# Cosmos 3 Super API

> Geração de texto para imagem com expansão do prompt e um modo opcional de comparação agêntica de candidatos

Cria de 1 a 4 imagens a partir de um `prompt` com até 4096 caracteres. Os lados de `image_size` são limitados ao intervalo 512-1280 px. `enable_agentic_generation` produz vários candidatos e aperfeiçoa o prompt entre rondas, com até 3 iterações. Inclui também `negative_prompt`, `guidance_scale` até 20, `num_inference_steps` até 50 e saída 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/pt-PT/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 | Descrição textual da imagem de saída pretendida. |
| `negative_prompt` |  | string | no | `` | ≤ 1024 characters | Orientação negativa que identifica cores, objetos ou artefactos indesejados a evitar na geração. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Melhoria do prompt antes da geração através do OpenRouter, produzindo a representação densa em JSON estruturado utilizada para treinar o Cosmos3 quando ativada. Se a melhoria falhar, a geração de imagens prossegue com o prompt original sem alterações. |
| `enable_agentic_generation` |  | boolean | no | `false` |  | Ciclo automático de refinamento do prompt destinado a uma maior fidelidade ao pedido original. Cada ronda gera vários candidatos de imagem e compara-os, com revisões do prompt entre rondas. |
| `agentic_max_iterations` |  | integer | no | `2` | 1 – 3 | Limite de rondas de refinamento para geração com o modo agentic ativado. |
| `agentic_samples_per_iteration` |  | integer | no | `2` | 1 – 3 | Contagem de candidatos de imagem por iteração para o ciclo agentic, determinando quantas imagens competem na avaliação antes de a melhor avançar para a reescrita do prompt. |
| `agentic_early_stop` |  | boolean | no | `true` |  | Controlo de paragem antecipada que considera suficiente uma forte correspondência entre imagem e prompt para terminar sem iterações adicionais. |
| `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` | Defina as dimensões da imagem de saída; o limite mantém cada lado entre 512 e 1280px, com comprimentos laterais restritos a múltiplos de 16. |
| `num_inference_steps` |  | integer | no | `28` | 1 – 50 | Número de passos de redução de ruído, trocando um processamento mais longo por melhor qualidade à medida que o número aumenta. |
| `guidance_scale` |  | number | no | `4` | 0 – 20 | Intensidade da orientação sem classificador. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | Número de imagens solicitado para a geração. |
| `seed` |  | integer \| null | no |  |  | Seed para geração de imagens repetível. A imagem de saída permanece inalterada entre execuções, exceto se a seed, o prompt ou a versão do modelo mudar. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Interruptor de moderação de conteúdo que abrange tanto a entrada do prompt como a saída da imagem. As contas têm de estar autorizadas para ignorar a moderação; caso contrário, as verificações permanecem obrigatórias independentemente desta definição. Qualquer imagem considerada insegura é substituída por uma imagem preta. |
| `output_format` |  | enum (string) | no | `jpeg` | `jpeg`, `png` | Formato de ficheiro da imagem resultante. |

## 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} | Imagens produzidas pelo modelo. |
| `seed` | integer | Valor da seed aplicado durante a geração. |
| `has_nsfw_concepts` | array of boolean | Estado do indicador de verificação de segurança para cada imagem gerada. |

## 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