# Triposplat API

> Convertit une image en fichier de splats gaussiens 3D, exporté au format .ply ou .splat

Génère un splat gaussien 3D à partir d'une seule image (`image_url`) plutôt que d'un maillage. `num_gaussians` va de 32,768 à 262,144 et `output_format` vaut ply ou splat. Vous pouvez aussi définir `num_inference_steps` (1-50), `guidance_scale` et `seed`. La réponse inclut le nombre réel de gaussiennes ainsi que l'image sans arrière-plan utilisée par le modèle.

- Model id: `tripo3d/triposplat`
- Made by: Tripo
- Category: Image to 3D
- Output: 3d
- Price: $0.05 / request (cheapest run $0.05 (50 API credits))
- Run: `POST https://api.doitong.com/v1/run/tripo3d/triposplat`
- Quote: `POST https://api.doitong.com/v1/quote/tripo3d/triposplat`
- Docs page: https://doitong.com/fr/developers/models/tripo3d/triposplat

## Pricing

Price: **$0.05 / request**. Billed once per request.

The full example input below costs $0.05 = 50 API credits (1 request × 50 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/tripo3d/triposplat` 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 de l'image source pour la conversion en nuage de points gaussiens 3D. |
| `num_gaussians` |  | integer | no | `262144` | 32,768 – 262,144 | Nombre de Gaussiens souhaité pour le nuage généré, arrondi en interne au multiple de 32 le plus proche. L'augmenter ajoute des détails, mais augmente également la taille du fichier et ralentit le rendu. |
| `num_inference_steps` |  | integer | no | `20` | 1 – 50 | Nombre d'étapes pour l'échantillonneur flow-matching. |
| `guidance_scale` |  | number | no | `3` | 0 – 10 | Contrôle du guidage sans classifieur : des paramètres plus élevés ajoutent des détails et rapprochent le résultat de l'image source, au risque de couleurs sursaturées. Le guidage est désactivé à 1.0 ou moins. |
| `output_format` |  | enum (string) | no | `ply` | `ply`, `splat` | Format du fichier de sortie du nuage de points gaussiens. |
| `seed` |  | integer \| null | no |  |  | Graine utilisée pour reproduire les résultats. La valeur None sélectionne une graine aléatoire. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Activation du contrôle de sécurité de l'image source. |

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/tripo3d/triposplat?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/tripo3d/triposplat?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/tripo3d/triposplat", 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/triposplat",
      "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": "tripo3d/triposplat",
  "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": 50,
    "usd": "0.05",
    "charged": 50,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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
    },
    "preprocessed_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,
      "width": 1024,
      "height": 768
    },
    "num_gaussians": 1,
    "seed": 42,
    "timings": {}
  },
  "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} | Fichier de sortie contenant le nuage de points gaussiens 3D, au format .ply ou .splat. |
| `preprocessed_image` | object {url, content_type, file_name, file_size, width, height} | Image effectivement utilisée par le modèle : composition RGB affichant le premier plan sur fond noir après suppression de l'arrière-plan. |
| `num_gaussians` | integer | Nombre réel de Gaussiens générés. |
| `seed` | integer | Valeur du seed appliquée pendant la génération. |
| `timings` | object | Temps consacré à chaque étape, mesuré en secondes. |

## Related models

- [Tripo3D · Image to 3D](https://doitong.com/developers/models/tripo3d/tripo/v2.5/image-to-3d.md) (`tripo3d/tripo/v2.5/image-to-3d`): from $0.20 / run
- [Tripo3D · Multiview to 3D](https://doitong.com/developers/models/tripo3d/tripo/v2.5/multiview-to-3d.md) (`tripo3d/tripo/v2.5/multiview-to-3d`): from $0.20 / run
- [Tripo3D Remesh](https://doitong.com/developers/models/tripo3d/tripo/remesh.md) (`tripo3d/tripo/remesh`): $0.40 / run
- [Tripo3D Segment](https://doitong.com/developers/models/tripo3d/tripo/segment.md) (`tripo3d/tripo/segment`): $0.40 / run
- [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 Image to 3D](https://doitong.com/developers/models/tripo3d/p1/image-to-3d.md) (`tripo3d/p1/image-to-3d`): from $0.40 / request
- [Tripo P2 Image to 3D](https://doitong.com/developers/models/tripo3d/p2/image-to-3d.md) (`tripo3d/p2/image-to-3d`): from $1.00 / run

## Links

- HTML page: https://doitong.com/developers/models/tripo3d/triposplat
- 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/triposplat
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/tripo3d/triposplat