Flux Video Upscale API Documentation

POST https://gateway.pixazo.ai/flux-video-upscale/v1/video-to-video

Authentication

All requests require an API key passed via header.

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

Flux Video Upscale generate request

Request Code

POST https://gateway.pixazo.ai/flux-video-upscale/v1/video-to-video
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "video_url": "https://v3b.fal.media/files/b/0a93a27d/-iFpecUCsSdwXVMevsZa3_output_5s_448x256.mp4",
  "upscale_factor": 2,
  "creativity": 1,
  "safety_tolerance": 2
}

import requests

url = "https://gateway.pixazo.ai/flux-video-upscale/v1/video-to-video"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "video_url": "https://v3b.fal.media/files/b/0a93a27d/-iFpecUCsSdwXVMevsZa3_output_5s_448x256.mp4",
    "upscale_factor": 2,
    "creativity": 1,
    "safety_tolerance": 2
}

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

const url = "https://gateway.pixazo.ai/flux-video-upscale/v1/video-to-video";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "video_url": "https://v3b.fal.media/files/b/0a93a27d/-iFpecUCsSdwXVMevsZa3_output_5s_448x256.mp4",
  "upscale_factor": 2,
  "creativity": 1,
  "safety_tolerance": 2
};

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/flux-video-upscale/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "video_url": "https://v3b.fal.media/files/b/0a93a27d/-iFpecUCsSdwXVMevsZa3_output_5s_448x256.mp4",
    "upscale_factor": 2,
    "creativity": 1,
    "safety_tolerance": 2
  }'

Output

{
  "request_id": "flux-video-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-video-upscale_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 - Flux Video Upscale generate request

Parameter	Required	Type	Default	Allowed values / range	Description
video_url	Yes	string	—	non-empty; ≤ 50 MB, ≤20 seconds	Publicly accessible URL of the input MP4 video. Must be ≤20 seconds and ≤50 MB.
upscale_factor	No	number	2	1.5 – 3	Output scaling factor. Any value in the range is accepted, including fractional values such as 1.5 or 2.5. The source aspect ratio is preserved. This also sets your price: the per-second rate is chosen from the OUTPUT height (your source height × this factor), and anything at or below 1080 is charged at the 1080p rate. See the pricing table below.
creativity	No	integer	1	0, 1	Use 0 for a source-faithful upscale or 1 for creative detail enhancement. Send it as a number, not a quoted string.
prompt	No	string	—	≤ 5000 characters	Optional text description used to guide creative detail enhancement (the creativity: 1 mode).
safety_tolerance	No	integer	2	0 – 4	Moderation strictness. Lower values are stricter: 0 is the strictest and 4 the most permissive.

Example Request

{
  "video_url": "https://v3b.fal.media/files/b/0a93a27d/-iFpecUCsSdwXVMevsZa3_output_5s_448x256.mp4",
  "upscale_factor": 2,
  "creativity": 1,
  "safety_tolerance": 2
}

Response

{
  "request_id": "flux-video-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-video-upscale_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 'flux-video-upscale' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-video-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-video-upscale",
  "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/flux-video-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-video-upscale_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-video-upscale",
  "error": null,
  "output": { "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-video-upscale_019dxxxx/output.mp4"], "media_type": "video/mp4" },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

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.

Flux Video Upscale API Pricing

Resolution	Price (USD)
Creative, up to 1080p / per second (default)	$0.20
Creative, up to 2K / per second	$0.35
Creative, 4K / per second	$0.79
Precise, up to 1080p / per second	$0.14
Precise, up to 2K / per second	$0.25
Precise, 4K / per second	$0.55

FLUX 3 Video API Documentation

Generate video with synchronised audio from a text prompt alone, up to 20 seconds at HD or FHD. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the video.

POST https://gateway.pixazo.ai/flux-3-video/v1/text-to-video

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 Video - FLUX 3 Video

Request Code

POST https://gateway.pixazo.ai/flux-3-video/v1/text-to-video
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "resolution": "hd",
  "duration": 5
}

import requests

url = "https://gateway.pixazo.ai/flux-3-video/v1/text-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "resolution": "hd",
  "duration": 5
}

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

const res = await fetch("https://gateway.pixazo.ai/flux-3-video/v1/text-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "resolution": "hd",
  "duration": 5
})
});
console.log(await res.json());

curl -X POST 'https://gateway.pixazo.ai/flux-3-video/v1/text-to-video' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.", "resolution": "hd", "duration": 5}'

Output

{
  "request_id": "flux-3-video-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-3-video-text-to-video_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. Provide a Webhook URL via header on the submit request. Video renders take minutes rather than seconds, so a webhook is usually the better fit here.

