Pixazo API→Models→Image to Image API→Pixelforge

Pixelforge 3.0 API, Pixelforge 2.0 API Free, Pixelforge 1.0 API: Pricing, Documentation

Pixelforge provides specialized AI capabilities for image generation and advanced relighting, allowing users to change lighting conditions in existing images. Through Pixazo's API, developers can generate new images and transform the lighting of existing photos for product photography, real estate, and creative applications. The API's relighting feature is particularly valuable for e-commerce and professional photography workflows.

Get API Key

Models Version

WELCOME BONUS

Get 10% Cashback on Your First Payment (up to $500)

Add funds and get 10% cashback on your first payment (up to $500).

Claim Your Cashback →

PixelForge 3.0 API Documentation

https://gateway.pixazo.ai/pixelforge-v3/v1/text-to-image

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Text to Image - PixelForge 3.0

Generate one or more images from a text prompt.

Request Code

POST https://gateway.pixazo.ai/pixelforge-v3/v1/text-to-image
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A single red maple leaf centred on a plain white background, studio lighting"
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-v3/v1/text-to-image"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "A single red maple leaf centred on a plain white background, studio lighting"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const response = await fetch("https://gateway.pixazo.ai/pixelforge-v3/v1/text-to-image", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    "prompt": "A single red maple leaf centred on a plain white background, studio lighting"
  })
});

const data = await response.json();
console.log(data);

curl -X POST "https://gateway.pixazo.ai/pixelforge-v3/v1/text-to-image" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A single red maple leaf centred on a plain white background, studio lighting"
  }'

Output

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Send an X-Webhook-URL header with your request and the finished result is POSTed to that URL, so you do not have to poll.

POST https://gateway.pixazo.ai/pixelforge-v3/v1/text-to-image
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
X-Webhook-URL: https://your-server.example.com/hooks/pixelforge

Webhook Payload (Success)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  }
}

Webhook Payload (Failure)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

Delivery — exactly one POST when the request reaches a terminal status. It is not retried: if your endpoint is unreachable or returns a non-2xx, that notification is lost and you must fall back to polling /v2/requests/status/{request_id}, which stays authoritative either way.
Respond quickly — return 2xx promptly. Because there is no retry, a slow or erroring handler loses the callback outright.
Treat it as an optimisation, not a guarantee — the webhook saves you from polling in the common case; the status endpoint is the source of truth.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Text to Image

Pricing: $0.011 per generated image. Requests that set num_images > 1 are billed per image (num_images × $0.011).

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–4000 characters	A detailed description of the image you want. Be specific about the subject, style, lighting and composition.
num_images	No	integer	1	1–4	How many images to generate in one request. Billed per image — n images cost n × $0.011.
image_size	No	string	auto	auto · 1024x1024 · 1024x1536 · 1536x1024 · 1792x1024 · 1024x1792 · 1:1 · 3:2 · 2:3 · 16:9 · 9:16 · square · portrait · landscape	The shape of the output. This sets the aspect ratio only — the generator picks its own resolution and caps the long edge at roughly 1600 px, so the returned pixel dimensions will not match the numbers you supply. Omit it, or send `auto`, to let the model choose.
output_format	No	string	webp	webp · png · jpeg · jpg	Encoding of the returned image. `webp` gives the smallest files at equivalent quality. `jpg` is accepted as a synonym for `jpeg`.
quality	No	string	high	standard · high	`high` lets the model reason for longer before drawing, which helps with complex prompts and legible text. `standard` is faster. Both cost the same.

Not supported by this model. Sending any of these returns 400 with an explanation rather than being silently ignored: seed (generation is non-deterministic — the same prompt returns a different image every time), mask / mask_url (there is no masked in-painting; describe the region to change in the prompt), background / transparent (output is always opaque), stream and partial_images (results arrive by polling), and model, moderation, response_format and tool_enablement.

Minimum Request

{
  "prompt": "A single red maple leaf centred on a plain white background, studio lighting"
}

Full Request (all options)

{
  "prompt": "A single red maple leaf centred on a plain white background, studio lighting",
  "num_images": 2,
  "image_size": "1024x1024",
  "output_format": "webp",
  "quality": "high"
}

Response

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Text to Image.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal 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 — Missing a required parameter
{
  "error": "Invalid request parameters",
  "message": "'prompt' is required",
  "violations": [
    "'prompt' is required"
  ]
}

Error via Status/Webhook

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

A request blocked by the content safety filter returns status: "ERROR" with a message asking you to rephrase the prompt or use a different reference image. Failed requests are not charged.

