Pixazo API→Models→Text to Image API→GPT Image 2

GPT Image 2 API, GPT Image 1.5 API: Pricing, Documentation

GPT Image 2 API, developers can create images that accurately reflect complex prompts, edit existing images with natural language instructions, and generate variations. The API combines GPT's language understanding with powerful image generation for intuitive creative workflows.

Get API Key

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

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

Claim Your $5 →

GPT Image 2 API Documentation

https://gateway.pixazo.ai/gpt-image-2/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 - GPT Image 2

Request Code

POST https://gateway.pixazo.ai/gpt-image-2/v1/text-to-image
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A serene sunset over mountains"
}

import requests

url = "https://gateway.pixazo.ai/gpt-image-2/v1/text-to-image"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
  "prompt": "A serene sunset over mountains"
}

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

const url = 'https://gateway.pixazo.ai/gpt-image-2/v1/text-to-image';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
  prompt: 'A serene sunset over mountains'
};

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

curl -X POST "https://gateway.pixazo.ai/gpt-image-2/v1/text-to-image" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
  "prompt": "A serene sunset over mountains"
}'

Output

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-2_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": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-2_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": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-2",
  "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 - Text to Image

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	Up to 32,000 characters	Text description of the desired image. Must be non-empty.
`n`	No	integer	1	1–10	Number of images to generate in one request.
`size`	No	string	`"auto"`	`1024x1024`, `1024x1536`, `1536x1024`, `2048x2048`, `2048x1152`, `2160x3840`, `3840x2160`, `auto`, or custom W×H	Output dimensions. Custom sizes: both edges multiples of 16px, longest edge up to 3840px, aspect ratio up to 3:1, total pixels 655,360–8,294,400.
`quality`	No	string	`"auto"`	`low`, `medium`, `high`, `auto`	Sets how much detail is rendered. High looks the sharpest but takes longer and costs more; Low is good for quick drafts.
`format`	No	string	`"png"`	`png`, `jpeg`, `webp`	Output file format. `jpeg` is fastest.
`output_compression`	No	integer	100	0–100	Sets how hard the image is squeezed when it is saved as a JPEG or WebP — lower means a smaller file with softer detail. It has no effect on PNG.
`background`	No	string	`"auto"`	`opaque`, `auto`	Sets how the background is handled. GPT Image 2 always fills the background in — transparent cut-outs are not available on this model.
`moderation`	No	string	`"auto"`	`auto`, `low`	Sets how strictly your prompt and the result are checked for sensitive content. Auto is the standard filter; Low is less restrictive.

Example Request

{
  "prompt": "Photorealistic 2K landscape of a fjord at golden hour, dramatic clouds, ultra-detailed",
  "n": 4,
  "size": "2048x1152",
  "quality": "high",
  "format": "webp",
  "output_compression": 80,
  "background": "opaque",
  "moderation": "low"
}

Response

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_API_KEY

Response Handling

Common status codes.

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 — Model not found
{
  "error": "Model not found",
  "message": "Model 'gpt-image-2' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-2",
  "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/gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "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.

GPT Image 2 API Pricing

Resolution	Price (USD)
1024x768 (Low)	$0.005
1024x1024 (Low)	$0.006
1024x1536 (Low)	$0.005
1536x1024 (Low)	$0.005
1920x1080 (Low)	$0.005
2560x1440 (Low)	$0.007
3840x2160 (Low)	$0.012
1024x768 (Medium)	$0.037
1024x1024 (Medium)	$0.053
1024x1536 (Medium)	$0.042
1536x1024 (Medium)	$0.042
1920x1080 (Medium)	$0.04
2560x1440 (Medium)	$0.056
3840x2160 (Medium)	$0.101
1024x768 (High)	$0.145
1024x1024 (High)	$0.211
1024x1536 (High)	$0.165
1536x1024 (High)	$0.165
1920x1080 (High)	$0.158
2560x1440 (High)	$0.222
3840x2160 (High)	$0.401

Image to Image (Image Editing)

GPT Image 2 API Documentation

https://gateway.pixazo.ai/gpt-image-2/v1/image-to-image-edit

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 (Edit Image) - GPT Image 2

Request Code

POST https://gateway.pixazo.ai/gpt-image-2/v1/image-to-image-edit
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Add a flamingo to the pool",
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/gpt-images-2/img_c86ec1806237_0.png"
}

import requests

url = "https://gateway.pixazo.ai/gpt-image-2/v1/image-to-image-edit"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
  "prompt": "Add a flamingo to the pool",
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/gpt-images-2/img_c86ec1806237_0.png"
}

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

const url = 'https://gateway.pixazo.ai/gpt-image-2/v1/image-to-image-edit';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
  prompt: 'Add a flamingo to the pool',
  image: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/gpt-images-2/img_c86ec1806237_0.png'
};

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

curl -X POST "https://gateway.pixazo.ai/gpt-image-2/v1/image-to-image-edit" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
  "prompt": "Add a flamingo to the pool",
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/gpt-images-2/img_c86ec1806237_0.png"
}'

Output

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-2_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.