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

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/flux-3-video/v1/text-to-video' \
  -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": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.", "resolution": "hd", "duration": 5}'

Callback Payload (success)

{
  "request_id": "flux-3-video-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-3-video-text-to-video",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-08-05T11:20:04.102Z",
  "completed_at": "2026-08-05T11:23:58.870Z"
}

Failure callback shape

{
  "request_id": "flux-3-video-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-3-video-text-to-video",
  "error": "Description of the failure"
}

Delivery semantics

terminal mode: one Webhook callback when the request is COMPLETED or ERROR.
sync mode: a Webhook callback on each status change.
Callbacks are idempotent on request_id — de-duplicate on it.
Respond 200 within a few seconds; the Webhook endpoint must be HTTPS.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	1 character or more	Free-form description of the video. When `generate_audio` is on, the soundtrack is derived from this prompt too — describing the sound (“rain patter, quiet kitchen”) shapes what you get.
`aspect_ratio`	No	string	`auto`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Output aspect ratio. `auto` picks one from the prompt and any reference media.
`duration`	No	integer or string	`auto`	a whole number 5–20, or `auto`	Length of the clip in seconds. `auto` fits the content. Duration does not change the price.
`resolution`	No	string	`hd`	`hd`, `fhd`	`fhd` runs the result through the video upsampler and costs more — see Pricing.
`generate_audio`	No	boolean	`true`	`true`, `false`	Generate a synchronised soundtrack alongside the video.
`safety_tolerance`	No	integer	`2`	0–4	Moderation tolerance, 0 (strictest) to 4. Sexual content is capped at 3 and hate content at 2 regardless of what you request; any request carrying reference media is capped at 2.

Notes

Nothing but a prompt is required. Add aspect_ratio and duration when you need a specific shape or length.

Example Request

{
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "resolution": "hd",
  "duration": 5
}

Example Response

{
  "request_id": "flux-3-video-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-3-video-text-to-video_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 (see Webhook section).

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 from the submit response until status is COMPLETED (or ERROR), then download output.media_url. A render typically takes a few minutes.

curl 'https://gateway.pixazo.ai/v2/requests/status/flux-3-video-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "flux-3-video-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-3-video-text-to-video",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-08-05T11:20:04.102Z",
  "completed_at": "2026-08-05T11:23:58.870Z"
}

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	URL of the generated mp4 (24fps, with audio unless disabled).
output.media_type	string	MIME type of the video — `video/mp4`.
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 as a flat price per render, set by the resolution you request. Duration does not change the price — a 20-second clip costs the same as a 5-second one.

Request	Cost per video
Text to Video at `hd`	$0.17
Text to Video at `fhd`	$0.29

Failed requests are not billed.

FLUX 3 Video API Pricing

Resolution	Price (USD)
hd	$0.17
fhd	$0.29

FLUX 3 Video API Documentation

Animate one or more still images into video with synchronised audio. Supply up to ten keyframes, optionally pinned to a second on the timeline. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the video.

POST https://gateway.pixazo.ai/flux-3-video/v1/keyframes-to-video

Authentication

All requests require an API key passed via header.

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

Keyframes to Video - FLUX 3 Video

Request Code

POST https://gateway.pixazo.ai/flux-3-video/v1/keyframes-to-video
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "keyframes": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
  "resolution": "hd",
  "duration": 5
}

import requests

url = "https://gateway.pixazo.ai/flux-3-video/v1/keyframes-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "keyframes": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
  "resolution": "hd",
  "duration": 5
}

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

const res = await fetch("https://gateway.pixazo.ai/flux-3-video/v1/keyframes-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "keyframes": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
  "resolution": "hd",
  "duration": 5
})
});
console.log(await res.json());

curl -X POST 'https://gateway.pixazo.ai/flux-3-video/v1/keyframes-to-video' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.", "keyframes": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png", "resolution": "hd", "duration": 5}'

Output

{
  "request_id": "flux-3-video-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-3-video-image-to-video_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. Provide a Webhook URL via header on the submit request. Video renders take minutes rather than seconds, so a webhook is usually the better fit here.

