Pixazo API→Models→Image to Image API→Grok Imagine Image

Grok Imagine Image 2.0 API, Grok Imagine Image API: Pricing, Documentation

Grok Imagine Image 2.0 API, developers can create new images from text prompts and transform existing images using xAI's image model.

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 →

Grok Imagine Image 2.0 API Documentation

Generate up to four images from a text prompt with xAI's Grok Imagine Image 2.0. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the images.

POST https://gateway.pixazo.ai/grok-imagine-image-v2/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 - Grok Imagine Image 2.0

Request Code

POST https://gateway.pixazo.ai/grok-imagine-image-v2/v1/text-to-image
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Abstract human silhouette, golden particles bursting outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "quality": "medium",
  "output_format": "jpeg"
}

import requests

url = "https://gateway.pixazo.ai/grok-imagine-image-v2/v1/text-to-image"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "Abstract human silhouette, golden particles bursting outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "quality": "medium",
  "output_format": "jpeg"
}

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

const res = await fetch("https://gateway.pixazo.ai/grok-imagine-image-v2/v1/text-to-image", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "prompt": "Abstract human silhouette, golden particles bursting outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "quality": "medium",
  "output_format": "jpeg"
})
});
console.log(await res.json());

curl -X POST 'https://gateway.pixazo.ai/grok-imagine-image-v2/v1/text-to-image' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"prompt": "Abstract human silhouette, golden particles bursting outward representing joy, data visualization style", "num_images": 1, "aspect_ratio": "1:1", "resolution": "1k", "quality": "medium", "output_format": "jpeg"}'

Output

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state.

Header	Required	Description
X-Webhook-URL	To enable	HTTPS URL to receive the Webhook callback.
X-Webhook-Mode	No	`terminal` (default) or `sync` (per-poll callbacks).

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/grok-imagine-image-v2/v1/text-to-image' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"prompt": "Abstract human silhouette, golden particles bursting outward representing joy, data visualization style", "num_images": 1, "aspect_ratio": "1:1", "resolution": "1k", "quality": "medium", "output_format": "jpeg"}'

Callback Payload (success)

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-image-v2",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.jpg"
    ],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-08-13T09:14:16.102Z",
  "completed_at": "2026-08-13T09:14:41.870Z"
}

Failure callback shape

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "grok-imagine-image-v2",
  "error": "Description of the failure"
}

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	Up to 8,000 characters	Text description of the image you want.
`num_images`	No	integer	`1`	`1`–`4`	How many images to generate. Each one is billed, so 4 images cost four times the per-image rate.
`resolution`	No	string	`1k`	`1k`, `2k`	Output resolution. Affects the price — see Pricing.
`quality`	No	string	`medium`	`low`, `medium`	Rendering quality. Also affects the price, independently of resolution — the two combine into a four-cell rate table.
`aspect_ratio`	No	string	`1:1`	`2:1`, `20:9`, `19.5:9`, `16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`, `9:19.5`, `9:20`, `1:2`	Frame shape of the output. Does not affect the price. `auto` is not accepted here — it only applies when editing, where there is an input image to match.
`output_format`	No	string	`jpeg`	`jpeg`, `png`, `webp`	Encoding of the returned file. Does not affect the price.

Notes

quality and resolution are independent price axes — see Pricing for the four-cell table. num_images is capped at 4 and multiplies whichever cell you land in. aspect_ratio does not accept auto on this operation. The model's sync_mode option is not supported here: it returns images as inline data URIs, which this asynchronous API cannot store or serve, so a request setting it is rejected.

Example Request

{
  "prompt": "Abstract human silhouette, golden particles bursting outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "quality": "medium",
  "output_format": "jpeg"
}

Example Response

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Required	Description
Content-Type	Yes	`application/json`
Ocp-Apim-Subscription-Key	Yes	Your API subscription key.
X-Webhook-URL	No	Enable Webhook callbacks.

Response Handling

Status Code	Meaning
202	Accepted — request queued; returns `request_id` and `polling_url`.
400	Bad request — a missing or out-of-range parameter. The message names the field.
401	Unauthorized — missing or invalid subscription key.
402	Insufficient balance.
429	Too many requests.
500	Internal server error.