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": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-2_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": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-2",
  "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

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	Up to 32,000 characters	Text instruction describing the edit. Must be non-empty.
`image`	Yes	string or string[]	—	Up to 16 images	Upload the image you want to edit. Add up to 16 to combine them into a single result. JPG, PNG or WebP; under 50 MB each.
`mask`	No	string	—	PNG with an alpha channel, same dimensions as the first input image	Optional. Upload a PNG the same size as your image, with the parts you want changed fully see-through and everything you want kept solid. Under 4 MB. It applies to the first image.
`n`	No	integer	1	1–10	Number of output variations to generate.
`size`	No	string	`"auto"`	`1024x1024`, `1024x1536`, `1536x1024`, `2048x2048`, `2048x1152`, `2160x3840`, `3840x2160`, `auto`, or custom W×H	Output dimensions. Custom sizes: both edges multiples of 16px, longest edge up to 3840px, aspect ratio up to 3:1, total pixels 655,360–8,294,400.
`quality`	No	string	`"auto"`	`low`, `medium`, `high`, `auto`	Sets how much detail is rendered. High looks the sharpest but takes longer and costs more; Low is good for quick drafts.
`format`	No	string	`"png"`	`png`, `jpeg`, `webp`	Output file format. `jpeg` is fastest.
`output_compression`	No	integer	100	0–100	Sets how hard the image is squeezed when it is saved as a JPEG or WebP — lower means a smaller file with softer detail. It has no effect on PNG.
`background`	No	string	`"auto"`	`opaque`, `auto`	Sets how the background is handled. GPT Image 2 always fills the background in — transparent cut-outs are not available on this model.
`moderation`	No	string	`"auto"`	`auto`, `low`	Sets how strictly your prompt and the result are checked for sensitive content. Auto is the standard filter; Low is less restrictive.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	16	JPG, PNG, WEBP · < 50 MB	Image(s) to edit (up to 16).
mask	1	PNG with an alpha channel · < 4 MB	Optional mask; must match image size. Transparent pixels mark the region to edit.

Input image requirements: HTTPS URL or data:image/...;base64,... data-URI. PNG, JPEG, or WEBP. Multiple input images may be combined in a single edit request via the image array.

Edit-specific Notes

image as array — each entry is independently resolved (URL fetched, or base64 decoded). All are uploaded as repeated image[] parts. Useful for "combine these references" workflows.
mask semantics — must match the input image's dimensions. The mask must be a PNG with an alpha channel — fully transparent pixels mark the region to edit, opaque pixels are preserved. A flat black & white PNG carries no alpha channel and is rejected before the request reaches the model, because a fully opaque image selects nothing. If mask is omitted, the entire image is in scope for the edit.
Multi-image + mask together — allowed, but the mask applies to the first input image only.
transparent background — NOT supported on gpt-image-2 (only opaque and auto).

Example Request

{
  "prompt": "Compose a gift basket containing all items, photorealistic, white background, with a Relax & Unwind ribbon",
  "image": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedream-5-0-lite-text-to-image_019ecace-485b-7447-c8d1-ce0344929afed/output.png",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/nano-banana-pro_019ed0b0-e2d6-70d5-7724-7322947d78d18/output.jpg",
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/recraft/a-red-cat-1781619282400-0.webp"
  ],
  "n": 1,
  "size": "1024x1024",
  "quality": "high",
  "format": "png",
  "output_compression": 90,
  "background": "opaque",
  "moderation": "auto"
}

Response

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_API_KEY

Response Handling

Common status codes.

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 — Model not found
{
  "error": "Model not found",
  "message": "Model 'gpt-image-2' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-2",
  "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/gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "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.

GPT Image 2 API Pricing

Resolution	Price (USD)
1024x768 (Low)	$0.005
1024x1024 (Low)	$0.006
1024x1536 (Low)	$0.005
1536x1024 (Low)	$0.005
1920x1080 (Low)	$0.005
2560x1440 (Low)	$0.007
3840x2160 (Low)	$0.012
1024x768 (Medium)	$0.037
1024x1024 (Medium)	$0.053
1024x1536 (Medium)	$0.042
1536x1024 (Medium)	$0.042
1920x1080 (Medium)	$0.04
2560x1440 (Medium)	$0.056
3840x2160 (Medium)	$0.101
1024x768 (High)	$0.145
1024x1024 (High)	$0.211
1024x1536 (High)	$0.165
1536x1024 (High)	$0.165
1920x1080 (High)	$0.158
2560x1440 (High)	$0.222
3840x2160 (High)	$0.401

2. GPT Image v1.5

GPT Image v1.5 API Documentation

https://gateway.pixazo.ai/gpt-image-1-5-api-923/v1/gpt-image-1-5-api-request

Authentication

All requests require an API key passed via header.

