# PixVerse V4 Text To Video Fast API

> Variante texte-vidéo V4 plus rapide, plafonnée à 720p et sans option de durée

Version plus rapide du modèle V4 de texte à vidéo. Il accepte une invite textuelle `prompt` et offre une sortie en 360p, 540p ou 720p, sans 1080p ni paramètre `duration`. Cinq proportions, de 16:9 à 9:16, sont prises en charge, ainsi que `negative_prompt`, `seed` et un préréglage `style` (anime, 3d_animation, clay, comic, cyberpunk). Les invites sont limitées à 2048 octets UTF-8.

- Model id: `pixverse/v4/text-to-video/fast`
- Made by: PixVerse
- Category: Text to Video
- Output: video
- Price: from $0.30 / request (cheapest run $0.30 (300 API credits))
- Run: `POST https://api.doitong.ru/v1/run/pixverse/v4/text-to-video/fast`
- Quote: `POST https://api.doitong.ru/v1/quote/pixverse/v4/text-to-video/fast`
- Docs page: https://doitong.com/fr-CA/developers/models/pixverse/v4/text-to-video/fast

## 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` = 720p: $0.40 (400 API credits) / request
- When `resolution` = 1080p: $0.80 (800 API credits) / request

The full example input below costs $0.40 = 400 API credits (1 request × 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.ru/v1/quote/pixverse/v4/text-to-video/fast` 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 |  |  | Invite de génération vidéo avec une limite de taille en octets : même un texte visuellement court peut la dépasser lorsque les émojis, les lettres accentuées ou les caractères non latins occupent plusieurs octets par caractère. La longueur encodée maximale est de 2048 octets en UTF-8; le nombre de caractères ne détermine pas si elle respecte la limite. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Rapport largeur/hauteur de la vidéo de sortie. |
| `resolution` |  | enum (string) | no | `720p` | `360p`, `540p`, `720p` | Résolution de la vidéo de sortie. |
| `negative_prompt` |  | string | no | `` |  | Invite négative de génération avec une limite de longueur en octets : même un texte visuellement court peut dépasser la limite, car les émojis, les lettres accentuées et les caractères non latins occupent plusieurs octets. Le maximum est de 2048 octets mesurés en UTF-8, et non un nombre de caractères. |
| `style` |  | enum (string) \| null | no |  | `anime`, `3d_animation`, `clay`, `comic`, `cyberpunk` | Style appliqué à la vidéo générée. |
| `seed` |  | integer \| null | no |  |  | Graine pour une génération vidéo reproductible. Une reproduction exacte à chaque exécution nécessite une version du modèle, une invite et une graine inchangées. |
| `enable_safety_checker` |  | boolean | no | `true` |  | La vérification peut être assouplie en définissant false, si l’appelant est autorisé. |

## 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.ru/v1/run/pixverse/v4/text-to-video/fast?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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/pixverse/v4/text-to-video/fast?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.ru/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/pixverse/v4/text-to-video/fast", 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.ru/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": "pixverse/v4/text-to-video/fast",
      "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": "pixverse/v4/text-to-video/fast",
  "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": 400,
    "usd": "0.40",
    "charged": 400,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/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

- [PixVerse V3.5 Text To Video](https://doitong.com/developers/models/pixverse/v3.5/text-to-video.md) (`pixverse/v3.5/text-to-video`): from $0.15 / run
- [PixVerse V3.5 Text To Video Fast](https://doitong.com/developers/models/pixverse/v3.5/text-to-video/fast.md) (`pixverse/v3.5/text-to-video/fast`): from $0.30 / request
- [PixVerse V4 Text To Video](https://doitong.com/developers/models/pixverse/v4/text-to-video.md) (`pixverse/v4/text-to-video`): from $0.15 / run
- [PixVerse Swap](https://doitong.com/developers/models/pixverse/swap.md) (`pixverse/swap`): from $0.15 / run
- [PixVerse V3.5 Effects](https://doitong.com/developers/models/pixverse/v3.5/effects.md) (`pixverse/v3.5/effects`): from $0.15 / run
- [PixVerse V3.5 Image To Video](https://doitong.com/developers/models/pixverse/v3.5/image-to-video.md) (`pixverse/v3.5/image-to-video`): from $0.15 / run
- [PixVerse V3.5 Image To Video Fast](https://doitong.com/developers/models/pixverse/v3.5/image-to-video/fast.md) (`pixverse/v3.5/image-to-video/fast`): from $0.30 / request
- [PixVerse V3.5 Transition](https://doitong.com/developers/models/pixverse/v3.5/transition.md) (`pixverse/v3.5/transition`): from $0.15 / run

## Links

- HTML page: https://doitong.com/developers/models/pixverse/v4/text-to-video/fast
- 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=pixverse/v4/text-to-video/fast
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/pixverse/v4/text-to-video/fast