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/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  },
  "created_at": "2026-07-23T10:00:00.000Z",
  "updated_at": "2026-07-23 10:00:15",
  "completed_at": "2026-07-23 10:00:15"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated images (R2 CDN)
output.media_type	string	MIME type of the output (image/webp)
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error (e.g. bad inputs) — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

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

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

PixelForge 3.0 API Pricing

Your request will cost $0.011 per image.

Image to Image (Image Editing)

PixelForge 3.0 API Documentation

https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/editing

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Image to Image (Image Editing) - PixelForge 3.0

Edit an existing image with a text instruction. The model changes only what you ask for and leaves the rest of the picture intact.

Request Code

POST https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/editing
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Change the background to a soft blue gradient",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/editing"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "Change the background to a soft blue gradient",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const response = await fetch("https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/editing", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    "prompt": "Change the background to a soft blue gradient",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  })
});

const data = await response.json();
console.log(data);

curl -X POST "https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/editing" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Change the background to a soft blue gradient",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  }'

Output

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Send an X-Webhook-URL header with your request and the finished result is POSTed to that URL, so you do not have to poll.

POST https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/editing
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
X-Webhook-URL: https://your-server.example.com/hooks/pixelforge

Webhook Payload (Success)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  }
}

Webhook Payload (Failure)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

Delivery — exactly one POST when the request reaches a terminal status. It is not retried: if your endpoint is unreachable or returns a non-2xx, that notification is lost and you must fall back to polling /v2/requests/status/{request_id}, which stays authoritative either way.
Respond quickly — return 2xx promptly. Because there is no retry, a slow or erroring handler loses the callback outright.
Treat it as an optimisation, not a guarantee — the webhook saves you from polling in the common case; the status endpoint is the source of truth.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Image to Image (Image Editing)

Pricing: $0.011 per generated image. Requests that set num_images > 1 are billed per image (num_images × $0.011).

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–4000 characters	A detailed description of the image you want. Be specific about the subject, style, lighting and composition.
image_url	Yes	string	—	Public HTTPS URL or base64 data URI	The image to edit, as a public HTTPS URL — no size limit — or supplied inline as a `data:image/...;base64,` data URI. Inline data URIs only are capped at 20 MB per image and 40 MB per request; use an HTTPS URL for anything larger.
num_images	No	integer	1	1–4	How many images to generate in one request. Billed per image — n images cost n × $0.011.
image_size	No	string	auto	auto · 1024x1024 · 1024x1536 · 1536x1024 · 1792x1024 · 1024x1792 · 1:1 · 3:2 · 2:3 · 16:9 · 9:16 · square · portrait · landscape	The shape of the output. This sets the aspect ratio only — the generator picks its own resolution and caps the long edge at roughly 1600 px, so the returned pixel dimensions will not match the numbers you supply. Omit it, or send `auto`, to let the model choose.
output_format	No	string	webp	webp · png · jpeg · jpg	Encoding of the returned image. `webp` gives the smallest files at equivalent quality. `jpg` is accepted as a synonym for `jpeg`.
quality	No	string	high	standard · high	`high` lets the model reason for longer before drawing, which helps with complex prompts and legible text. `standard` is faster. Both cost the same.

Minimum Request

{
  "prompt": "Change the background to a soft blue gradient",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
}

Full Request (all options)

{
  "prompt": "Change the background to a soft blue gradient",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "num_images": 1,
  "image_size": "1024x1024",
  "output_format": "webp",
  "quality": "high"
}

Response

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Image to Image (Image Editing).

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal 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 — Missing a required parameter
{
  "error": "Invalid request parameters",
  "message": "'prompt' is required",
  "violations": [
    "'prompt' is required"
  ]
}

Error via Status/Webhook

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

A request blocked by the content safety filter returns status: "ERROR" with a message asking you to rephrase the prompt or use a different reference image. Failed requests are not charged.

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/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  },
  "created_at": "2026-07-23T10:00:00.000Z",
  "updated_at": "2026-07-23 10:00:15",
  "completed_at": "2026-07-23 10:00:15"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated images (R2 CDN)
output.media_type	string	MIME type of the output (image/webp)
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error (e.g. bad inputs) — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

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

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

PixelForge 3.0 API Pricing

Your request will cost $0.011 per image.

Image to Image (Multi-Image Compose)

PixelForge 3.0 API Documentation

https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/compose

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Image to Image (Multi-Image Compose) - PixelForge 3.0

Blend two or more images into a single scene — for example, place a product from one photograph into the setting of another. The model may rearrange the layout to make the composition work.