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

GPT-Image 1.5 API generate request - GPT Image 1.5 API

Request Code

POST https://gateway.pixazo.ai/gpt-image-1-5-api-923/v1/gpt-image-1-5-api-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
  "image_size": "1024x1024",
  "background": "auto",
  "quality": "high",
  "num_images": 1,
  "output_format": "png"
}

import requests

url = "https://gateway.pixazo.ai/gpt-image-1-5-api-923/v1/gpt-image-1-5-api-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
    "image_size": "1024x1024",
    "background": "auto",
    "quality": "high",
    "num_images": 1,
    "output_format": "png"
}

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

const url = 'https://gateway.pixazo.ai/gpt-image-1-5-api-923/v1/gpt-image-1-5-api-request';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912',
  image_size: '1024x1024',
  background: 'auto',
  quality: 'high',
  num_images: 1,
  output_format: 'png'
};

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

curl -X POST "https://gateway.pixazo.ai/gpt-image-1-5-api-923/v1/gpt-image-1-5-api-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
    "image_size": "1024x1024",
    "background": "auto",
    "quality": "high",
    "num_images": 1,
    "output_format": "png"
  }'

Output

{
  "request_id": "gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-1-5-api-923_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.

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": "gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-1-5-api-923",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-1-5-api-923_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": "gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-1-5-api-923",
  "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 - GPT-Image 1.5 API generate request

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	2–32,000 characters	Detailed text description of the desired image (2–32,000 characters).
`image_size`	No	string	`"1024x1024"`	`1024x1024`, `1536x1024`, `1024x1536`	Output dimensions — square, landscape, or portrait.
`quality`	No	string	`"high"`	`low`, `medium`, `high`	Sets how much detail is rendered. High looks the sharpest but takes longer and costs more; Low is good for quick drafts.
`background`	No	string	`"auto"`	`auto`, `transparent`, `opaque`	Sets how the background is handled. Transparent gives you a cut-out with no background, saved as a PNG or WebP; Opaque fills it in.
`num_images`	No	integer	1	1–4	Number of images to generate in one request.
`output_format`	No	string	`"png"`	`jpeg`, `png`, `webp`	Output file format.
`sync_mode`	No	boolean	false	—	If `true`, returns the image as a base64-encoded data URI inline in the response. If `false`, returns hosted image URLs via the async queue.

Example Request

{
  "prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
  "image_size": "1024x1024",
  "background": "auto",
  "quality": "high",
  "num_images": 1,
  "output_format": "png"
}

Response

{
  "request_id": "gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

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 — Model not found
{
  "error": "Model not found",
  "message": "Model 'gpt-image-1-5-api-923' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-1-5-api-923",
  "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/gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "gpt-image-1-5-api-923_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-1-5-api-923",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-1-5-api-923_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.

GPT Image v1.5 API Pricing

Variants map to quality tiers: Variant 1 = Low, Variant 2 = Medium, Variant 3 = High. Higher = more detail and better prompt adherence at higher cost and latency.

Resolution	Model	Price (USD)
1024x1024	low-1024x1024	$0.009
1024x1536	low-1024x1536	$0.013
1536x1024	low-1536x1024	$0.013
1024x1024	medium-1024x1024	$0.034
1024x1536	medium-1024x1536	$0.051
1536x1024	medium-1536x1024	$0.05
1024x1024	high-1024x1024	$0.133
1024x1536	high-1024x1536	$0.20
1536x1024	high-1536x1024	$0.199

Image to Image (Image Editing)

GPT Image v1.5 API Documentation

https://gateway.pixazo.ai/gpt-image-1-5/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

GPT Image 1.5 Edit generate request

Request Code

POST https://gateway.pixazo.ai/gpt-image-1-5/v1/image-to-image/editing
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
  ],
  "num_images": 1,
  "image_size": "auto",
  "background": "auto",
  "quality": "high",
  "input_fidelity": "high",
  "output_format": "png",
  "sync_mode": false
}

import requests

url = "https://gateway.pixazo.ai/gpt-image-1-5/v1/image-to-image/editing"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
    "image_urls": [
        "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
    ],
    "num_images": 1,
    "image_size": "auto",
    "background": "auto",
    "quality": "high",
    "input_fidelity": "high",
    "output_format": "png",
    "sync_mode": false
}

