# Trellis 2 API

> Jibdel immaġni waħda f’mesh 3D GLB b’tessut, b’settings aġġustabbli għall-istruttura, il-forma, it-tessut u l-UV

Jibni asset 3D minn immaġni waħda (`image_url`) u jirritorna fajl GLB. `resolution` huwa 512, 1024 jew 1536, u `texture_size` huwa 1024, 2048 jew 4096. Kull wieħed mit-tliet stadji (structure, shape, texture) għandu kontrolli tiegħu għall-guidance u l-passi tat-teħid tal-kampjuni. `decimation_target` jistabbilixxi l-għadd ta’ vertiċi tal-mesh (5,000 sa 2,000,000), u huma esposti għażliet għar-remeshing u l-UV-unwrapping.

- Model id: `trellis-2`
- Made by: Microsoft
- Category: Image to 3D
- Output: 3d
- Price: from $0.25 / request (cheapest run $0.25 (250 API credits))
- Run: `POST https://api.doitong.com/v1/run/trellis-2`
- Quote: `POST https://api.doitong.com/v1/quote/trellis-2`
- Docs page: https://doitong.com/mt/developers/models/trellis-2

## Pricing

Price: **from $0.25 / 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` = 1024: $0.30 (300 API credits) / request
- When `resolution` = 1536: $0.35 (350 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/trellis-2` 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 |
|---|---|---|---|---|---|---|
| `seed` |  | integer \| null | no |  |  | Seed użat għall-ġenerazzjoni każwali riproduċibbli. |
| `resolution` |  | enum (integer) | no | `1024` | `512`, `1024`, `1536` | Riżoluzzjoni tal-output; iż-żieda tagħha żżid id-dettall iżda tieħu aktar ħin. |
| `ss_guidance_strength` |  | number | no | `7.5` | 0 – 10 | Kontroll tal-fedeltà tal-istruttura 3D inizjali: iż-żieda tagħha tiffavorixxi qbil eqreb mal-immaġni input bir-riskju ta’ aktar storbju. |
| `ss_guidance_rescale` |  | number | no | `0.7` | 0 – 1 | Kontroll tal-artifacts tal-gwida fl-istadju 1, li jibbilanċja effetti ta’ gwida aktar b’saħħithom f’settings baxxi ma’ output aktar stabbli f’settings għoljin. |
| `ss_guidance_interval_start` |  | number | no | `0.6` | 0 – 1 | Il-konfini tal-bidu tat-tieqa tal-gwida mingħajr klassifikatur fl-istadju 1 (struttura skarsa), espressa bħala frazzjoni tad-denoising. Settings aktar baxxi jibdew il-gwida qabel; l-intervall biss minn interval_start sa interval_end juża l-gwida, filwaqt li l-ipproċessar x'imkien ieħor isir mingħajrha. |
| `ss_guidance_interval_end` |  | number | no | `1` | 0 – 1 | Limitu tal-gwida għall-istadju 1 (struttura skarsa): agħżel valur mill-inqas daqs ss_guidance_interval_start. Il-valur jidentifika l-frazzjoni tad-denoising li tintlaħaq meta tieqaf il-gwida mingħajr klassifikatur. |
| `ss_sampling_steps` |  | integer | no | `12` | 1 – 50 | Għadd tad-denoising tal-istruttura inizjali: titjib potenzjali fil-kwalità minn passi addizzjonali jġib ipproċessar aktar bil-mod. |
| `ss_rescale_t` |  | number | no | `5` | 1 – 6 | Issettja l-qawwa tat-tranżizzjoni permezz tal-iskeda tal-istorbju tal-ġenerazzjoni tal-istruttura: iż-żieda ta’ dan il-valur tagħmel it-tranżizzjonijiet aktar qawwija. |
| `shape_slat_guidance_strength` |  | number | no | `7.5` | 0 – 10 | Kontroll tal-fedeltà tal-ġeometrija dettaljata: aderenza akbar mal-immaġni input iżżid id-dettall, bir-riskju ta’ aktar storbju. |
| `shape_slat_guidance_rescale` |  | number | no | `0.5` | 0 – 1 | Żid dan l-issettjar meta l-ġeometrija tidher storbjuża: inaqqas l-artifacts ikkawżati minn gwida qawwija matul l-istadju tal-forma. |
| `shape_slat_guidance_interval_start` |  | number | no | `0.6` | 0 – 1 | Punt ta' attivazzjoni tal-gwida mingħajr klassifikatur għar-raffinar tal-forma fl-istadju 2. Espress bħala frazzjoni tal-progress tad-denoising, jistabbilixxi interval_start; il-gwida topera biss fit-tieqa delimitata minn interval_start u interval_end. |
| `shape_slat_guidance_interval_end` |  | number | no | `1` | 0 – 1 | Limitu tal-gwida għall-istadju 2 (raffinar tal-forma): agħżel valur mill-inqas daqs shape_slat_guidance_interval_start. Il-valur jidentifika l-frazzjoni tad-denoising li tintlaħaq meta tieqaf il-gwida mingħajr klassifikatur. |
| `shape_slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | Għadd tad-denoising tar-raffinament tal-forma: ġeometrija potenzjalment aktar lixxa tiġi bi spiża fil-veloċità meta jintużaw passi addizzjonali. |
| `shape_slat_rescale_t` |  | number | no | `3` | 1 – 6 | Issettja l-qawwa tad-dettall ġeometriku permezz tal-iskeda tal-istorbju tar-raffinament tal-forma; iż-żieda ta’ dan il-valur tagħti dettalji aktar qawwija. |
| `tex_slat_guidance_strength` |  | number | no | `1` | 0 – 10 | Kontroll tal-fedeltà tal-kulur tan-nisġa: aderenza eqreb mal-kuluri fl-immaġni input f’settings ogħla żżid il-vividità iżda tista’ tikkawża saturazzjoni żejda. |