Request Code

POST https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/compose
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Place the product from the first image on the table in the second image",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/scene-end.jpg"
  ]
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/compose"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "Place the product from the first image on the table in the second image",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/scene-end.jpg"
  ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const response = await fetch("https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/compose", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    "prompt": "Place the product from the first image on the table in the second image",
    "image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/scene-end.jpg"
    ]
  })
});

const data = await response.json();
console.log(data);

curl -X POST "https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/compose" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Place the product from the first image on the table in the second image",
    "image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/scene-end.jpg"
    ]
  }'

Output

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Send an X-Webhook-URL header with your request and the finished result is POSTed to that URL, so you do not have to poll.

POST https://gateway.pixazo.ai/pixelforge-v3/v1/image-to-image/compose
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
X-Webhook-URL: https://your-server.example.com/hooks/pixelforge

Webhook Payload (Success)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  }
}

Webhook Payload (Failure)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

Delivery — exactly one POST when the request reaches a terminal status. It is not retried: if your endpoint is unreachable or returns a non-2xx, that notification is lost and you must fall back to polling /v2/requests/status/{request_id}, which stays authoritative either way.
Respond quickly — return 2xx promptly. Because there is no retry, a slow or erroring handler loses the callback outright.
Treat it as an optimisation, not a guarantee — the webhook saves you from polling in the common case; the status endpoint is the source of truth.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Image to Image (Multi-Image Compose)

Pricing: $0.011 per generated image. Requests that set num_images > 1 are billed per image (num_images × $0.011).

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–4000 characters	A detailed description of the image you want. Be specific about the subject, style, lighting and composition.
image_urls	Yes	array of string	—	2–6 items	The images to combine, as public HTTPS URLs or base64 data URIs. At least two are required — use `image-to-image/editing` for a single image. They must be two different images: repeated URLs are collapsed before the minimum is checked, so `[A, A]` is rejected as one image, not accepted as two.
num_images	No	integer	1	1–4	How many images to generate in one request. Billed per image — n images cost n × $0.011.
image_size	No	string	auto	auto · 1024x1024 · 1024x1536 · 1536x1024 · 1792x1024 · 1024x1792 · 1:1 · 3:2 · 2:3 · 16:9 · 9:16 · square · portrait · landscape	The shape of the output. This sets the aspect ratio only — the generator picks its own resolution and caps the long edge at roughly 1600 px, so the returned pixel dimensions will not match the numbers you supply. Omit it, or send `auto`, to let the model choose.
output_format	No	string	webp	webp · png · jpeg · jpg	Encoding of the returned image. `webp` gives the smallest files at equivalent quality. `jpg` is accepted as a synonym for `jpeg`.
quality	No	string	high	standard · high	`high` lets the model reason for longer before drawing, which helps with complex prompts and legible text. `standard` is faster. Both cost the same.

Minimum Request

{
  "prompt": "Place the product from the first image on the table in the second image",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/scene-end.jpg"
  ]
}

Full Request (all options)

{
  "prompt": "Place the product from the first image on the table in the second image",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/scene-end.jpg"
  ],
  "num_images": 1,
  "image_size": "1536x1024",
  "output_format": "webp",
  "quality": "high"
}

Response

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Image to Image (Multi-Image Compose).

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal 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 — Missing a required parameter
{
  "error": "Invalid request parameters",
  "message": "'prompt' is required",
  "violations": [
    "'prompt' is required"
  ]
}

Error via Status/Webhook

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

A request blocked by the content safety filter returns status: "ERROR" with a message asking you to rephrase the prompt or use a different reference image. Failed requests are not charged.

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/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  },
  "created_at": "2026-07-23T10:00:00.000Z",
  "updated_at": "2026-07-23 10:00:15",
  "completed_at": "2026-07-23 10:00:15"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated images (R2 CDN)
output.media_type	string	MIME type of the output (image/webp)
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error (e.g. bad inputs) — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

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

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

PixelForge 3.0 API Pricing

Your request will cost $0.011 per image.

Reference to Image

PixelForge 3.0 API Documentation

https://gateway.pixazo.ai/pixelforge-v3/v1/reference-to-image

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Reference to Image - PixelForge 3.0

Generate a new image that keeps the subject, style or product from one to three reference images. Use it to hold a character or a product identity steady across a series of shots.