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

const url = "https://gateway.pixazo.ai/gpt-image-1-5/v1/image-to-image/editing";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
  ],
  "num_images": 1,
  "image_size": "auto",
  "background": "auto",
  "quality": "high",
  "input_fidelity": "high",
  "output_format": "png",
  "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/gpt-image-1-5/v1/image-to-image/editing" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
    "image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
    ],
    "num_images": 1,
    "image_size": "auto",
    "background": "auto",
    "quality": "high",
    "input_fidelity": "high",
    "output_format": "png",
    "sync_mode": false
  }'

Output

{
  "request_id": "gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

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 - GPT Image 1.5 Edit generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	2–32,000 characters	Text description of the desired edit (2–32,000 characters). Must clearly specify changes to the reference image.
image_urls	Yes	string[]	—	—	Upload the image you want to edit. Add more than one to combine them into a single result. JPG, PNG or WebP; under 50 MB each.
num_images	No	integer	1	1, 2, 3, 4	Number of edited images to generate. Allowed values: 1, 2, 3, 4.
image_size	No	enum	"auto"	auto, 1024x1024, 1536x1024, 1024x1536	Output image dimensions. Allowed values: `auto`, `1024x1024`, `1536x1024`, `1024x1536`. `auto` selects size based on input image.
background	No	enum	"auto"	auto, transparent, opaque	Sets how the background is handled. Transparent removes it for a cut-out; Opaque fills it with a neutral tone.
quality	No	enum	"high"	low, medium, high	Sets how much detail is kept in the edit. High looks the sharpest but takes longer and costs more; Low is good for quick drafts.
input_fidelity	No	enum	"high"	low, high	Sets how closely the result sticks to your original image. High keeps more of its texture and detail, which suits faces and fine detail; Low gives the model more freedom to change things.
output_format	No	enum	"png"	jpeg, png, webp	File format of generated images. Allowed values: `jpeg`, `png`, `webp`.
mask_image_url	No	string	—	—	Optional. Upload a PNG with an alpha channel, the same size as the one you are editing: fully transparent pixels mark the areas to change, opaque pixels stay as they are. A black-and-white or grayscale PNG has no alpha channel and is rejected. Under 4 MB.
sync_mode	No	boolean	false	—	If `true`, returns media as base64-encoded data URI inline in the response. If `false`, returns a polling ID and async output URL.

Content Item Types & Limits

Type	Max	Format / Size	Description
image_urls	—	JPG, PNG, WEBP · < 50 MB	Image(s) to edit.
mask_image_url	1	PNG with an alpha channel · < 4 MB	Optional mask; must match image size. Transparent pixels mark the region to edit.

Example Request

{
  "prompt": "Replace the sky with a dramatic sunset and add a flock of birds in the distance",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/nano-banana-2-image-to-image-batch_019eacab-dc06-7502-95d0-927f64f29bb60/output.jpg"
  ],
  "num_images": 1,
  "image_size": "auto",
  "background": "auto",
  "quality": "high",
  "input_fidelity": "high",
  "output_format": "png",
  "sync_mode": false
}

Response

{
  "request_id": "gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_API_KEY

Response Handling

Common status codes.

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 — Model not found
{
  "error": "Model not found",
  "message": "Model 'gpt-image-1-5' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-image-1-5",
  "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/gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "gpt-image-1-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-image-1-5",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-1-5_019dxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "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	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.

GPT Image v1.5 API Pricing

Resolution	Model	Price (USD)
1024x1024	low-1024x1024	$0.009
1024x1536	low-1024x1536	$0.013
1536x1024	low-1536x1024	$0.013
1024x1024	medium-1024x1024	$0.034
1024x1536	medium-1024x1536	$0.051
1536x1024	medium-1536x1024	$0.05
1024x1024	high-1024x1024	$0.133
1024x1536	high-1024x1536	$0.20
1536x1024	high-1536x1024	$0.199

⚡ 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

2,167,900last 30d

~72,263 per day

Success rate

98.5%

of completed generations

Generation time

109.3savg

p95 3.6min

Requests

Aug 3max 268,000Sep 1

GPT Image 2Avg 70,250/day

GPT Image v1.5Avg 2,013/day

Generation Time

Aug 3max 3.3minSep 1

GPT Image 2Avg 109.2s

GPT Image v1.5Avg 100.1s

Error Rate

Aug 3max 100.0%Sep 1

GPT Image 2Avg 1.5%

GPT Image v1.5Avg 1.7%

〰 Uptime

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

Avg. Success Rate (30d)

98.47%

across all generations of this model family

Uptime

Aug 3max 100%Sep 1

GPT Image 2Avg 98.47%

GPT Image v1.5Avg 98.25%