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or ERROR), then download output.media_url. With num_images above 1, media_url holds one entry per image.

curl 'https://gateway.pixazo.ai/v2/requests/status/grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-image-v2",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.jpg"
    ],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-08-13T09:14:16.102Z",
  "completed_at": "2026-08-13T09:14:41.870Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier.
status	string	QUEUED, PROCESSING, COMPLETED or ERROR.
model_id	string	The model that handled the request.
output.media_url	array	One URL per generated image.
output.media_type	string	MIME type of the generated images.
created_at	string	Request creation timestamp.
completed_at	string	Completion timestamp.
error	string	Error message when `status` is ERROR.

Status Values & Flow

QUEUED → PROCESSING → COMPLETED (success) or ERROR (failure).

Pricing

Billed per output image, at a rate set by quality and resolution together. Aspect ratio and output format do not affect the price.

Quality	Resolution	Per image	4 images
`low`	`1k`	$0.04	$0.16
`medium`	`1k`	$0.06	$0.24
`low`	`2k`	$0.06	$0.24
`medium`	`2k`	$0.08	$0.32

A request generating num_images images costs that many times the cell rate.

Failed requests are not billed.

Grok Imagine Image 2.0 API Pricing

No data available

Could not load current pricing

Image to Image (Edit Image)

Grok Imagine Image 2.0 API Documentation

Edit up to three images with a text instruction. The default auto aspect ratio keeps the shape of your first input. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the images.

POST https://gateway.pixazo.ai/grok-imagine-image-v2/v1/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) - Grok Imagine Image 2.0

Request Code

POST https://gateway.pixazo.ai/grok-imagine-image-v2/v1/edit
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "quality": "medium",
  "output_format": "jpeg"
}

import requests

url = "https://gateway.pixazo.ai/grok-imagine-image-v2/v1/edit"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "quality": "medium",
  "output_format": "jpeg"
}

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

const res = await fetch("https://gateway.pixazo.ai/grok-imagine-image-v2/v1/edit", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "quality": "medium",
  "output_format": "jpeg"
})
});
console.log(await res.json());

curl -X POST 'https://gateway.pixazo.ai/grok-imagine-image-v2/v1/edit' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"prompt": "Make this scene more realistic but still keep the game vibes", "num_images": 1, "aspect_ratio": "auto", "resolution": "1k", "image_urls": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"], "quality": "medium", "output_format": "jpeg"}'

Output

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state.

Header	Required	Description
X-Webhook-URL	To enable	HTTPS URL to receive the Webhook callback.
X-Webhook-Mode	No	`terminal` (default) or `sync` (per-poll callbacks).

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/grok-imagine-image-v2/v1/edit' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"prompt": "Make this scene more realistic but still keep the game vibes", "num_images": 1, "aspect_ratio": "auto", "resolution": "1k", "image_urls": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"], "quality": "medium", "output_format": "jpeg"}'

Callback Payload (success)

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-image-v2",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.jpg"
    ],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-08-13T09:14:16.102Z",
  "completed_at": "2026-08-13T09:14:41.870Z"
}

Failure callback shape

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "grok-imagine-image-v2",
  "error": "Description of the failure"
}

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	Up to 8,000 characters	Text description of the image you want.
`image_urls`	Yes	array of string	—	1–3 publicly reachable http(s) urls	The images to edit. Fetched server-side, so they must be reachable from the internet. Each input adds $0.01 to the request — see Pricing.
`num_images`	No	integer	`1`	`1`–`4`	How many images to generate. Each one is billed, so 4 images cost four times the per-image rate.
`resolution`	No	string	`1k`	`1k`, `2k`	Output resolution. Affects the price — see Pricing.
`quality`	No	string	`medium`	`low`, `medium`	Rendering quality. Also affects the price, independently of resolution — the two combine into a four-cell rate table.
`aspect_ratio`	No	string	`auto`	`auto`, `2:1`, `20:9`, `19.5:9`, `16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`, `9:19.5`, `9:20`, `1:2`	Frame shape of the output. Does not affect the price. `auto` preserves the aspect ratio of the first input image.
`output_format`	No	string	`jpeg`	`jpeg`, `png`, `webp`	Encoding of the returned file. Does not affect the price.

Notes

quality and resolution are independent price axes — see Pricing for the four-cell table. num_images is capped at 4 and multiplies whichever cell you land in; image_urls is capped at 3 and each input adds a flat surcharge. The model's sync_mode option is not supported here: it returns images as inline data URIs, which this asynchronous API cannot store or serve, so a request setting it is rejected.

Example Request

{
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg"
  ],
  "quality": "medium",
  "output_format": "jpeg"
}

Example Response

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Required	Description
Content-Type	Yes	`application/json`
Ocp-Apim-Subscription-Key	Yes	Your API subscription key.
X-Webhook-URL	No	Enable Webhook callbacks.