Request Code

POST https://gateway.pixazo.ai/pixelforge-v3/v1/reference-to-image
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "The same product photographed on a marble kitchen counter in morning light",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ]
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-v3/v1/reference-to-image"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "The same product photographed on a marble kitchen counter in morning light",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const response = await fetch("https://gateway.pixazo.ai/pixelforge-v3/v1/reference-to-image", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    "prompt": "The same product photographed on a marble kitchen counter in morning light",
    "reference_image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
    ]
  })
});

const data = await response.json();
console.log(data);

curl -X POST "https://gateway.pixazo.ai/pixelforge-v3/v1/reference-to-image" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "The same product photographed on a marble kitchen counter in morning light",
    "reference_image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
    ]
  }'

Output

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Send an X-Webhook-URL header with your request and the finished result is POSTed to that URL, so you do not have to poll.

POST https://gateway.pixazo.ai/pixelforge-v3/v1/reference-to-image
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
X-Webhook-URL: https://your-server.example.com/hooks/pixelforge

Webhook Payload (Success)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  }
}

Webhook Payload (Failure)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

Delivery — exactly one POST when the request reaches a terminal status. It is not retried: if your endpoint is unreachable or returns a non-2xx, that notification is lost and you must fall back to polling /v2/requests/status/{request_id}, which stays authoritative either way.
Respond quickly — return 2xx promptly. Because there is no retry, a slow or erroring handler loses the callback outright.
Treat it as an optimisation, not a guarantee — the webhook saves you from polling in the common case; the status endpoint is the source of truth.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Reference to Image

Pricing: $0.011 per generated image. Requests that set num_images > 1 are billed per image (num_images × $0.011).

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–4000 characters	A detailed description of the image you want. Be specific about the subject, style, lighting and composition.
reference_image_urls	Yes	array of string	—	1–3 items	Reference images that anchor the subject, product or style, as public HTTPS URLs or base64 data URIs. They condition the new image rather than being edited in place.
num_images	No	integer	1	1–4	How many images to generate in one request. Billed per image — n images cost n × $0.011.
image_size	No	string	auto	auto · 1024x1024 · 1024x1536 · 1536x1024 · 1792x1024 · 1024x1792 · 1:1 · 3:2 · 2:3 · 16:9 · 9:16 · square · portrait · landscape	The shape of the output. This sets the aspect ratio only — the generator picks its own resolution and caps the long edge at roughly 1600 px, so the returned pixel dimensions will not match the numbers you supply. Omit it, or send `auto`, to let the model choose.
output_format	No	string	webp	webp · png · jpeg · jpg	Encoding of the returned image. `webp` gives the smallest files at equivalent quality. `jpg` is accepted as a synonym for `jpeg`.
quality	No	string	high	standard · high	`high` lets the model reason for longer before drawing, which helps with complex prompts and legible text. `standard` is faster. Both cost the same.

Minimum Request

{
  "prompt": "The same product photographed on a marble kitchen counter in morning light",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ]
}

Full Request (all options)

{
  "prompt": "The same product photographed on a marble kitchen counter in morning light",
  "reference_image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "num_images": 2,
  "image_size": "1024x1536",
  "output_format": "webp",
  "quality": "high"
}

Response

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Reference to Image.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal 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 — Missing a required parameter
{
  "error": "Invalid request parameters",
  "message": "'prompt' is required",
  "violations": [
    "'prompt' is required"
  ]
}

Error via Status/Webhook

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-v3",
  "error": "Description of the error",
  "output": null
}

A request blocked by the content safety filter returns status: "ERROR" with a message asking you to rephrase the prompt or use a different reference image. Failed requests are not charged.

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/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-v3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-v3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.webp"
    ],
    "media_type": "image/webp"
  },
  "created_at": "2026-07-23T10:00:00.000Z",
  "updated_at": "2026-07-23 10:00:15",
  "completed_at": "2026-07-23 10:00:15"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated images (R2 CDN)
output.media_type	string	MIME type of the output (image/webp)
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error (e.g. bad inputs) — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

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

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

PixelForge 3.0 API Pricing

Your request will cost $0.011 per image.

2. PixelForge 2.0

PixelForge 2.0 API Documentation

https://gateway.pixazo.ai/pixelforge-image-v2/v1/text-to-image

Text to Image - PixelForge V2

Image search — returns existing library images matching your text query (not a generation). Free, synchronous (~1s), and returns results inline (no polling). Up to 100 results per query.

