# Cosmos 3 Super API

> Text-zu-Bild-Generatioun mat Prompt-Erweiderung an engem optionalen agentesche Modus zum Verglach vu Kandidaten

Erstellt 1 bis 4 Biller aus engem `prompt` vu bis zu 4096 Zeechen. D'Kante vun `image_size` ginn op 512-1280 px begrenzt. `enable_agentic_generation` erstellt verschidde Kandidaten a verfeinert de Prompt tëscht den Duerchleef mat bis zu 3 Iteratiounen. Et gëtt och `negative_prompt`, `guidance_scale` bis 20, `num_inference_steps` bis 50 an jpeg- oder png-Ausgab.

- 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.com/v1/run/nvidia/cosmos-3-super/text-to-image`
- Quote: `POST https://api.doitong.com/v1/quote/nvidia/cosmos-3-super/text-to-image`
- Docs page: https://doitong.com/lb/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.com/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 | Textbeschreiwung vum gewënschten Output-Bild. |
| `negative_prompt` |  | string | no | `` | ≤ 1024 characters | Negativ Guidance, déi ongewollte Faarwen, Objeten oder Artefakter identifizéiert, déi bei der Generatioun vermeit solle ginn. |
| `enable_prompt_expansion` |  | boolean | no | `false` |  | Prompt-Verbesserung virun der Generatioun iwwer OpenRouter, déi bei Aktivéierung d'Dicht-strukturéiert JSON-Duerstellung produzéiert, mat där Cosmos3 trainéiert gëtt. Wann d'Verbesserung feelerschléit, fiert d'Bildgeneratioun mam onverännerten Prompt weider. |
| `enable_agentic_generation` |  | boolean | no | `false` |  | Automatesch Prompt-Verfeinerungsschläif, déi eng méi genee Befollegung vun der ursprénglecher Ufro ustrieft. All Ronn generéiert verschidde Bildkandidaten a vergläicht se, mat Prompt-Ännerungen tëscht de Ronnen. |
| `agentic_max_iterations` |  | integer | no | `2` | 1 – 3 | Limitt vun de Verfeinerungsronne fir d'Generatioun mat aktivéiertem agentesche Modus. |
| `agentic_samples_per_iteration` |  | integer | no | `2` | 1 – 3 | Zuel vu Bildkandidaten pro Iteratioun an der agentescher Schläif; si bestëmmt, wéi vill Biller an der Evaluatioun konkurréieren, ier dee beschte fir d'Ëmschreiwe vum Prompt virugeet. |
| `agentic_early_stop` |  | boolean | no | `true` |  | Kontroll fir de fréie Stopp, déi eng staark Iwwereneestëmmung tëscht Bild a Prompt als genuch behandelt, fir ouni weider Iteratiounen ofzeschléissen. |
| `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` | Setzt d'Dimensioune vum Output-Bild; d'Begrenzung hält all Säit tëscht 512 an 1280px, mat Säitelängten, déi op Multiple vu 16 limitéiert sinn. |
| `num_inference_steps` |  | integer | no | `28` | 1 – 50 | Unzuel vun den Entnoise-Schrëtt; méi Schrëtt bedeite méi laang Veraarbechtung, awer besser Qualitéit. |
| `guidance_scale` |  | number | no | `4` | 0 – 20 | Stäerkt vun der classifier-free Guidance. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | Ugefrote Bildzuel fir d'Generatioun. |
| `seed` |  | integer \| null | no |  |  | Seed fir reproduzéierbar Bildgeneratioun. D'Output-Bild bleift bei successive Laf onverännert, ausser de Seed, de Prompt oder d'Modellversioun ännert sech. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Schalter fir d'Inhaltsmoderatioun, déi souwuel de Prompt-Input wéi och de Bild-Output ofdeckt. Konten mussen autoriséiert sinn, fir d'Moderatioun ze ëmgoen; soss bleiwen d'Kontrollen onofhängeg vun dëser Astellung obligatoresch. All Bild, dat als onsécher bewäert gëtt, gëtt duerch e schwaarzt Bild ersat. |
| `output_format` |  | enum (string) | no | `jpeg` | `jpeg`, `png` | Dateiformat vum resultéierende Bild. |

## 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.com/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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/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.com/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.com/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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `images` | array of object {url, content_type, file_name, file_size, width, height} | Biller, déi vum Modell erstallt goufen. |
| `seed` | integer | Seed-Wäert, deen während der Generatioun applizéiert gouf. |
| `has_nsfw_concepts` | array of boolean | Status vum Sécherheetschecker fir all generéiert Bild. |

## 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.com/v1/models/nvidia/cosmos-3-super/text-to-image