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

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/flux-3-video/v1/keyframes-to-video' \
  -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": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.", "keyframes": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png", "resolution": "hd", "duration": 5}'

Callback Payload (success)

{
  "request_id": "flux-3-video-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-3-video-image-to-video",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-08-05T11:20:04.102Z",
  "completed_at": "2026-08-05T11:23:58.870Z"
}

Failure callback shape

{
  "request_id": "flux-3-video-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-3-video-image-to-video",
  "error": "Description of the failure"
}

Delivery semantics

terminal mode: one Webhook callback when the request is COMPLETED or ERROR.
sync mode: a Webhook callback on each status change.
Callbacks are idempotent on request_id — de-duplicate on it.
Respond 200 within a few seconds; the Webhook endpoint must be HTTPS.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	1 character or more	Free-form description of the video. When `generate_audio` is on, the soundtrack is derived from this prompt too — describing the sound (“rain patter, quiet kitchen”) shapes what you get.
`keyframes`	Yes	string or array	—	1–10 images, optionally timed	The image(s) to animate, each a public https url or a base64 data URI. Accepts a single image; a single `[seconds, image]` pair; up to 10 untimed images (one starts the video, two start and end it, more are spread evenly); or up to 10 `[seconds, image]` pairs. Three or more untimed images require an explicit whole-number `duration`.
`aspect_ratio`	No	string	`auto`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Output aspect ratio. `auto` picks one from the prompt and any reference media.
`duration`	No	integer or string	`auto`	a whole number 5–20, or `auto`	Length of the clip in seconds. `auto` fits the content. Duration does not change the price.
`resolution`	No	string	`hd`	`hd`, `fhd`	`fhd` runs the result through the video upsampler and costs more — see Pricing.
`generate_audio`	No	boolean	`true`	`true`, `false`	Generate a synchronised soundtrack alongside the video.
`safety_tolerance`	No	integer	`2`	0–4	Moderation tolerance, 0 (strictest) to 4. Sexual content is capped at 3 and hate content at 2 regardless of what you request; any request carrying reference media is capped at 2.

Notes

Keyframes may be plain images or [seconds, image] pairs — but not a mix of the two in one request.

Using more than one keyframe

keyframes accepts four shapes. Pick whichever fits — all four are equivalent to the model, they differ only in how much control you take over timing.

1. A single image — the opening frame

The video starts here and the prompt drives the rest.

{
  "prompt": "gentle push in on the scene",
  "keyframes": "https://your-server.com/frame-1.jpg",
  "resolution": "hd",
  "duration": 5
}

2. Two images — start and end

With exactly two untimed images, the first opens the video and the second closes it.

{
  "prompt": "morph smoothly from the first scene to the second",
  "keyframes": [
    "https://your-server.com/frame-1.jpg",
    "https://your-server.com/frame-2.jpg"
  ],
  "resolution": "hd",
  "duration": 5
}

3. Several untimed images — spread evenly

The first opens the video, the last closes it, and the rest fall evenly in between. With three or more untimed images you must also send an explicit whole-number duration — there is no last-pair second for auto to derive the length from.

{
  "prompt": "drift across the scenes",
  "keyframes": [
    "https://your-server.com/frame-1.jpg",
    "https://your-server.com/frame-2.jpg",
    "https://your-server.com/frame-3.jpg",
    "https://your-server.com/frame-4.jpg"
  ],
  "resolution": "hd",
  "duration": 10
}

4. Timed `[seconds, image]` pairs — exact placement

Pin each image to a second on the timeline. With duration: "auto" the video runs to the last pair's second, rounded up.

{
  "prompt": "drift between the two scenes",
  "keyframes": [
    [
      0,
      "https://your-server.com/frame-1.jpg"
    ],
    [
      4,
      "https://your-server.com/frame-2.jpg"
    ]
  ],
  "resolution": "hd",
  "duration": 5
}

Limits

Ten keyframes maximum. An eleventh is rejected — that is the model's ceiling, not a gateway restriction.
Do not mix the two styles. A list must be all plain images or all [seconds, image] pairs, never both in one request.
Each image is a public https url or a data:image/...;base64 URI. We fetch urls server-side, so they must be reachable from the internet — a signed url is fine, a private one is not.

