Gen-2.5-Minimum`, `Gen-2.5-Extreme-Low`, `Gen-2.5-Low`, `Gen-2.5-Medium`, `Gen-2.5-High`, `Gen-2.5-Extreme-High` | Mesh-detail tier; increasing the tier adds detail, but Gen-2.5-Minimum automatically activates minimum mode and forces 50K Triangle regardless of quality_mesh_option. Further details are in the [documentation](https://developer.hyper3d.ai/api-specification/rodin-gen2.5#use-gen-2.5-generation-with-following-gen-2.5-tiers). |
| `use_original_alpha` |  | boolean | no | `false` |  | Controls retention of input-image transparency channels when generating 3D content. |
| `seed` |  | integer \| null | no |  | 0 – 65,535 | Optional randomization seed with a range of 0–65535. |
| `geometry_file_format` |  | enum (string) | no | `glb` | `glb`, `usdz`, `fbx`, `obj`, `stl` | Geometry file format, selected from glb, usdz, fbx, obj, stl; defaults to glb. |
| `material` |  | enum (string) | no | `All` | `PBR`, `Shaded`, `All`, `None` | Material output selection: choose None for geometry without textures, or All to receive both material variants. For realistic lighting with physically based materials, choose PBR; for baked lighting without PBR maps, choose Shaded. |
| `quality_mesh_option` |  | enum (string) | no | `Auto` | `Auto`, `4K Quad`, `8K Quad`, `18K Quad`, `50K Quad`, `100K Quad`, `200K Quad`, `2K Triangle`, `20K Triangle`, `50K Triangle`, `150K Triangle`, `500K Triangle`, `1M Triangle`, `2M Triangle` | Mesh topology and quality, with available face counts determined by the tier: Extreme-Low, Low, and Medium allow up to 1M Triangle; High and Extreme-High support 20K Triangle through 2M Triangle. Auto applies these recommended settings: 1. Gen-2.5-Minimum → 50K Triangle; 2. Gen-2.5-Extreme-Low → 50K Triangle; 3. Gen-2.5-Low → 50K Triangle; 4. Gen-2.5-Medium → 500K Triangle; 5. Gen-2.5-High → 500K Triangle; Gen-2.5-Extreme-High → 1M Triangle. For manual selection, Quad favors smooth surfaces and Triangle favors detailed geometry; the Hyper3D API receives the topology as `mesh_mode` (Quad/Raw) and the face count as `quality_override`. |
| `texture_mode` |  | enum (string) \| null | no |  | `legacy`, `extreme-low`, `low`, `medium`, `high` | Choose the texture quality explicitly or leave the choice to the API, which uses a default suited to the tier. |
| `enable_creative_mode` |  | boolean | no | `false` |  | Creative generation mode, equivalent to `geometry_instruct_mode` set to `creative` in the Hyper3D API. Enabling it makes generation more robust without sacrificing output consistency. |
| `hd_texture` |  | boolean | no | `false` |  | Controls advanced texture post-processing to improve visual fidelity. |
| `texture_delight` |  | boolean | no | `false` |  | Strips baked-in illumination and highlights out of generated textures. |
| `is_micro` |  | boolean | no | `false` |  | Adds finer geometric detail at micro scale; takes effect only when `tier="Gen-2.5-Extreme-High"`. |
| `TAPose` |  | boolean | no | `false` |  | Character pose setting for easier rigging and animation in 3D software: enabling it generates characters in either T-pose or A-pose. |
| `bbox_condition` |  | object {width, height, length} \| null | no |  |  | Limit how large the generated model can be using a ControlNet. |
| `bbox_condition.width` |  | integer | no | `0` | 1 – 2,048 | Bounding box constraint width along the x axis. |
| `bbox_condition.height` |  | integer | no | `0` | 1 – 2,048 | Bounding box constraint height along the y axis. |
| `bbox_condition.length` |  | integer | no | `0` | 1 – 2,048 | Bounding box constraint length along the z axis. |
| `addons` |  | object {high_pack} \| null | no |  |  | Optional add-on selection, supplied as a list or, for just one add-on, as a single value. |
| `addons.high_pack` |  | boolean | no | `false` |  | HighPack enhancement: Quad output has approximately 16 times the face count requested through the quality parameter, and textures use 4K resolution rather than the 2K default. |
| `preview_render` |  | boolean | no | `false` |  | Preview-render toggle that adds an image showing the generated 3D model to the delivered model files. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Screening can be relaxed by setting false, provided the caller is authorized. |

File parameters (`images`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{}
```

A fuller example:

```json
{
  "prompt": ""
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/hyper3d/rodin/v2.5?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": ""
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/hyper3d/rodin/v2.5?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": ""
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/hyper3d/rodin/v2.5", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "hyper3d/rodin/v2.5",
      "input": {
        "prompt": ""
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "hyper3d/rodin/v2.5",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 400,
    "usd": "0.40",
    "charged": 400,
    "refunded": 0
  },
  "input": {
    "prompt": ""
  },
  "output": {
    "model_mesh": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "model_meshes": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    ],
    "seed": 42,
    "textures": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200,
        "width": 1024,
        "height": 768
      }
    ]
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `model_mesh` | object {url, content_type, file_name, file_size} | File containing the generated 3D object. |
| `model_meshes` | array of object {url, content_type, file_name, file_size} | Extra 3D object files generated by Hyper3D and returned in addition to model_mesh. |
| `seed` | integer | Seed applied during generation. |
| `textures` | array of object {url, content_type, file_name, file_size, width, height} | Textures produced for the 3D object. |

## Related models

- [Hyper3D - Rodin V2.5 - Image to 3D - Fast](https://doitong.com/developers/models/hyper3d/rodin/v2.5/fast.md) (`hyper3d/rodin/v2.5/fast`): $0.10 / request
- [Hyper3D - Rodin V2.5 - Text to 3D](https://doitong.com/developers/models/hyper3d/rodin/v2.5/text-to-3d.md) (`hyper3d/rodin/v2.5/text-to-3d`): from $0.40 / request
- [Hyper3D - Rodin V2.5 - Text to 3D - Fast](https://doitong.com/developers/models/hyper3d/rodin/v2.5/text-to-3d/fast.md) (`hyper3d/rodin/v2.5/text-to-3d/fast`): $0.10 / request
- [Hyper3d](https://doitong.com/developers/models/hyper3d/rodin/v2.md) (`hyper3d/rodin/v2`): $0.40 / request
- [Hyper3D Rodin](https://doitong.com/developers/models/hyper3d/rodin.md) (`hyper3d/rodin`): $0.40 / request
- [Hi3D Image to 3D](https://doitong.com/developers/models/hitem3d/hi3d/image-to-3d.md) (`hitem3d/hi3d/image-to-3d`): $0.50 / run
- [Hi3D Image to 3D · v3.0](https://doitong.com/developers/models/hitem3d/hi3d/v3.0/image-to-3d.md) (`hitem3d/hi3d/v3.0/image-to-3d`): from $1.80 / run
- [Hi3D Multiview to 3D · Multi View to 3D](https://doitong.com/developers/models/hitem3d/hi3d/multi-view-to-3d.md) (`hitem3d/hi3d/multi-view-to-3d`): $0.50 / run

## Links

- HTML page: https://doitong.com/developers/models/hyper3d/rodin/v2.5
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=hyper3d/rodin/v2.5
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/hyper3d/rodin/v2.5