# Veo 3.1 API

> Modèle vidéo phare de Google, clips de 4 à 8 secondes avec dialogue et son, jusqu'en 4K.

Veo 3.1 produit des séquences très réalistes avec dialogue synchronisé sur les lèvres, son ambiant et musique générés lors de la même passe, et suit précisément les instructions de caméra et d'éclairage. Les clips durent 4, 6 ou 8 secondes, en paysage ou en portrait, en 720p, 1080p ou 4K. Le son peut être désactivé pour un prix inférieur.

- Model id: `veo3.1`
- Made by: Google
- Category: Text to Video
- Output: video
- Price: from $0.20 / second (8 s ≈ $1.60) (cheapest run $1.60 (1600 API credits))
- Run: `POST https://api.doitong.com/v1/run/veo3.1`
- Quote: `POST https://api.doitong.com/v1/quote/veo3.1`
- Docs page: https://doitong.com/fr/developers/models/veo3.1

## Pricing

Price: **from $0.20 / second (8 s ≈ $1.60)** (the lowest tier; the quote prices your exact input). Billed per second of output (`duration`, default 8).

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

- When `resolution` = 4k and `generate_audio` = true: $0.60 (600 API credits) / second
- When `resolution` = 4k: $0.40 (400 API credits) / second
- When `generate_audio` = true: $0.40 (400 API credits) / second

The full example input below costs $3.20 = 3200 API credits (8 s × 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/veo3.1` 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 |  | ≤ 20000 characters | Description textuelle de la vidéo souhaitée à générer. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `16:9`, `9:16` | Rapport largeur/hauteur de la vidéo générée. |
| `duration` |  | enum (string) | no | `8s` | `4s`, `6s`, `8s` | Durée de la vidéo de sortie. |
| `negative_prompt` |  | string \| null | no |  |  | Prompt négatif utilisé pour orienter la génération vidéo. |
| `resolution` |  | enum (string) | no | `720p` | `720p`, `1080p`, `4k` | Résolution utilisée pour la vidéo de sortie. |
| `generate_audio` |  | boolean | no | `true` |  | Contrôle l’inclusion d’un audio généré dans la vidéo. |
| `seed` |  | integer \| null | no |  |  | Valeur de graine qui initialise la génération de nombres aléatoires. |
| `auto_fix` |  | boolean | no | `true` |  | Réécriture automatique des prompts pour tenter de résoudre les échecs des contrôles de politique de contenu ou d'autres validations. |
| `safety_tolerance` |  | enum (string) | no | `4` | `1`, `2`, `3`, `4`, `5`, `6` | Définissez la tolérance de modération du contenu entre le niveau le moins restrictif, 6, et le niveau le plus strict, 1, qui bloque la plupart des contenus. |

## Example input

Required parameters only:

```json
{
  "prompt": "A street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\""
}
```

A fuller example:

```json
{
  "prompt": "A street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\"",
  "duration": 8,
  "resolution": "720p"
}
```

## 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/veo3.1?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\"",
    "duration": 8,
    "resolution": "720p"
  }'

# 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/veo3.1?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\"",
    "duration": 8,
    "resolution": "720p"
  }),
});
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 street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\"",
    "duration": 8,
    "resolution": "720p",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/veo3.1", 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": "veo3.1",
      "input": {
        "prompt": "A street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\"",
        "duration": 8,
        "resolution": "720p"
      },
      "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": "veo3.1",
  "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": 3200,
    "usd": "3.20",
    "charged": 3200,
    "refunded": 0
  },
  "input": {
    "prompt": "A street interviewer in New York asks a passer-by \"Did you hear the news?\" and she laughs \"Everyone has!\"",
    "duration": 8,
    "resolution": "720p"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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 |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Vidéo produite par le modèle. |

## Related models

- [Veo 3.1 Fast](https://doitong.com/developers/models/veo3.1/fast.md) (`veo3.1/fast`): from $0.10 / second
- [Veo 3.1 Fast Image to Video](https://doitong.com/developers/models/veo3.1/fast/image-to-video.md) (`veo3.1/fast/image-to-video`): from $0.10 / second
- [Veo 3.1 Image to Video](https://doitong.com/developers/models/veo3.1/image-to-video.md) (`veo3.1/image-to-video`): from $0.20 / second
- [Veo3.1 Fast First Last Frame to Video](https://doitong.com/developers/models/veo3.1/fast/first-last-frame-to-video.md) (`veo3.1/fast/first-last-frame-to-video`): from $0.10 / second
- [Veo3.1 First Last Frame to Video](https://doitong.com/developers/models/veo3.1/first-last-frame-to-video.md) (`veo3.1/first-last-frame-to-video`): from $0.20 / second
- [Veo3.1 Reference to Video](https://doitong.com/developers/models/veo3.1/reference-to-video.md) (`veo3.1/reference-to-video`): from $0.20 / second
- [FLUX 3 Max Text to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/text-to-video.md) (`blackforestlabs/flux-3-max/text-to-video`): from $0.0425 / second of output video
- [Grok Imagine Video 1.5 Text to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/text-to-video.md) (`xai/grok-imagine-video/v1.5/text-to-video`): from $0.08 / second

## Links

- HTML page: https://doitong.com/developers/models/veo3.1
- 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=veo3.1
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/veo3.1