# Cosmos 3 Super Image to Video API

> Anime une image de première image en vidéo, avec expansion facultative du prompt et boucle de raffinement agentique

Utilise un `image_url` comme image d'ouverture et un `prompt` de 4096 caractères maximum. `num_frames` va jusqu'à 189 et `frames_per_second` de 4 à 60. L'expansion du prompt est activée par défaut, et `enable_agentic_generation` exécute des candidats itératifs avec critique. Propose également `negative_prompt`, `guidance_scale` et `num_inference_steps` jusqu'à 50.

- Model id: `nvidia/cosmos-3-super/image-to-video`
- Made by: NVIDIA
- Category: Image to Video
- Output: video
- Price per second of your output video: from $0.05 / second of output video (cheapest run $0.05 (50 API credits))
- Run: `POST https://api.doitong.ru/v1/run/nvidia/cosmos-3-super/image-to-video`
- Quote: `POST https://api.doitong.ru/v1/quote/nvidia/cosmos-3-super/image-to-video`
- Docs page: https://doitong.com/fr/developers/models/nvidia/cosmos-3-super/image-to-video

## Pricing

Price: **from $0.05 / second of output video** (the lowest tier; the quote prices your exact input). Price per second of your output video: 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 $0.40 = 400 API credits (8 s output video × $0.05).

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/nvidia/cosmos-3-super/image-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

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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 4096 characters | Instructions de génération vidéo sous forme de texte : précisez ce que contient la scène et le mouvement qu'elle doit montrer. |
| `image_url` | `image` | string (image URL) | yes |  |  | URL d'image utilisée pour conditionner la première image de la vidéo. |
| `negative_prompt` |  | string | no | `The video captures a series of frames showing macroblocking artifacts, chromatic aberration, high-frequency noise, and rolling shutter distortion. It includes 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, bit-depth compression artifacts, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, hard cut, visual noise, and flickering. It features moiré patterns, edge halos, and temporal aliasing. Furthermore, the content defies common sense, generating illogical scenarios, nonsensical entities, absurd character behaviors, and conceptual paradoxes that violate basic human reasoning and everyday reality. The video looks like a surreal or glitchy hallucination. Overall, the video is of poor quality.` | ≤ 2048 characters | Prompt négatif destiné à décourager les contenus tels que les mouvements indésirables ou les artefacts. Son omission utilise le prompt négatif recommandé par NVIDIA pour i2v, tandis qu'une chaîne vide désactive le guidage négatif. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Expansion du prompt qui, lorsqu'elle vaut true, utilise Cosmos3-Nano Reasoner pour produire le format de légende dense utilisé pour entraîner Cosmos3 ; ce VLM examine la première image. COSMOS_PROMPT_UPSAMPLER_BASE_URL sélectionne un service Reasoner configuré ; sinon, l'application en lance un localement. En cas d'échec de l'expansion, le prompt non modifié reste utilisé. |
| `enable_agentic_generation` |  | boolean | no | `false` |  | Génération agentique itérative de Cosmos, nettement plus lente et plus coûteuse qu'une génération unique, car chaque candidat nécessite un rendu complet. La boucle augmente le prompt, génère des candidats vidéo, utilise un VLM pour critiquer les images échantillonnées et réécrit le prompt. |
| `agentic_max_iterations` |  | integer | no | `2` | 1 – 3 | Limite supérieure du nombre d'étapes du prompt lorsque la génération agentique est activée. |
| `agentic_samples_per_iteration` |  | integer | no | `2` | 1 – 3 | Nombre de candidats vidéo par itération pour la boucle agentique, déterminant combien de vidéos sont comparées lors de l'évaluation avant que la meilleure ne passe à la réécriture du prompt. |
| `agentic_early_stop` |  | boolean | no | `true` |  | Contrôle d'arrêt anticipé qui considère qu'un score du critique supérieur au seuil de qualité strict suffit à terminer la boucle agentique. |
| `image_size` |  | object {width, height} \| enum (string) | no | `{"height":480,"width":832}` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensions vidéo demandées avant l'ajustement automatique. Pour obtenir une taille prise en charge, le système borne la requête et choisit le niveau NVIDIA le plus proche — 256p, 480p ou 720p — ainsi que le format d'image pris en charge. |
| `num_frames` |  | integer | no | `189` | 5 – 189 | Nombre d'images pour la génération ; l'augmenter produit une vidéo plus longue. |
| `frames_per_second` |  | integer | no | `24` | 4 – 60 | Fréquence d'images de la vidéo de sortie, mesurée en images par seconde. |
| `num_inference_steps` |  | integer | no | `28` | 1 – 50 | Nombre d’étapes de débruitage, avec un traitement plus long mais une meilleure qualité lorsque le nombre augmente. |
| `guidance_scale` |  | number | no | `6` | 0 – 20 | Puissance du guidage sans classifieur. |
| `seed` |  | integer \| null | no |  |  | Seed contrôlant la reproductibilité : un prompt et une seed identiques produisent une vidéo identique lorsque la version du modèle ne change pas. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Contrôle de modération pour l'image et le prompt fournis, dont la désactivation est autorisée uniquement pour les comptes autorisés. Les requêtes non autorisées sont vérifiées quel que soit ce réglage. |

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
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "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.ru/v1/run/nvidia/cosmos-3-super/image-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",
    "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.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/nvidia/cosmos-3-super/image-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",
    "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.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",
    "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/nvidia/cosmos-3-super/image-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": "nvidia/cosmos-3-super/image-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "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": "nvidia/cosmos-3-super/image-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": 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",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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} | Vidéo produite par le modèle. |
| `seed` | integer | Valeur du seed appliquée pendant la génération. |

## Related models

- [Cosmos 3 Super](https://doitong.com/developers/models/nvidia/cosmos-3-super/text-to-image.md) (`nvidia/cosmos-3-super/text-to-image`): from $0.04 / run of output image
- [FLUX 3 Max Image to Video](https://doitong.com/developers/models/blackforestlabs/flux-3-max/image-to-video.md) (`blackforestlabs/flux-3-max/image-to-video`): from $0.0425 / second of output video
- [Grok Imagine Video 1.5 Image to Video](https://doitong.com/developers/models/xai/grok-imagine-video/v1.5/image-to-video.md) (`xai/grok-imagine-video/v1.5/image-to-video`): from $0.082 / second
- [Kling 3.0 Pro Image to Video](https://doitong.com/developers/models/kling-video/v3/pro/image-to-video.md) (`kling-video/v3/pro/image-to-video`): from $0.112 / second
- [LTX 2.5 Pro Image to Video](https://doitong.com/developers/models/lightricks/ltx-2.5/image-to-video/pro.md) (`lightricks/ltx-2.5/image-to-video/pro`): from $0.12 / second
- [MiniMax H3 Image to Video](https://doitong.com/developers/models/minimax/h3/image-to-video.md) (`minimax/h3/image-to-video`): from $0.05 / second
- [Seedance 2.0 Fast Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/image-to-video.md) (`bytedance/seedance-2.0/fast/image-to-video`): from $0.113 / second
- [Seedance 2.0 Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/image-to-video.md) (`bytedance/seedance-2.0/image-to-video`): from $0.141 / second

## Links

- HTML page: https://doitong.com/developers/models/nvidia/cosmos-3-super/image-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=nvidia/cosmos-3-super/image-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/nvidia/cosmos-3-super/image-to-video