Request Code

POST https://gateway.pixazo.ai/pixelforge-image-v2/v1/text-to-image
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: your-subscription-key-here

{
  "text": "red dress",
  "type": "tags,caption",
  "seed": 1,
  "size": 10
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-image-v2/v1/text-to-image"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "your-subscription-key-here"
}
data = {
    "text": "red dress",
  "type": "tags,caption",
  "seed": 1,
  "size": 10
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/pixelforge-image-v2/v1/text-to-image';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'your-subscription-key-here'
};
const body = {
  text: 'red dress',
  type: 'tags,caption',
  seed: 1,
  size: 10
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(body)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST https://gateway.pixazo.ai/pixelforge-image-v2/v1/text-to-image \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: your-subscription-key-here" \
  -d '{
    "text": "red dress",
  "type": "tags,caption",
  "seed": 1,
  "size": 10
  }'

Output

{
  "text": "red dress",
  "type": ["tags", "caption"],
  "seed": 1,
  "size": 10,
  "total": 100,
  "results": [
    {
      "key": "vibe/example-image.png",
      "caption": "A short caption describing the image.",
      "url": "https://images.mediadirhub.com/vibe/example-image.png"
    }
  ]
}

Try Now

Request Parameters - Text to Image

Parameter	Required	Type	Default	Allowed values / range	Description
`text`	Yes	string	—	—	The search query. Matches against the image library; an empty value returns no results.
`type`	No	string	all fields	`tags`, `caption` (comma-separated)	Which fields to match against, e.g. `tags,caption`. Omit (or send an unknown value) to search all fields. Also accepts a JSON array, e.g. `["tags","caption"]`.
`seed`	No	integer	— (random)	−(2^53−1) … 2^53−1	Deterministic shuffle seed — the same seed returns the same ordering. Omit for a random order each call. Values beyond ±2^53 lose precision.
`size`	No	integer	10	1 – 100	Number of results to return. Values > 100 are clamped to 100; ≤ 0 or non-numeric fall back to 10.

Served by the Qwen text-to-image engine. Free — no credit cost. Advanced callers may send a full DashScope-style body (model/input/parameters), which is passed through unchanged. Typical generation time ~10–15 seconds (synchronous response).

Example Request

{
  "text": "red dress",
  "type": "tags,caption",
  "seed": 1,
  "size": 10
}

Response

{
  "text": "red dress",
  "type": ["tags", "caption"],
  "seed": 1,
  "size": 10,
  "total": 100,
  "results": [
    {
      "key": "vibe/example-image.png",
      "caption": "A short caption describing the image.",
      "url": "https://images.mediadirhub.com/vibe/example-image.png"
    }
  ]
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key for authentication

Response Handling

Common status codes for Text to Image.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

PixelForge 2.0 API Pricing

Your request is Free

Content Safety

PixelForge 2.0 API Documentation

POST https://gateway.pixazo.ai/content-safety/v1/image-moderation

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Image Moderation - Content Safety

Analyze an image for objectionable content across four harm categories (Hate, SelfHarm, Sexual, Violence). The response returns a per-category severity (0 Safe, 2 Low, 4 Medium, 6 High) and a single flagged boolean. Synchronous — the verdict is returned in one call (typically under 1 second).

Request Code

POST /content-safety/v1/image-moderation HTTP/1.1
Host: gateway.pixazo.ai
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
Content-Type: application/json

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
}

import requests

url = "https://gateway.pixazo.ai/content-safety/v1/image-moderation"
headers = {
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY",
    "Content-Type": "application/json",
}
payload = {"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"}

resp = requests.post(url, headers=headers, json=payload)
print(resp.json())

const res = await fetch("https://gateway.pixazo.ai/content-safety/v1/image-moderation", {
  method: "POST",
  headers: {
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ image_url: "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg" }),
});
const data = await res.json();
console.log(data);

curl -X POST "https://gateway.pixazo.ai/content-safety/v1/image-moderation" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"}'

Output

{
  "flagged": false,
  "categories": [
    { "category": "Sexual", "severity": 0 },
    { "category": "Violence", "severity": 0 },
    { "category": "Hate", "severity": 0 },
    { "category": "SelfHarm", "severity": 0 }
  ],
  "severity_threshold": 2,
  "ms": 414
}

Try Now

Request Parameters

Parameter	Type	Required	Default	Description
image_url	string	Conditional	—	Public http(s) URL of the image to analyze. Must return an `image/*` content-type and be ≤ 4 MB (50×50 to 2048×2048 px). Provide either `image_url` or `image_b64`.
image_b64	string	Conditional	—	Base64-encoded image bytes, as an alternative to `image_url` (same size limits). Provide either `image_url` or `image_b64`.
categories	array<string>	No	all four	Restrict analysis to a subset of `["Hate", "SelfHarm", "Sexual", "Violence"]`. Omit to analyze all four.
severity_threshold	integer	No	2	Minimum severity (0, 2, 4, 6) counted as `flagged`. 2 = Low and up (strict), 4 = Medium/High only, 6 = High only. Clamped to 0–6.

