Pixazo APIModelsCosmos
Pixazo APIModelsCosmos

Cosmos 3 Super API - AI Image & Video Generation APIs: Pricing, Documentation

by NVIDIA

Cosmos 3 Super API delivers a unified, high-performance integration layer designed to streamline complex data workflows and accelerate digital transformation across enterprise ecosystems. This robust solution offers developers seamless connectivity, exceptional uptime, and low-latency processing to handle demanding workloads without compromising on speed or reliability. With its intuitive architecture and advanced security protocols, the platform simplifies API management, automates routine tasks, and scales effortlessly to meet growing business demands. By eliminating operational bottlenecks and ensuring data consistency across various internal endpoints, it empowers organizations to optimize their software architecture and unlock maximum technical efficiency.

Get API Key
Cosmos API

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

Cosmos 3 Super API Documentation

https://gateway.pixazo.ai/cosmos-3-super-text-to-image/v1/cosmos-3-super-text-to-image-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

Cosmos 3 Super Text to Image generate request

Request Code

POST https://gateway.pixazo.ai/cosmos-3-super-text-to-image/v1/cosmos-3-super-text-to-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A futuristic mountain observatory under a star-filled sky, cinematic lighting, photorealistic",
  "negative_prompt": "",
  "image_size": "square_hd",
  "num_inference_steps": 28,
  "guidance_scale": 4,
  "num_images": 1,
  "output_format": "jpeg",
  "enable_prompt_expansion": false,
  "enable_safety_checker": true,
  "sync_mode": false
}
import requests

url = "https://gateway.pixazo.ai/cosmos-3-super-text-to-image/v1/cosmos-3-super-text-to-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A futuristic mountain observatory under a star-filled sky, cinematic lighting, photorealistic",
    "negative_prompt": "",
    "image_size": "square_hd",
    "num_inference_steps": 28,
    "guidance_scale": 4,
    "num_images": 1,
    "output_format": "jpeg",
    "enable_prompt_expansion": false,
    "enable_safety_checker": true,
    "sync_mode": false
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = "https://gateway.pixazo.ai/cosmos-3-super-text-to-image/v1/cosmos-3-super-text-to-image-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "A futuristic mountain observatory under a star-filled sky, cinematic lighting, photorealistic",
  "negative_prompt": "",
  "image_size": "square_hd",
  "num_inference_steps": 28,
  "guidance_scale": 4,
  "num_images": 1,
  "output_format": "jpeg",
  "enable_prompt_expansion": false,
  "enable_safety_checker": true,
  "sync_mode": false
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));
curl -X POST "https://gateway.pixazo.ai/cosmos-3-super-text-to-image/v1/cosmos-3-super-text-to-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A futuristic mountain observatory under a star-filled sky, cinematic lighting, photorealistic",
    "negative_prompt": "",
    "image_size": "square_hd",
    "num_inference_steps": 28,
    "guidance_scale": 4,
    "num_images": 1,
    "output_format": "jpeg",
    "enable_prompt_expansion": false,
    "enable_safety_checker": true,
    "sync_mode": false
  }'

Output

{
  "request_id": "cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Cosmos 3 Super Text to Image generate request

Parameter Required Type Default Allowed values / range Description
promptYesstring1–4096 charactersText prompt for image generation (1-4096 characters).
negative_promptNostring""≤ 1024 charactersContent to steer away from during generation (max 1024 characters).
enable_prompt_expansionNobooleanfalseAutomatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_agentic_generationNobooleanfalseEnable iterative generation and comparison of multiple candidate images. Each candidate is billed separately.
agentic_max_iterationsNointeger21–3Maximum refinement rounds (1-3). Only applies if enable_agentic_generation is true.
agentic_samples_per_iterationNointeger21–3Number of candidate images generated per iteration (1-3). Only applies if enable_agentic_generation is true.
agentic_early_stopNobooleantrueStop refinement early if a candidate is deemed a strong match. Only applies if enable_agentic_generation is true.
image_sizeNostring or object"square_hd""square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9", or {width: integer, height: integer}Preset aspect ratios: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Alternatively, provide a custom object: {"width": integer, "height": integer}.
num_inference_stepsNointeger281–50Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scaleNofloat40–20Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
num_imagesNointeger11–4Number of images to generate (1-4). Each image is billed at $0.04.
output_formatNostring"jpeg""jpeg", "png"Output image format. Allowed: jpeg, png.
enable_safety_checkerNobooleantrueTurns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
seedNointegerRandom seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_modeNobooleanfalseIf on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Example Request