Response Handling

Status Code	Meaning
202	Accepted — request queued; returns `request_id` and `polling_url`.
400	Bad request — a missing or out-of-range parameter. The message names the field.
401	Unauthorized — missing or invalid subscription key.
402	Insufficient balance.
429	Too many requests.
500	Internal server error.

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or ERROR), then download output.media_url. With num_images above 1, media_url holds one entry per image.

curl 'https://gateway.pixazo.ai/v2/requests/status/grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "grok-imagine-image-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-image-v2",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.jpg"
    ],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-08-13T09:14:16.102Z",
  "completed_at": "2026-08-13T09:14:41.870Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier.
status	string	QUEUED, PROCESSING, COMPLETED or ERROR.
model_id	string	The model that handled the request.
output.media_url	array	One URL per generated image.
output.media_type	string	MIME type of the generated images.
created_at	string	Request creation timestamp.
completed_at	string	Completion timestamp.
error	string	Error message when `status` is ERROR.

Status Values & Flow

QUEUED → PROCESSING → COMPLETED (success) or ERROR (failure).

Pricing

Billed per output image, at a rate set by quality and resolution together. Aspect ratio and output format do not affect the price.

Quality	Resolution	Per image	4 images
`low`	`1k`	$0.04	$0.16
`medium`	`1k`	$0.06	$0.24
`low`	`2k`	$0.06	$0.24
`medium`	`2k`	$0.08	$0.32

Editing adds $0.01 per input image, charged once per input — not once per output. Three inputs producing two 1k medium images is $0.06×2 + $0.01×3 = $0.15.

Failed requests are not billed.

Grok Imagine Image 2.0 API Pricing

No data available

Could not load current pricing

2. Grok Imagine Image

Grok Imagine Image API Documentation

https://gateway.pixazo.ai/grok-imagine-pro-text-to-image-quality/v1/grok-imagine-pro-text-to-image-quality-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

Grok Imagine Pro Text to Image (Quality) generate request

Request Code

POST https://gateway.pixazo.ai/grok-imagine-pro-text-to-image-quality/v1/grok-imagine-pro-text-to-image-quality-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Abstract human silhouette, golden particles ready to burst outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "output_format": "jpeg"
}

import requests

url = "https://gateway.pixazo.ai/grok-imagine-pro-text-to-image-quality/v1/grok-imagine-pro-text-to-image-quality-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Abstract human silhouette, golden particles ready to burst outward representing joy, data visualization style",
    "num_images": 1,
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "output_format": "jpeg"
}

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

const url = "https://gateway.pixazo.ai/grok-imagine-pro-text-to-image-quality/v1/grok-imagine-pro-text-to-image-quality-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Abstract human silhouette, golden particles ready to burst outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "output_format": "jpeg"
};

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/grok-imagine-pro-text-to-image-quality/v1/grok-imagine-pro-text-to-image-quality-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Abstract human silhouette, golden particles ready to burst outward representing joy, data visualization style",
    "num_images": 1,
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "output_format": "jpeg"
  }'

Output

{
  "request_id": "grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-pro-text-to-image-quality_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": "grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-pro-text-to-image-quality",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.jpeg"
    ],
    "media_type": "image/jpeg"
  },
  "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": "grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "grok-imagine-pro-text-to-image-quality",
  "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 - Grok Imagine Pro Text to Image (Quality) generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	Up to 8000 characters	Text description of the desired image. Must be descriptive and detailed for optimal results.
num_images	No	integer	1	1–4	Number of images to generate. Must be between 1 and 4.
aspect_ratio	No	string	"1:1"	"2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2"	Aspect ratio of the generated image.
resolution	No	string	"1k"	"1k", "2k"	Resolution of the generated image. 1k for standard resolution, 2k for high resolution.
output_format	No	string	"jpeg"	"jpeg", "png", "webp"	The format of the generated image.
sync_mode	No	boolean	false	true, false	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Example Request

{
  "prompt": "Abstract human silhouette, golden particles ready to burst outward representing joy, data visualization style",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "output_format": "jpeg"
}

Response

{
  "request_id": "grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-pro-text-to-image-quality_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 'grok-imagine-pro-text-to-image-quality' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "grok-imagine-pro-text-to-image-quality",
  "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/grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "grok-imagine-pro-text-to-image-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-pro-text-to-image-quality",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/grok-imagine-pro-text-to-image-quality_019dxxxx/output.jpeg"],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

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.