Severity levels returned per category: 0 Safe, 2 Low, 4 Medium, 6 High.

Example Request

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "categories": ["Sexual", "Violence"],
  "severity_threshold": 4
}

Example Response

{
  "flagged": false,
  "categories": [
    { "category": "Sexual", "severity": 0 },
    { "category": "Violence", "severity": 2 }
  ],
  "severity_threshold": 4,
  "ms": 512
}

Response Fields

Field	Type	Description
`flagged`	boolean	true = at least one category's severity is ≥ `severity_threshold`, so the image should be blocked or sent for review. false = every category is below the threshold (safe to allow). Use the per-category `severity` values to decide how to handle a flagged image.
`categories`	array	One entry per analyzed harm category.
`categories[].category`	string	The harm category: `Hate`, `SelfHarm`, `Sexual`, or `Violence`.
`categories[].severity`	integer	How strongly that category was detected — `0`, `2`, `4`, or `6` (see Severity Levels below).
`severity_threshold`	integer	The threshold applied to this request (minimum severity counted as `flagged`). Defaults to 2; override per request.
`ms`	integer	Server-side processing time, in milliseconds.

What Each Category Detects

Every image is analyzed against these four harm categories.

Category	Covers
Sexual	Nudity & pornography, sexual acts and imagery, vulgar content, prostitution, abuse, and child exploitation/grooming (including forced or assault sexual content).
Violence	Physical actions intended to hurt, injure, or kill; weapons & guns; gore, injury, and death; bullying & intimidation; domestic violence & physical abuse; terrorism; stalking.
Hate	Attacks or discriminatory content targeting identity attributes — race, ethnicity, nationality, gender identity/expression, sexual orientation, religion, appearance/body size, disability — plus harassment, bullying, and hate symbols.
SelfHarm	Self-injury, suicide, and related acts; eating disorders; and bullying/intimidation that promotes self-harm.

Severity Levels

Each category returns one of four severity levels. flagged is true when any category's severity is at or above severity_threshold.

Severity	Level	Meaning
0	Safe	No objectionable content detected in this category; content is appropriate.
2	Low	Content may be inappropriate in some contexts; low risk.
4	Medium	Content is inappropriate and should generally be filtered.
6	High	Content is highly inappropriate or harmful and should be blocked.

Example: Sexual: 4 with severity_threshold: 2 → flagged: true (4 ≥ 2). The same image with severity_threshold: 6 → flagged: false (4 < 6).

What Each Level Means Per Category (images)

Category	Low (2)	Medium (4)	High (6)
Sexual	Suggestive/racy poses, non-graphic nudity in artwork, body art.	Erotic or soft-nude content, obscured/partial sexual activity.	Explicit sexual acts & organs, CSAM, non-consensual acts.
Violence	Weapons or bladed tools in display or use, light injury, non-realistic violence.	Moderate gore; domestic violence & physical abuse; use of force/coercion to intimidate an individual; a weapon used against a target.	High gore, graphic injury/death, dismemberment, terrorism.
Hate	Stereotyping, biased sentiment, certain hate symbols in context.	Insults, mocking, dehumanization, promotion of exclusion of an identity group.	Hate-speech/hate-crime imagery, glorified extremist/hate symbols.
SelfHarm	Scars, self-harm tools/injury in recovery, emaciation.	Mocking survivors; self-harm shown as a solution; moderate gore.	Explicit self-harm or suicide acts, high gore.

Request Headers

Header	Required	Description
Ocp-Apim-Subscription-Key	Yes	Your API subscription key
Content-Type	Yes	Must be `application/json`

Response Handling

Status	Meaning
200 OK	Analysis complete. Body contains `flagged` and per-category `severity`.
400 Bad Request	Invalid JSON, missing both `image_url` and `image_b64`, or invalid `categories`.
401 Unauthorized	Missing or invalid subscription key.
403 Insufficient Balance	Wallet balance is too low to cover the request.
422 Unprocessable	The image could not be fetched or is not a valid/supported image (bad URL, non-image content-type, > 4 MB, or corrupt).
429 Too Many Requests	Rate limit exceeded. Retry after a short delay.
503 Service Unavailable	Moderation backend temporarily unavailable. Retry.