{
  "prompt": "A futuristic mountain observatory under a star-filled sky, cinematic lighting, photorealistic",
  "negative_prompt": "",
  "image_size": "square_hd",
  "num_inference_steps": 28,
  "guidance_scale": 4,
  "num_images": 1,
  "output_format": "jpeg",
  "enable_prompt_expansion": false,
  "enable_safety_checker": true,
  "sync_mode": false
}

Response

{
  "request_id": "cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'cosmos-3-super-text-to-image' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "cosmos-3-super-text-to-image",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "cosmos-3-super-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "cosmos-3-super-text-to-image",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/cosmos-3-super-text-to-image_019dxxxx/output.jpg"],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Cosmos 3 Super API Pricing

UsagePrice (USD)
Per image$0.04
Prompt expansion (per request)$0.02
Image to Video

Cosmos 3 Super API Documentation

https://gateway.pixazo.ai/cosmos-3-super-image-to-video/v1/cosmos-3-super-image-to-video-request

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

Cosmos 3 Super Image to Video generate request

Request Code

POST https://gateway.pixazo.ai/cosmos-3-super-image-to-video/v1/cosmos-3-super-image-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Cinematic slow camera push-in; the subject animates naturally",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
  "num_frames": 189,
  "frames_per_second": 24,
  "num_inference_steps": 28,
  "guidance_scale": 6,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "sync_mode": false
}
import requests

url = "https://gateway.pixazo.ai/cosmos-3-super-image-to-video/v1/cosmos-3-super-image-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Cinematic slow camera push-in; the subject animates naturally",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
    "num_frames": 189,
    "frames_per_second": 24,
    "num_inference_steps": 28,
    "guidance_scale": 6,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "sync_mode": false
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = "https://gateway.pixazo.ai/cosmos-3-super-image-to-video/v1/cosmos-3-super-image-to-video-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Cinematic slow camera push-in; the subject animates naturally",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
  "num_frames": 189,
  "frames_per_second": 24,
  "num_inference_steps": 28,
  "guidance_scale": 6,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "sync_mode": false
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));
curl -X POST "https://gateway.pixazo.ai/cosmos-3-super-image-to-video/v1/cosmos-3-super-image-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Cinematic slow camera push-in; the subject animates naturally",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
    "num_frames": 189,
    "frames_per_second": 24,
    "num_inference_steps": 28,
    "guidance_scale": 6,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "sync_mode": false
  }'

Output

{
  "request_id": "cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Cosmos 3 Super Image to Video generate request

Parameter Required Type Default Allowed values / range Description
promptYesstringnon-empty; ≤ 4096 charsText describing motion and scene (max 4096 characters). Must describe dynamic elements such as camera movement, object motion, or environmental changes.
image_urlYesstringURL of the conditioning first-frame image. Must be publicly accessible.
negative_promptNostring"blurry, low quality, distorted, unnatural motion, flickering, stuttering, deformed limbs, extra limbs, bad anatomy"≤ 2048 charsContent to steer away from during generation (max 2048 characters).
enable_prompt_expansionNobooleantrueAutomatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_agentic_generationNobooleanfalseEnable iterative agentic refinement loop for improved motion quality.
agentic_max_iterationsNointeger21, 2, 3Maximum number of agentic refinement stages.
agentic_samples_per_iterationNointeger21, 2, 3Number of candidate videos generated per agentic iteration.
agentic_early_stopNobooleantrueStop agentic loop early when the critic score exceeds the threshold.
image_sizeNostring or object{"width":832,"height":480}square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9Preset aspect ratio or custom dimensions. Custom object must include width and height as integers.
num_framesNointeger1895–189Number of frames in output video.
frames_per_secondNointeger244–60Output frame rate.
num_inference_stepsNointeger281–50Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scaleNofloat60–20Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
enable_safety_checkerNobooleantrueTurns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
seedNointegerRandom seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_modeNobooleanfalseIf on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image1JPG, PNG, WEBPInput image to animate.

Example Request

{
  "prompt": "Cinematic slow camera push-in; the subject animates naturally",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
  "num_frames": 189,
  "frames_per_second": 24,
  "num_inference_steps": 28,
  "guidance_scale": 6,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "sync_mode": false
}

Response

{
  "request_id": "cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'cosmos-3-super-image-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "cosmos-3-super-image-to-video",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "cosmos-3-super-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "cosmos-3-super-image-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/cosmos-3-super-image-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Cosmos 3 Super API Pricing

Your request will cost $0.05 per second.