Example Request

{
  "prompt": "A cozy ramen shop on a rainy Tokyo night, steam rising from the broth. Rain patter and quiet kitchen sounds.",
  "keyframes": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png",
  "resolution": "hd",
  "duration": 5
}

Example Response

{
  "request_id": "flux-3-video-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-3-video-image-to-video_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 (see Webhook section).

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 from the submit response until status is COMPLETED (or ERROR), then download output.media_url. A render typically takes a few minutes.

curl 'https://gateway.pixazo.ai/v2/requests/status/flux-3-video-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "flux-3-video-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-3-video-image-to-video",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-08-05T11:20:04.102Z",
  "completed_at": "2026-08-05T11:23:58.870Z"
}

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	URL of the generated mp4 (24fps, with audio unless disabled).
output.media_type	string	MIME type of the video — `video/mp4`.
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 as a flat price per render, set by the resolution you request. Duration does not change the price — a 20-second clip costs the same as a 5-second one.

Request	Cost per video
Keyframes to Video at `hd`	$0.17
Keyframes to Video at `fhd`	$0.29

Failed requests are not billed.

FLUX 3 Video API Pricing

Resolution	Price (USD)
hd	$0.17
fhd	$0.29

FLUX 3 Video API Documentation

Continue an existing clip. The model reads the final frames of the video you supply and carries the motion onward, with synchronised audio. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the video.

POST https://gateway.pixazo.ai/flux-3-video/v1/video-to-video

Authentication

All requests require an API key passed via header.

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

Video to Video - FLUX 3 Video

Request Code

POST https://gateway.pixazo.ai/flux-3-video/v1/video-to-video
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "the camera pulls back to reveal the whole street",
  "start_video": "https://your-server.com/clip.mp4",
  "resolution": "hd",
  "duration": 5
}

import requests

url = "https://gateway.pixazo.ai/flux-3-video/v1/video-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "prompt": "the camera pulls back to reveal the whole street",
  "start_video": "https://your-server.com/clip.mp4",
  "resolution": "hd",
  "duration": 5
}

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

const res = await fetch("https://gateway.pixazo.ai/flux-3-video/v1/video-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "prompt": "the camera pulls back to reveal the whole street",
  "start_video": "https://your-server.com/clip.mp4",
  "resolution": "hd",
  "duration": 5
})
});
console.log(await res.json());

curl -X POST 'https://gateway.pixazo.ai/flux-3-video/v1/video-to-video' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"prompt": "the camera pulls back to reveal the whole street", "start_video": "https://your-server.com/clip.mp4", "resolution": "hd", "duration": 5}'

Output

{
  "request_id": "flux-3-video-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-3-video-video-to-video_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. Provide a Webhook URL via header on the submit request. Video renders take minutes rather than seconds, so a webhook is usually the better fit here.

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

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/flux-3-video/v1/video-to-video' \
  -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": "the camera pulls back to reveal the whole street", "start_video": "https://your-server.com/clip.mp4", "resolution": "hd", "duration": 5}'

Callback Payload (success)

{
  "request_id": "flux-3-video-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-3-video-video-to-video",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-08-05T11:20:04.102Z",
  "completed_at": "2026-08-05T11:23:58.870Z"
}

Failure callback shape

{
  "request_id": "flux-3-video-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-3-video-video-to-video",
  "error": "Description of the failure"
}

Delivery semantics

terminal mode: one Webhook callback when the request is COMPLETED or ERROR.
sync mode: a Webhook callback on each status change.
Callbacks are idempotent on request_id — de-duplicate on it.
Respond 200 within a few seconds; the Webhook endpoint must be HTTPS.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	1 character or more	Free-form description of the video. When `generate_audio` is on, the soundtrack is derived from this prompt too — describing the sound (“rain patter, quiet kitchen”) shapes what you get.
`start_video`	Yes	string	—	https url or base64 mp4, ≤50MB, ≤15s	The video to continue. The new clip carries on from its final frames.
`aspect_ratio`	No	string	`auto`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Output aspect ratio. `auto` picks one from the prompt and any reference media.
`duration`	No	integer or string	`auto`	a whole number 5–20, or `auto`	Length of the clip in seconds. `auto` fits the content. Duration does not change the price.
`resolution`	No	string	`hd`	`hd`, `fhd`	`fhd` runs the result through the video upsampler and costs more — see Pricing.
`generate_audio`	No	boolean	`true`	`true`, `false`	Generate a synchronised soundtrack alongside the video.
`safety_tolerance`	No	integer	`2`	0–4	Moderation tolerance, 0 (strictest) to 4. Sexual content is capped at 3 and hate content at 2 regardless of what you request; any request carrying reference media is capped at 2.