| `tex_slat_guidance_rescale` |  | number | no | `0` | 0 – 1 | Żid dan l-issettjar biex tindirizza nisġiet storbjużi jew banding tal-kulur: inaqqas l-artifacts ikkawżati minn gwida qawwija matul l-istadju tan-nisġa. |
| `tex_slat_guidance_interval_start` |  | number | no | `0.6` | 0 – 1 | Punt ta' attivazzjoni tal-gwida mingħajr klassifikatur għall-ġenerazzjoni tan-nisġa fl-istadju 3. Espress bħala frazzjoni tal-progress tad-denoising, jistabbilixxi interval_start; il-gwida topera biss fit-tieqa delimitata minn interval_start u interval_end. |
| `tex_slat_guidance_interval_end` |  | number | no | `0.9` | 0 – 1 | Limitu tal-gwida għall-istadju 3 (nisġa): agħżel valur mill-inqas daqs tex_slat_guidance_interval_start. Il-valur jidentifika l-frazzjoni tad-denoising li tintlaħaq meta tieqaf il-gwida mingħajr klassifikatur. |
| `tex_slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | Għadd tal-passi tad-denoising użati biex jinħolqu n-nisġiet. Iż-żieda tal-għadd tal-passi tieħu aktar ħin iżda tista’ tagħti nisġiet aktar nodfa. |
| `tex_slat_rescale_t` |  | number | no | `3` | 1 – 6 | Issettja l-qawwa tad-dettall tan-nisġa permezz tal-iskeda tal-istorbju tal-ġenerazzjoni tan-nisġa; iż-żieda ta’ dan il-valur tagħti dettalji aktar qawwija. |
| `decimation_target` |  | integer | no | `500000` | 5,000 – 2,000,000 | Mira għall-għadd tal-vertiċi tal-malja, b'500k rakkomandat għall-użu ġenerali u 20k–50k għall-web/mowbajl. It-tnaqqis tal-mira jiskambja d-dettall tal-malja ma' fajls iżgħar. |
| `texture_size` |  | enum (integer) | no | `2048` | `1024`, `2048`, `4096` | Riżoluzzjoni tan-nisġa tal-mesh għall-baking. Daqs akbar ta’ fajl jirriżulta minn dettall tal-wiċċ aktar fin meta tiżdied din ir-riżoluzzjoni. |
| `remesh` |  | boolean | no | `true` |  | Bini mill-ġdid tat-topoloġija li joħloq triangoli tal-malja aktar nodfa, u ġeneralment itejjeb l-adegwatezza għal użi sussegwenti bħall-animazzjoni jew l-istampar 3D, bi spiża ta' ipproċessar aktar bil-mod. |
| `remesh_band` |  | number | no | `1` | 0 – 4 | Allowance għall-moviment tar-remeshing: smoothing addizzjonali jista' jissagrifika d-dettall fin meta jiżdied dan il-valur. Is-setting jillimita l-ispostament tal-vertiċi relattiv għall-wiċċ oriġinali. |
| `remesh_project` |  | number | no | `0` | 0 – 1 | Qawwa tal-projezzjoni biex il-vertiċi remeshed jerġgħu lura għall-wiċċ oriġinali: 1 iżomm id-dettall permezz ta' projezzjoni sħiħa, filwaqt li 0 iħalli l-projezzjoni mitfija għal riżultat aktar lixx. |
| `uv_unwrap_angle_threshold_deg` |  | number | no | `90` | 0 – 180 | Limitu tal-angolu tal-grafika UV fi gradi, li jirrestrinġi kemm jistgħu jvarjaw in-normali tal-uċuħ ġirien fi grafika waħda. Żieda fil-limitu tiffavorixxi grafiċi inqas u akbar bir-riskju ta' stretching; tnaqqis tiegħu jiffavorixxi aktar grafiċi u inqas distorsjoni. |
| `uv_unwrap_refine_iterations` |  | integer | no | `0` | 0 – 10 | Għadd ta' passes ta' raffinar lokali użati biex jiġu kkalkulati l-grafiċi UV. |
| `uv_unwrap_global_iterations` |  | integer | no | `1` | 1 – 10 | Il-bilanċ tal-grafika UV jista' jitjieb billi jiżdied dan l-għadd ta' passes ta' clustering globali użati biex jiġu kkalkulati l-grafiċi. |
| `uv_unwrap_smooth_strength` |  | number | no | `1` | 0 – 10 | Aġġusta kemm jittaffew b'mod qawwi t-truf tal-grafika UV; ħjatat inqas viżibbli f'settings ogħla jġibu magħhom riskju ta' distorsjoni UV. |
| `image_url` | `image` | string (image URL) | yes |  |  | URL li jindika l-immaġni sors għall-konverżjoni 3D. |

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/trellis-2?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/trellis-2?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/trellis-2", 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": "trellis-2",
      "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": "trellis-2",
  "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
    }
  },
  "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} | Mudell 3D iġġenerat f’format GLB. |

## Related models

- [Trellis 2 · Retexture](https://doitong.com/developers/models/trellis-2/retexture.md) (`trellis-2/retexture`): from $0.20 / request
- [Trellis](https://doitong.com/developers/models/trellis.md) (`trellis`): $0.02 / request
- [Trellis · Multi](https://doitong.com/developers/models/trellis/multi.md) (`trellis/multi`): $0.02 / request
- [TRELLIS.2 LoRA Inference](https://doitong.com/developers/models/trellis-2-lora.md) (`trellis-2-lora`): 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

## Links

- HTML page: https://doitong.com/developers/models/trellis-2
- 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=trellis-2
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/trellis-2