Limitations & Best Practices

Strong on graphic / explicit content — gore, weapons, visible injury, and explicit sexual imagery are detected reliably.
May under-detect implied or staged scenes — a threatening pose or an intimidation scene without visible weapons, gore, or injury can score below the flag threshold even when a human reads it as harmful. Treat a low or zero score as “no graphic violation detected,” not a guarantee that the image is safe.
Tune the threshold — lower severity_threshold (to 0 or 2) to catch borderline / suggestive content; raise it to flag only clear violations.
For high-stakes moderation, pair the API with human review of flagged and borderline content.

PixelForge 2.0 API Pricing

Your request will cost $0.002 per image.

3. PixelForge 1.0

PixelForge 1.0 API Documentation

https://gateway.pixazo.ai/pixelforge-image/v1/qwen_image_gen/serve_image

Generate Image - Pixelforge Image API

Request Code

POST https://gateway.pixazo.ai/pixelforge-image/v1/qwen_image_gen/serve_image
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: your-subscription-key-here

{
  "prompt": "A futuristic city skyline at sunset with flying cars and neon signs"
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-image/v1/qwen_image_gen/serve_image"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "your-subscription-key-here"
}
data = {
    "prompt": "A futuristic city skyline at sunset with flying cars and neon signs"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/pixelforge-image/v1/qwen_image_gen/serve_image';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'your-subscription-key-here'
};
const body = {
  prompt: 'A futuristic city skyline at sunset with flying cars and neon signs'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(body)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST https://gateway.pixazo.ai/pixelforge-image/v1/qwen_image_gen/serve_image \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: your-subscription-key-here" \
  -d '{
    "prompt": "A futuristic city skyline at sunset with flying cars and neon signs"
  }'

Output

Synchronous — the generated image is returned inline in this response at output.choices[0].message.content[0].image. There is no separate “get result” / polling step.

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            { "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/....png" }
          ]
        }
      }
    ],
    "task_metric": { "FAILED": 0, "SUCCEEDED": 1, "TOTAL": 1 }
  },
  "usage": { "height": 1328, "image_count": 1, "width": 1328 }
}

Try Now

Request Parameters - Generate Image

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	Max 800 characters (longer prompts are truncated to the first 800)	The text prompt describing the image you want to generate. You can provide detailed and creative descriptions to guide the image generation process.
size	No	string	1328*1328	1664928 (16:9), 14721104 (4:3), 13281328 (1:1), 11041472 (3:4), 928*1664 (9:16)	Output image resolution as widthheight. When omitted, the gateway applies 13281328 (square).

Served by the PixelForge text-to-image engine. Advanced callers may send a DashScope-style body (model/input/parameters); only the prompt text in input.messages[0].content and parameters.size are used, and the model value is ignored. Other parameters, such as negative_prompt, prompt_extend, seed and watermark, are not supported and are ignored. Typical generation time ~10–40 seconds (synchronous response).

Content Item Types & Limits

Type	Max	Format / Size	Description
image	0	Not supported	Image input is not supported on this endpoint; requests that include an image return 400 InvalidParameter.

Example Request

{
  "prompt": "A futuristic city skyline at sunset with flying cars and neon signs"
}

Response

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            { "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/....png" }
          ]
        }
      }
    ],
    "task_metric": { "FAILED": 0, "SUCCEEDED": 1, "TOTAL": 1 }
  },
  "usage": { "height": 1328, "image_count": 1, "width": 1328 }
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key for authentication

Response Handling

Common status codes for Generate Image. InvalidParameter, DataInspectionFailed, Throttling and InternalError errors return JSON with code, message and request_id. Failed requests are not charged.

Code	Meaning
200	Success
400	Bad Request — `InvalidParameter` (for example a missing prompt, an unsupported size, or image input) or `DataInspectionFailed` (the prompt was rejected by the content safety filter)
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests — retry shortly (`Throttling`: the image service is busy)
500	Internal Server Error
502	Bad Gateway — `InternalError`: image generation failed; retry

PixelForge 1.0 API Pricing

Your request will cost $0.04 per image.