Notes

The source clip must be 15 seconds or less and 50MB or less. Continuation is priced higher than a fresh render — see Pricing.

Example Request

{
  "prompt": "the camera pulls back to reveal the whole street",
  "start_video": "https://your-server.com/clip.mp4",
  "resolution": "hd",
  "duration": 5
}

Example Response

{
  "request_id": "flux-3-video-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-3-video-video-to-video_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 (see Webhook section).

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 from the submit response until status is COMPLETED (or ERROR), then download output.media_url. A render typically takes a few minutes.

curl 'https://gateway.pixazo.ai/v2/requests/status/flux-3-video-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "flux-3-video-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-3-video-video-to-video",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-08-05T11:20:04.102Z",
  "completed_at": "2026-08-05T11:23:58.870Z"
}

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	URL of the generated mp4 (24fps, with audio unless disabled).
output.media_type	string	MIME type of the video — `video/mp4`.
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 as a flat price per render, set by the resolution you request. Duration does not change the price — a 20-second clip costs the same as a 5-second one.

Request	Cost per video
Video to Video at `hd`	$0.41
Video to Video at `fhd`	$0.53

Failed requests are not billed.

FLUX 3 Video API Pricing

Resolution	Price (USD)
hd	$0.41
fhd	$0.53

FLUX 2 Max API Documentation

https://gateway.pixazo.ai/flux-2-max/v1/flux-2-max-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

FLUX 2 Max generate request

Request Code

POST https://gateway.pixazo.ai/flux-2-max/v1/flux-2-max-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "An intricate fantasy castle on a floating island at dusk, volumetric lighting, photoreal",
  "image_size": "landscape_4_3",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "sync_mode": false
}

import requests

url = "https://gateway.pixazo.ai/flux-2-max/v1/flux-2-max-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "An intricate fantasy castle on a floating island at dusk, volumetric lighting, photoreal",
    "image_size": "landscape_4_3",
    "safety_tolerance": "2",
    "enable_safety_checker": true,
    "output_format": "jpeg",
    "sync_mode": false
}

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

const url = "https://gateway.pixazo.ai/flux-2-max/v1/flux-2-max-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "An intricate fantasy castle on a floating island at dusk, volumetric lighting, photoreal",
  "image_size": "landscape_4_3",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "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/flux-2-max/v1/flux-2-max-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
        "prompt": "An intricate fantasy castle on a floating island at dusk, volumetric lighting, photoreal",
        "image_size": "landscape_4_3",
        "safety_tolerance": "2",
        "enable_safety_checker": true,
        "output_format": "jpeg",
        "sync_mode": false
    }'

Output

{
  "request_id": "flux-2-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-max_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 - FLUX 2 Max generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description for image generation. Must be detailed for optimal results.
image_size	No	string or object	landscape_4_3	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9; or {"width": integer, "height": integer}	Preset aspect ratio or custom dimensions. Allowed presets: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Custom object format: {"width": integer, "height": integer}.
output_format	No	string	jpeg	jpeg, png	Output image format. Allowed: jpeg, png.
safety_tolerance	No	string	2	1, 2, 3, 4, 5	NSFW filtering sensitivity level. Higher values are more permissive.
enable_safety_checker	No	boolean	true	—	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	No	boolean	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": "An intricate fantasy castle on a floating island at dusk, volumetric lighting, photoreal",
  "image_size": "landscape_4_3",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "sync_mode": false
}

Response

{
  "request_id": "flux-2-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-max_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 'flux-2-max' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-max",
  "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/flux-2-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-max",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-max_019dxxxx/output.jpg"],
    "media_type": "image/jpeg"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

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.

