# Cosmos Predict 2.5 2B · Text to Video API

> Cosmos Predict 2.5 2B texte vers vidéo standard avec échelle de guidage et jusqu'à 50 étapes

Génère une vidéo uniquement depuis un `prompt` textuel. Définissez `num_frames` entre 9 et 93, `num_inference_steps` jusqu'à 50 (35 par défaut) et `guidance_scale` de 1 à 20. Un `negative_prompt` est disponible et la sortie peut être en mp4, webm, mov ou GIF, avec une qualité de low à maximum.

- Model id: `cosmos-predict-2.5/text-to-video`
- Made by: NVIDIA
- Category: Text to Video
- Output: video
- Price: $0.20 / video (cheapest run $0.20 (200 API credits))
- Run: `POST https://api.doitong.ru/v1/run/cosmos-predict-2.5/text-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/cosmos-predict-2.5/text-to-video`
- Docs page: https://doitong.com/fr/developers/models/cosmos-predict-2.5/text-to-video

## Pricing

Price: **$0.20 / video**. Billed once per generated video.

The full example input below costs $0.20 = 200 API credits (1 video × 200 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/cosmos-predict-2.5/text-to-video` 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 |  |  | Description textuelle de la vidéo souhaitée. |
| `negative_prompt` |  | string | no | `The video captures a series of frames showing ugly scenes, static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, artifacting, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, visual noise, and flickering. Overall, the video is of poor quality.` |  | Prompt négatif indiquant le contenu indésirable à éviter lors de la génération. |
| `num_frames` |  | integer | no | `93` | 9 – 93 | Nombre d’images pour la génération, compris entre 9 et 93. |
| `num_inference_steps` |  | integer | no | `35` | 1 – 50 | Nombre d’étapes de débruitage, avec un traitement plus long mais une meilleure qualité lorsque le nombre augmente. |
| `guidance_scale` |  | number | no | `7` | 1 – 20 | Échelle du guidage sans classifieur ; l’augmenter amène la génération à suivre plus étroitement le prompt. |
| `seed` |  | integer \| null | no |  |  | Seed aléatoire rendant la génération reproductible. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Format de la vidéo résultante. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Paramètre de qualité de la vidéo résultante. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Le filtrage peut être assoupli 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/cosmos-predict-2.5/text-to-video?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/cosmos-predict-2.5/text-to-video?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/cosmos-predict-2.5/text-to-video", 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": "cosmos-predict-2.5/text-to-video",
      "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": "cosmos-predict-2.5/text-to-video",
  "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": {
    "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42
  },
  "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, width, height, fps, duration, num_frames} | Fichier vidéo produit par la génération. |
| `seed` | integer | Graine contrôlant l’aléatoire pendant la génération. |

## Related models

- [Cosmos Predict 2.5 2B Distilled](https://doitong.com/developers/models/cosmos-predict-2.5/distilled/text-to-video.md) (`cosmos-predict-2.5/distilled/text-to-video`): $0.08 / video
- [Cosmos Predict 2.5 2B · Image to Video](https://doitong.com/developers/models/cosmos-predict-2.5/image-to-video.md) (`cosmos-predict-2.5/image-to-video`): $0.20 / video
- [Cosmos Predict 2.5 2B · Video to Video](https://doitong.com/developers/models/cosmos-predict-2.5/video-to-video.md) (`cosmos-predict-2.5/video-to-video`): $0.20 / video
- [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
- [Kling 3.0 Pro Text to Video](https://doitong.com/developers/models/kling-video/v3/pro/text-to-video.md) (`kling-video/v3/pro/text-to-video`): from $0.112 / second
- [LTX 2.5 Pro Text to Video](https://doitong.com/developers/models/lightricks/ltx-2.5/text-to-video/pro.md) (`lightricks/ltx-2.5/text-to-video/pro`): from $0.12 / second
- [MiniMax H3 Text to Video](https://doitong.com/developers/models/minimax/h3/text-to-video.md) (`minimax/h3/text-to-video`): from $0.05 / second

## Links

- HTML page: https://doitong.com/developers/models/cosmos-predict-2.5/text-to-video
- 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=cosmos-predict-2.5/text-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/cosmos-predict-2.5/text-to-video