NVIDIA modelsimage generation api

nvidia/cosmos-3-super/text-to-image

Name: Cosmos 3 Super
Author: NVIDIA

Cosmos 3 Super by NVIDIA - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.

Input

Prompt(string)

Text prompt describing the image to generate.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Guidance scale (CFG)(number)

020

Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity. Range: 0 to 20.

Num Inference Steps(integer)

150

Number of denoising steps. More steps yield higher quality but take longer. Range: 1 to 50.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Seed(integer)

The same seed and prompt given to the same model version will produce the same image every time.

Agentic Early Stop(boolean)

Stop early when a candidate image is already a strong match for the prompt.

Agentic Max Iterations(integer)

Maximum number of refinement rounds when agentic generation is enabled. Range: 1 to 3.

Enable Agentic Generation(boolean)

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.

Agentic Samples Per Iteration(integer)

Candidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage. Range: 1 to 3.

Num Images(integer)

Minimum: 1.

Enable Prompt Expansion(boolean)

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDnvidia/cosmos-3-super/text-to-image

Input Schema

12 parameters · 1 required · 11 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Text prompt describing the image to generate. · Min length: 1 · Max length: 4096
`seed`	integer	Optional	The same seed and prompt given to the same model version will produce the same image every time.
`num_images`	integer	Optional	Min: 1 · Default: 1
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16
`output_format`	string	Optional	The format of the generated image. · Options: jpeg, png · Default: "jpeg" jpegpng
`guidance_scale`	number	Optional	Classifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity. · Min: 0 · Max: 20 · Default: 4
`agentic_early_stop`	boolean	Optional	Stop early when a candidate image is already a strong match for the prompt. · Default: true
`num_inference_steps`	integer	Optional	Number of denoising steps. More steps yield higher quality but take longer. · Min: 1 · Max: 50 · Default: 28
`agentic_max_iterations`	integer	Optional	Maximum number of refinement rounds when agentic generation is enabled. · Min: 1 · Max: 3 · Default: 2
`enable_prompt_expansion`	boolean	Optional	Default: false
`enable_agentic_generation`	boolean	Optional	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
`agentic_samples_per_iteration`	integer	Optional	Candidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage. · Min: 1 · Max: 3 · Default: 2

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "nvidia/cosmos-3-super/text-to-image",
  "prompt": "A photorealistic close-up of two damp hands shaping a spinning cylinder of wet gray clay on a pottery wheel, fingers pinching the walls upward into a narrow-necked vase, water glistening on the clay, soft studio lighting, shallow depth of field.",
  "num_images": 1,
  "output_format": "jpeg",
  "guidance_scale": 4,
  "agentic_early_stop": true,
  "num_inference_steps": 28,
  "agentic_max_iterations": 2,
  "enable_prompt_expansion": false,
  "enable_agentic_generation": false,
  "agentic_samples_per_iteration": 2
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Cosmos 3 Super

API README

PRICED DRAFT — MANUAL REVIEW REQUIRED exact_model_mode: nvidia/cosmos-3-super/text-to-image original_unit: Your request will cost $0.04 per generated image. Prompt expansion adds $0.02 per request when enabled. Agentic generation bills for every candidate image generated during selection, not just the final returned image. method: per-generated-candidate plus optional prompt-expansion request price result_base_price: 0.04 result_price_formula: (usage.output_count ?? ((params.enable_agentic_generation ?? false) ? (params.agentic_samples_per_iteration ?? 2) * (params.agentic_max_iterations ?? 2) : (params.num_images ?? 1))) * 0.04 + ((params.enable_prompt_expansion ?? false) ? 0.02 : 0) review_status: pending; model remains disabled checked_at: 2026-08-16