# Cosmos 3 Super API

> Génération texte-image avec expansion du prompt et mode facultatif de comparaison agentique de candidats

Crée de 1 à 4 images à partir d’un `prompt` de 4096 caractères maximum. Les dimensions de `image_size` sont limitées à 512-1280 px. `enable_agentic_generation` produit plusieurs candidats et affine le prompt entre les tours, avec jusqu’à 3 itérations. Inclut aussi `negative_prompt`, `guidance_scale` jusqu’à 20, `num_inference_steps` jusqu’à 50 et une sortie jpeg ou png.

- Model id: `nvidia/cosmos-3-super/text-to-image`
- Made by: NVIDIA
- Category: Text to Image
- Output: image
- Price per run: from $0.04 / run of output image (cheapest run $0.04 (40 API credits))
- Run: `POST https://api.doitong.ru/v1/run/nvidia/cosmos-3-super/text-to-image`
- Quote: `POST https://api.doitong.ru/v1/quote/nvidia/cosmos-3-super/text-to-image`
- Docs page: https://doitong.com/fr/developers/models/nvidia/cosmos-3-super/text-to-image

## Pricing

Price: **from $0.04 / run of output image** (the lowest tier; the quote prices your exact input). Price per run: 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 $0.04 = 40 API credits (1 run × $0.04).

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/text-to-image` 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 | Description textuelle de l'image de sortie souhaitée. |
| `negative_prompt` |  | string | no | `` | ≤ 1024 characters | Guidage négatif identifiant les couleurs, objets ou artefacts indésirables que la génération doit éviter. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Amélioration du prompt avant génération via OpenRouter, produisant la représentation dense en JSON structuré utilisée pour entraîner Cosmos3 lorsqu'elle est activée. En cas d'échec, la génération d'image se poursuit avec le prompt non modifié. |
| `enable_agentic_generation` |  | boolean | no | `false` |  | Boucle automatique d'affinement du prompt visant une meilleure fidélité à la requête d'origine. Chaque tour génère plusieurs images candidates et les compare, avec des révisions du prompt entre les tours. |
| `agentic_max_iterations` |  | integer | no | `2` | 1 – 3 | Limite de tours d'affinement pour la génération lorsque le mode agentique est activé. |
| `agentic_samples_per_iteration` |  | integer | no | `2` | 1 – 3 | Nombre d'images candidates par itération pour la boucle agentique, déterminant combien d'images 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'une forte correspondance image-prompt suffit à terminer sans autres itérations. |
| `image_size` |  | object {width, height} \| enum (string) | no | `square_hd` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Définissez les dimensions de l'image de sortie ; le bornage maintient chaque côté entre 512 et 1280px, les longueurs étant limitées aux multiples de 16. |
| `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 | `4` | 0 – 20 | Puissance du guidage sans classifieur. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | Nombre d'images demandé pour la génération. |
| `seed` |  | integer \| null | no |  |  | Seed pour une génération d'image reproductible. L'image de sortie reste inchangée d'une exécution à l'autre, sauf si la seed, le prompt ou la version du modèle change. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Commutateur de modération du contenu couvrant à la fois l'entrée du prompt et la sortie image. Les comptes doivent être autorisés à contourner la modération ; sinon, les vérifications restent obligatoires quel que soit ce réglage. Toute image jugée dangereuse est remplacée par une image noire. |
| `output_format` |  | enum (string) | no | `jpeg` | `jpeg`, `png` | Format de fichier de l'image obtenue. |

## 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/nvidia/cosmos-3-super/text-to-image?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/nvidia/cosmos-3-super/text-to-image?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/nvidia/cosmos-3-super/text-to-image", 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/text-to-image",
      "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": "nvidia/cosmos-3-super/text-to-image",
  "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": 40,
    "usd": "0.04",
    "charged": 40,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "images": [
      {
        "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
      }
    ],
    "seed": 42,
    "has_nsfw_concepts": [
      false
    ]
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "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 |
|---|---|---|
| `images` | array of object {url, content_type, file_name, file_size, width, height} | Images produites par le modèle. |
| `seed` | integer | Valeur du seed appliquée pendant la génération. |
| `has_nsfw_concepts` | array of boolean | État du contrôle de sécurité pour chaque image générée. |

## Related models

- [Cosmos 3 Super Image to Video](https://doitong.com/developers/models/nvidia/cosmos-3-super/image-to-video.md) (`nvidia/cosmos-3-super/image-to-video`): from $0.05 / second of output video
- [FLUX.1 \[dev\]](https://doitong.com/developers/models/flux/dev.md) (`flux/dev`): $0.025 / megapixel
- [FLUX.1 \[schnell\]](https://doitong.com/developers/models/flux/schnell.md) (`flux/schnell`): $0.003 / megapixel
- [FLUX.2 \[dev\]](https://doitong.com/developers/models/flux-2.md) (`flux-2`): $0.012 / megapixel
- [FLUX.2 \[pro\]](https://doitong.com/developers/models/flux-2-pro.md) (`flux-2-pro`): $0.015 / megapixel of output image
- [GPT Image 2.5 Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/text-to-image.md) (`openai/gpt-image-2.5/flare/text-to-image`): from $0.008 / image
- [Ideogram V4.5](https://doitong.com/developers/models/ideogram/v4.5.md) (`ideogram/v4.5`): from $0.03 / image
- [Nano Banana 2](https://doitong.com/developers/models/nano-banana-2.md) (`nano-banana-2`): from $0.06 / image

## Links

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