Grok Imagine Image API Pricing

No data available

Could not load current pricing

Image to Image (Image Editing)

Grok Imagine Image API Documentation

https://gateway.pixazo.ai/grok-imagine-pro-edit-quality/v1/grok-imagine-pro-edit-quality-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

Grok Imagine Pro Edit (Quality) generate request

Request Code

POST https://gateway.pixazo.ai/grok-imagine-pro-edit-quality/v1/grok-imagine-pro-edit-quality-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
  ],
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "output_format": "jpeg"
}

import requests

url = "https://gateway.pixazo.ai/grok-imagine-pro-edit-quality/v1/grok-imagine-pro-edit-quality-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Make this scene more realistic but still keep the game vibes",
    "image_urls": [
        "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
    ],
    "num_images": 1,
    "aspect_ratio": "auto",
    "resolution": "1k",
    "output_format": "jpeg"
}

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

const url = "https://gateway.pixazo.ai/grok-imagine-pro-edit-quality/v1/grok-imagine-pro-edit-quality-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
  ],
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "output_format": "jpeg"
};

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/grok-imagine-pro-edit-quality/v1/grok-imagine-pro-edit-quality-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Make this scene more realistic but still keep the game vibes",
    "image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
    ],
    "num_images": 1,
    "aspect_ratio": "auto",
    "resolution": "1k",
    "output_format": "jpeg"
  }'

Output

{
  "request_id": "grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-pro-edit-quality_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": "grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-pro-edit-quality",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.jpeg"
    ],
    "media_type": "image/jpeg"
  },
  "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": "grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "grok-imagine-pro-edit-quality",
  "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.

⚠ Content policy. The Grok Imagine provider screens every prompt and reference image. Requests involving nudity, sexually suggestive content, or edits that preserve the identity of a real person are rejected upstream with a 422 content-flagged error and are not billed. Keep prompts and reference images policy-compliant to avoid failures.

Request Parameters - Grok Imagine Pro Edit (Quality) generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	Up to 8000 characters	Text instruction describing the desired edit to apply to the source image(s).
image_urls	Yes	string[]	—	1–3 image URLs	List of URLs of the images to edit. A maximum of 3 images are supported.
num_images	No	integer	1	1–4	Number of output images to generate. Must be between 1 and 4.
aspect_ratio	No	string	"auto"	"auto", "2:1", "20:9", "19.5:9", "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "9:19.5", "9:20", "1:2"	Aspect ratio of the edited image. When set to auto (the default), the output preserves the aspect ratio of the first input image.
resolution	No	string	"1k"	"1k", "2k"	Resolution of the generated image. 1k for standard resolution, 2k for high resolution.
output_format	No	string	"jpeg"	"jpeg", "png", "webp"	The format of the generated image.
sync_mode	No	boolean	false	true, false	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Content Item Types & Limits

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

Example Request

{
  "prompt": "Make this scene more realistic but still keep the game vibes",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg"
  ],
  "num_images": 1,
  "aspect_ratio": "auto",
  "resolution": "1k",
  "output_format": "jpeg"
}

Response

{
  "request_id": "grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/grok-imagine-pro-edit-quality_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 'grok-imagine-pro-edit-quality' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "grok-imagine-pro-edit-quality",
  "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/grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "grok-imagine-pro-edit-quality_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "grok-imagine-pro-edit-quality",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/grok-imagine-pro-edit-quality_019dxxxx/output.jpeg"
    ],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

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.

Grok Imagine Image API Pricing

No data available

Could not load current pricing

⚡ 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

111,700last 30d

~3,723 per day

Success rate

99.3%

of completed generations

Generation time

65.3savg

p95 2.1min

Requests

Aug 9max 12,100Sep 7

Grok Imagine ImageAvg 3,100/day

Grok Imagine Image 2.0Avg 623/day

Generation Time

Aug 9max 9.1minSep 7

Grok Imagine ImageAvg 65.4s

Grok Imagine Image 2.0Avg 69.4s

Error Rate

Aug 9max 22.2%Sep 7

Grok Imagine ImageAvg 0.7%

Grok Imagine Image 2.0Avg 1.1%

〰 Uptime

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

Avg. Success Rate (30d)

99.28%

across all generations of this model family

Uptime

Aug 9max 100%Sep 7

Grok Imagine ImageAvg 99.34%

Grok Imagine Image 2.0Avg 98.93%