Covered by your monthly free credit

Image to Image (Image Editing — Relighting)

PixelForge 1.0 API Documentation

https://gateway.pixazo.ai/pixelforge-relighting-api/v1/relighting/generate

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Image Edit Request - Pixelforge Relighting API

Request Code

POST https://gateway.pixazo.ai/pixelforge-relighting-api/v1/relighting/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Professional studio lighting with soft shadows",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/f1.png"
  ]
}

import requests

url = "https://gateway.pixazo.ai/pixelforge-relighting-api/v1/relighting/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Professional studio lighting with soft shadows",
    "image_urls": [
        "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/f1.png"
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

async function generateRelitImage() {
  const url = 'https://gateway.pixazo.ai/pixelforge-relighting-api/v1/relighting/generate';
  const headers = {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  };
  const data = {
    prompt: 'Professional studio lighting with soft shadows',
    image_urls: [
      'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/f1.png'
    ]
  };

  const response = await fetch(url, {
    method: 'POST',
    headers: headers,
    body: JSON.stringify(data)
  });
  const result = await response.json();
  console.log(result);
}

generateRelitImage();

curl -X POST "https://gateway.pixazo.ai/pixelforge-relighting-api/v1/relighting/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Professional studio lighting with soft shadows",
    "image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/f1.png"
    ]
  }'

Output

{
  "request_id": "pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

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

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-relighting-api",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-relighting-api",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Image Edit Request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description of desired lighting effect. Max 800 characters.
image_urls	Yes	array	—	—	Array of reference image URLs (1-10 images). Must be publicly accessible. Supports JPEG, PNG, WEBP.
image_size	No	string/object	"square_hd"	"square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9" or custom {"width": 1280, "height": 720}	Output size. Options: "square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9" or custom {"width": 1280, "height": 720}
num_inference_steps	No	integer	50	1–150.	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	number	4	1–20.	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
num_images	No	integer	1	1–4.	Number of images to generate. Range: 1-4.
enable_safety_checker	No	boolean	true	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
output_format	No	string	"png"	—	Output format: "jpeg" or "png".
negative_prompt	No	string	" "	—	Elements to exclude from generation.
acceleration	No	string	"regular"	—	Speed optimization: "none" or "regular".
loras	No	array	[]	—	A list of style add-ons (LoRAs) to apply, up to 3. Each entry needs a 'path' (the add-on's location) and an optional 'scale' for its strength (0.0-2.0).
webhook	No	string	—	—	Webhook URL for async notifications.
webhook_events_filter	No	array	["*"]	—	Event types: ["start"], ["complete"], ["*"].

Content Item Types & Limits

Type	Max	Format / Size	Description
image	—	JPG, PNG, WEBP	Image(s) to relight.

Minimum Request

{
  "prompt": "Professional lighting",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png"
  ]
}

Full Request (all options)

{
  "prompt": "Professional studio lighting with soft shadows",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/f1.png"
  ],
  "image_size": "square_hd",
  "num_inference_steps": 50,
  "guidance_scale": 4,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "png",
  "negative_prompt": " ",
  "acceleration": "regular",
  "loras": [
    {
      "path": "https://.../files/lighting-lora.safetensors",
      "scale": 1.0
    }
  ],
  "webhook": "https://your-domain.com/webhook",
  "webhook_events_filter": [
    "*"
  ]
}

Response

{
  "request_id": "pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Image Edit Request.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal 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 'pixelforge-relighting-api' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "pixelforge-relighting-api",
  "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/pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "pixelforge-relighting-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "pixelforge-relighting-api",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/pixelforge-relighting-api_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "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

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

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

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

PixelForge 1.0 API Pricing

Your request will cost $0.035 per image.

Covered by your monthly free credit

⚡ Performance

Live usage measured on Pixazo's gateway, split by model version. Generation time is how long a generation takes end-to-end (lower is better). Success rate is the percent of generations that complete (higher is better).

Show data for the last

Generations

139,400last 30d

~4,647 per day

Success rate

99.4%

of completed generations

Generation time

58.5savg

p95 82.3s

Requests

Sep 17max 20,900Oct 16

PixelForge 1.0Avg 4,640/day

PixelForge 3.0Avg 7/day

Generation Time

Sep 17max 2.4minOct 16

PixelForge 1.0Avg 58.3s

PixelForge 3.0Avg 27.8s

Error Rate

Sep 17max 50.0%Oct 16

PixelForge 1.0Avg 0.3%

PixelForge 3.0Avg 50.0%

〰 Uptime

Percent of generations that succeeded over the selected period, per model version.

Avg. Success Rate (30d)

99.43%

across all generations of this model family

Uptime

Sep 17max 100%Oct 16

PixelForge 1.0Avg 99.68%

PixelForge 3.0Avg 50.00%