Cosmos 3 Super

Liveby NVIDIA

Cosmos3 is a collection of Omnimodal world models capable of generating dynamic, high-quality video, image, audio, and action commands from combinations of text, image, video, and action trajectory inputs.

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Make an image with Cosmos 3 Super: a cozy coffee shop in São Paulo at golden hour.

Create a product photo of our new sneaker on a white background.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Image generation API by NVIDIA, callable through Superpowers. It costs $0.043 per image, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.nvidia-cosmos-3-super-text-to-image", or over MCP with run_tool. 88 other providers in this category take the same input and can be compared side by side.

Tool id
Price per call: $0.043 / image

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.nvidia-cosmos-3-super-text-to-image","input":{"prompt":""},"idempotency_key":"example-request-1"}'

Input

15 fields · 1 required

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "agentic_samples_per_iteration": {
      "type": "integer",
      "description": "Candidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage.",
      "default": 2
    },
    "agentic_early_stop": {
      "type": "boolean",
      "description": "Stop early when a candidate image is already a strong match for the prompt.",
      "default": true
    },
    "sync_mode": {
      "type": "boolean",
      "description": "If `True`, the image is returned as a data URI and the output data won't be available in the request history.",
      "default": false
    },
    "negative_prompt": {
      "type": "string",
      "description": "Content to steer the generation away from (colors, objects, artifacts).",
      "default": ""
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "Enable content moderation for the input prompt and generated images. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images.",
      "default": true
    },
    "output_format": {
      "type": "string",
      "description": "The format of the generated image.",
      "default": "jpeg",
      "enum": [
        "jpeg",
        "png"
      ]
    },
    "enable_prompt_expansion": {
      "type": "boolean",
      "description": "Expand the prompt with OpenRouter before image generation. When enabled, the prompt is rewritten into the dense structured-JSON format Cosmos3 was trained on; generation falls back to the raw prompt if expansion fails.",
      "default": false
    },
    "num_images": {
      "type": "integer",
      "description": "The number of images to generate.",
      "default": 1
    },
    "num_inference_steps": {
      "type": "integer",
      "description": "Number of denoising steps. More steps yield higher quality but take longer.",
      "default": 28
    },
    "agentic_max_iterations": {
      "type": "integer",
      "description": "Maximum number of refinement rounds when agentic generation is enabled.",
      "default": 2
    },
    "enable_agentic_generation": {
      "type": "boolean",
      "description": "Automatically generate and compare multiple candidate images, then refine the prompt between rounds to better match the original request. This can improve prompt adherence but increases latency and billable image generations.",
      "default": false
    },
    "prompt": {
      "type": "string",
      "description": "Text prompt describing the image to generate."
    },
    "guidance_scale": {
      "type": "number",
      "description": "Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity.",
      "default": 4
    },
    "seed": {
      "type": "integer",
      "description": "The same seed and prompt given to the same model version will produce the same image every time."
    },
    "image_size": {
      "type": "string",
      "description": "The size of the generated image. Each edge is clamped to 512-1280px (multiples of 16).",
      "default": "square_hd",
      "enum": [
        "square_hd",
        "square",
        "portrait_4_3",
        "portrait_16_9",
        "landscape_4_3",
        "landscape_16_9"
      ]
    }
  }
}