# Tripo H3.1 Text to 3D API

> Text-to-3D mesh generator with negative prompt, separate geometry and texture quality tiers, and a very high face cap

Builds a 3D model from a text description of up to 1024 characters, with an optional `negative_prompt` for features to avoid. `face_limit` accepts 1,000 to 2,000,000 faces. `geometry_quality` and `texture_quality` can each be standard or detailed. Options include PBR materials, quad topology, auto-scaling to real-world size, and separate seeds for geometry, the text-to-image step and texture.

- Model id: `tripo3d/h3.1/text-to-3d`
- Made by: Tripo
- Category: Text to 3D
- Output: 3d
- Price per run: from $0.10 / run (cheapest run $0.10 (100 API credits))
- Run: `POST https://api.doitong.com/v1/run/tripo3d/h3.1/text-to-3d`
- Quote: `POST https://api.doitong.com/v1/quote/tripo3d/h3.1/text-to-3d`
- Docs page: https://doitong.com/developers/models/tripo3d/h3.1/text-to-3d

## Pricing

Price: **from $0.10 / run** (the lowest tier; the quote prices your exact input). Price per run: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.20 = 200 API credits (1 run × $0.20).

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/tripo3d/h3.1/text-to-3d` 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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | ≤ 1024 characters | Description in text of the desired 3D object, limited to 1024 characters. |
| `negative_prompt` |  | string \| null | no |  | ≤ 1024 characters | Description of features that should be excluded from the generated model. |
| `face_limit` |  | integer \| null | no |  | 1,000 – 2,000,000 | Explicit face-count target for mesh generation, overriding the model's adaptive count selection when supplied. |
| `texture` |  | boolean | no | `true` |  | Controls whether the model receives generated textures. |
| `pbr` |  | boolean | no | `true` |  | Enable PBR materials (Physically Based Rendering), which also turns on texture generation when true. |
| `model_seed` |  | integer \| null | no |  |  | Seed used to make geometry generation reproducible. |
| `image_seed` |  | integer \| null | no |  |  | Seed used during the text-to-image stage. |
| `texture_seed` |  | integer \| null | no |  |  | Seed used to make texture generation reproducible. |
| `texture_quality` |  | enum (string) | no | `standard` | `standard`, `detailed` | Texture quality setting; choosing 'detailed' increases texture resolution. |
| `geometry_quality` |  | enum (string) | no | `standard` | `standard`, `detailed` | Quality setting for the geometry. |
| `auto_size` |  | boolean | no | `false` |  | Automatic scaling to give the model real-world dimensions measured in meters. |
| `quad` |  | boolean | no | `false` |  | Choose between triangular faces and quads with 4 sides by enabling quad topology. For quad results, an FBX file is returned whenever Tripo supplies the data as FBX bytes. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Screening can be relaxed by setting false, provided the caller is authorized. |

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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/tripo3d/h3.1/text-to-3d?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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/tripo3d/h3.1/text-to-3d?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/tripo3d/h3.1/text-to-3d", 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": "tripo3d/h3.1/text-to-3d",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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": "tripo3d/h3.1/text-to-3d",
  "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": 200,
    "usd": "0.20",
    "charged": 200,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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_urls": {
      "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
      },
      "fbx": {
        "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
      },
      "base_model": {
        "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
      },
      "pbr_model": {
        "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
      }
    },
    "rendered_image": {
      "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
    },
    "task_id": "string"
  },
  "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} | GLB or FBX file containing the generated 3D model, with the format determined by what Tripo produces. |
| `model_urls` | object {glb, fbx, base_model, pbr_model} | URLs pointing to alternative versions of the 3D model. |
| `rendered_image` | object {url, content_type, file_name, file_size} \| null | Rendered preview showing the generated 3D model. |
| `task_id` | string \| null | Reusable Tripo task ID identifying the generated model for rig or rig-check, allowing those operations without another model upload. |

## Related models

- [Tripo H3.1 Image to 3D](https://doitong.com/developers/models/tripo3d/h3.1/image-to-3d.md) (`tripo3d/h3.1/image-to-3d`): from $0.20 / run
- [Tripo H3.1 Multiview to 3D](https://doitong.com/developers/models/tripo3d/h3.1/multiview-to-3d.md) (`tripo3d/h3.1/multiview-to-3d`): from $0.20 / run
- [Tripo P1 Text to 3D](https://doitong.com/developers/models/tripo3d/p1/text-to-3d.md) (`tripo3d/p1/text-to-3d`): $1.10 / run
- [Tripo P2 Text to 3D](https://doitong.com/developers/models/tripo3d/p2/text-to-3d.md) (`tripo3d/p2/text-to-3d`): from $1.00 / run
- [Hunyuan 3d](https://doitong.com/developers/models/hunyuan-3d/v3.1/rapid/text-to-3d.md) (`hunyuan-3d/v3.1/rapid/text-to-3d`): from $0.225 / request
- [Hunyuan 3D Pro Text to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/pro/text-to-3d.md) (`hunyuan-3d/v3.1/pro/text-to-3d`): $0.375 / run
- [Hunyuan Motion \[0.46B\]](https://doitong.com/developers/models/hunyuan-motion/fast.md) (`hunyuan-motion/fast`): $0.06 / request
- [Hunyuan Motion \[1B\]](https://doitong.com/developers/models/hunyuan-motion.md) (`hunyuan-motion`): $0.08 / request

## Links

- HTML page: https://doitong.com/developers/models/tripo3d/h3.1/text-to-3d
- 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=tripo3d/h3.1/text-to-3d
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/tripo3d/h3.1/text-to-3d