# Pixal3d API

> Mengonversi satu gambar menjadi model 3D GLB bertekstur dengan kontrol terperinci pada setiap tahap generasi

Menerima satu gambar dan mengembalikan model GLB beserta seed yang digunakan. Tahap struktur, bentuk, dan tekstur masing-masing memiliki pengaturan panduan, rescale, jumlah langkah, dan jadwal noise sendiri. Output `resolution` adalah 1024 atau 1536, `texture_size` adalah 1024, 2048, atau 4096, dan `decimation_target` mengatur jumlah vertex dari 5000 hingga 1586021. `remesh` membangun ulang topologi.

- Model id: `pixal3d`
- Made by: Open model
- Category: Image to 3D
- Output: 3d
- Price: from $0.30 / request (cheapest run $0.30 (300 API credits))
- Run: `POST https://api.doitong.com/v1/run/pixal3d`
- Quote: `POST https://api.doitong.com/v1/quote/pixal3d`
- Docs page: https://doitong.com/id/developers/models/pixal3d

## Pricing

Price: **from $0.30 / 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 `resolution` = 1536: $0.42 (420 API credits) / request

The full example input below costs $0.30 = 300 API credits (1 request × 300 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/pixal3d` 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 |
|---|---|---|---|---|---|---|
| `image_url` | `image` | string (image URL) | yes |  |  | URL yang mengarah ke gambar sumber untuk konversi 3D. |
| `seed` |  | integer \| null | no |  |  | Seed yang digunakan untuk pembuatan acak yang dapat direproduksi. |
| `resolution` |  | enum (integer) | no | `1024` | `1024`, `1536` | Resolusi output; meningkatkannya menambahkan detail tetapi membutuhkan waktu lebih lama. |
| `ss_guidance_strength` |  | number | no | `7.5` | 0 – 10 | Kontrol fidelitas struktur 3D awal: meningkatkannya menghasilkan kesesuaian yang lebih dekat dengan gambar input dengan risiko noise tambahan. |
| `ss_guidance_rescale` |  | number | no | `0.7` | 0 – 1 | Kontrol artefak panduan tahap 1, menukar efek panduan yang lebih kuat pada pengaturan rendah dengan output yang lebih stabil pada pengaturan tinggi. |
| `ss_sampling_steps` |  | integer | no | `12` | 1 – 50 | Jumlah denoising struktur awal: potensi peningkatan kualitas dari langkah tambahan disertai pemrosesan yang lebih lambat. |
| `ss_rescale_t` |  | number | no | `5` | 1 – 6 | Atur ketajaman transisi melalui jadwal noise pembuatan struktur: meningkatkan nilai ini membuat transisi lebih tajam. |
| `shape_slat_guidance_strength` |  | number | no | `7.5` | 0 – 10 | Kontrol fidelitas geometri terperinci: meningkatkan kepatuhan pada gambar input menghasilkan detail tambahan, dengan risiko noise tambahan. |
| `shape_slat_guidance_rescale` |  | number | no | `0.5` | 0 – 1 | Tingkatkan pengaturan ini saat geometri tampak ber-noise: ini mengurangi artefak yang disebabkan oleh panduan kuat selama tahap bentuk. |
| `shape_slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | Jumlah denoising penyempurnaan bentuk: geometri yang berpotensi lebih halus mengorbankan kecepatan saat langkah tambahan digunakan. |
| `shape_slat_rescale_t` |  | number | no | `3` | 1 – 6 | Atur ketajaman detail geometris melalui jadwal noise penyempurnaan bentuk; meningkatkan nilai ini menghasilkan detail yang lebih tajam. |
| `tex_slat_guidance_strength` |  | number | no | `1` | 0 – 10 | Kontrol fidelitas warna tekstur: kepatuhan yang lebih dekat pada warna gambar input pada pengaturan tinggi meningkatkan kejelasan warna, tetapi dapat menyebabkan oversaturasi. |
| `tex_slat_guidance_rescale` |  | number | no | `0` | 0 – 1 | Tingkatkan pengaturan ini untuk mengatasi tekstur ber-noise atau color banding: ini mengurangi artefak yang disebabkan oleh panduan kuat selama tahap tekstur. |
| `tex_slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | Jumlah langkah denoising yang digunakan untuk menghasilkan tekstur. Meningkatkan jumlah langkah membutuhkan waktu lebih lama, tetapi dapat menghasilkan tekstur yang lebih bersih. |
| `tex_slat_rescale_t` |  | number | no | `3` | 1 – 6 | Atur ketajaman detail tekstur melalui jadwal noise pembuatan tekstur; meningkatkan nilai ini menghasilkan detail yang lebih tajam. |
| `mesh_scale` |  | number | no | `1` | 0.1 – 4 | Skalakan mesh yang diinferensikan untuk memengaruhi estimasi jarak kamera yang digunakan model. |
| `max_num_tokens` |  | integer | no | `49152` | 4,096 – 131,072 | Batas token HR untuk sampler bentuk bertingkat, menyeimbangkan geometri yang lebih halus pada pengaturan tinggi dengan penghematan memori dan waktu pemrosesan pada pengaturan rendah. |
| `decimation_target` |  | integer | no | `200000` | 5,000 – 1,586,021 | Target kompleksitas mesh, dinyatakan sebagai jumlah vertex untuk hasil akhir. Mengurangi ukuran file dengan menurunkan target ini juga mengorbankan detail. |
| `texture_size` |  | enum (integer) | no | `2048` | `1024`, `2048`, `4096` | Resolusi tekstur mesh untuk baking. Detail permukaan yang lebih halus menghasilkan file yang lebih besar saat resolusi ini ditingkatkan. |
| `remesh` |  | boolean | no | `true` |  | Pembangunan ulang topologi mesh yang umumnya bermanfaat untuk penggunaan lanjutan dengan membuat segitiga yang lebih bersih, dengan konsekuensi pemrosesan yang lebih lama. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Penyaringan dapat dilonggarkan dengan menetapkan false, jika pemanggil berwenang. |

File parameters (`image`) 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
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

## 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/pixal3d?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# 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/pixal3d?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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 = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/pixal3d", 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": "pixal3d",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "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": "pixal3d",
  "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": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "model_glb": {
      "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
  },
  "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_glb` | object {url, content_type, file_name, file_size} | Model 3D yang dibuat dalam format GLB. |
| `seed` | integer | Nilai seed yang sebenarnya digunakan. |

## Related models

- [ReconViaGen 0.5](https://doitong.com/developers/models/reconviagen-0.5.md) (`reconviagen-0.5`): from $0.25 / 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
- [Hi3D Multiview to 3D · v3.0 · Multi View to 3D](https://doitong.com/developers/models/hitem3d/hi3d/v3.0/multi-view-to-3d.md) (`hitem3d/hi3d/v3.0/multi-view-to-3d`): from $1.80 / run
- [Hunyuan 3D Pro Image to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/pro/image-to-3d.md) (`hunyuan-3d/v3.1/pro/image-to-3d`): $0.375 / run
- [Hunyuan 3D Rapid Image to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/rapid/image-to-3d.md) (`hunyuan-3d/v3.1/rapid/image-to-3d`): from $0.225 / request
- [Hunyuan World · Image to World](https://doitong.com/developers/models/hunyuan_world/image-to-world.md) (`hunyuan_world/image-to-world`): $0.30 / request

## Links

- HTML page: https://doitong.com/developers/models/pixal3d
- 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=pixal3d
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/pixal3d