FLUX 2 Max API Pricing

Usage	Price (USD)
First megapixel	$0.07
Each additional megapixel	$0.03

FLUX 2 Max API Documentation

https://gateway.pixazo.ai/flux-2-max-edit/v1/flux-2-max-edit-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

FLUX 2 Max Edit generate request

Request Code

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

{
  "prompt": "Restyle the scene with warm golden-hour lighting and soft bokeh",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
  ],
  "image_size": "auto",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "sync_mode": false
}

import requests

url = "https://gateway.pixazo.ai/flux-2-max-edit/v1/flux-2-max-edit-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Restyle the scene with warm golden-hour lighting and soft bokeh",
    "image_urls": [
        "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
    ],
    "image_size": "auto",
    "safety_tolerance": "2",
    "enable_safety_checker": true,
    "output_format": "jpeg",
    "sync_mode": false
}

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

const url = "https://gateway.pixazo.ai/flux-2-max-edit/v1/flux-2-max-edit-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Restyle the scene with warm golden-hour lighting and soft bokeh",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
  ],
  "image_size": "auto",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "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/flux-2-max-edit/v1/flux-2-max-edit-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Restyle the scene with warm golden-hour lighting and soft bokeh",
    "image_urls": [
        "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg"
    ],
    "image_size": "auto",
    "safety_tolerance": "2",
    "enable_safety_checker": true,
    "output_format": "jpeg",
    "sync_mode": false
}'

Output

{
  "request_id": "flux-2-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-max-edit_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 - FLUX 2 Max Edit generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text instruction describing the desired edit. Must be detailed and specific for best results.
image_urls	Yes	string[]	—	—	Array of publicly accessible URLs of input images to edit. All images will be edited according to the same prompt.
image_size	No	string or object	"auto"	"auto", "square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9", or { "width": integer, "height": integer }	Preset aspect ratio or custom dimensions. Allowed presets: `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Custom object format: `{ "width": integer, "height": integer }`.
output_format	No	string	"jpeg"	"jpeg", "png"	Output image format. Allowed: `jpeg`, `png`.
safety_tolerance	No	string	"2"	"1", "2", "3", "4", "5"	Sensitivity level for NSFW filtering. Higher values are more permissive. Allowed: `1`, `2`, `3`, `4`, `5`.
enable_safety_checker	No	boolean	true	—	Enable or disable the NSFW content filter. Set to `false` to bypass filtering.
seed	No	integer	—	—	Optional random seed for reproducible results. Use the same seed with identical inputs to get identical outputs.
sync_mode	No	boolean	false	—	If `true`, returns the edited image(s) as base64-encoded data URIs inline in the response. If `false`, returns a `request_id` for async polling.

Content Item Types & Limits

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

Example Request

{
  "prompt": "Restyle the scene with warm golden-hour lighting and soft bokeh",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/recraft/a-breathtaking-mountain-landscape-at-golden-hour-w-1782135397335-0.webp"
  ],
  "image_size": "auto",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg",
  "sync_mode": false
}

Response

{
  "request_id": "flux-2-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-max-edit_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 'flux-2-max-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-max-edit",
  "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/flux-2-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-max-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-max-edit_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.

FLUX 2 Max API Pricing

Resolution	Price (USD)
First processed megapixel	$0.07
Each additional megapixel	$0.03
Input images count toward processed megapixels	$0.03

Flux Pro VTO API Documentation

https://gateway.pixazo.ai/flux-pro-v1-virtual-try-on/v1/flux-pro-v1-virtual-try-on-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

FLUX Pro V1 Virtual Try-On generate request

Request Code

POST https://gateway.pixazo.ai/flux-pro-v1-virtual-try-on/v1/flux-pro-v1-virtual-try-on-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "The garment is worn naturally, tucked in slightly at the waist",
  "human_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Person.jpeg",
  "garment_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Garment.jpeg",
  "num_inference_steps": 4,
  "output_format": "jpeg",
  "sync_mode": false
}

import requests

url = "https://gateway.pixazo.ai/flux-pro-v1-virtual-try-on/v1/flux-pro-v1-virtual-try-on-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "The garment is worn naturally, tucked in slightly at the waist",
    "human_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Person.jpeg",
    "garment_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Garment.jpeg",
    "num_inference_steps": 4,
    "output_format": "jpeg",
    "sync_mode": false
}

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

const url = "https://gateway.pixazo.ai/flux-pro-v1-virtual-try-on/v1/flux-pro-v1-virtual-try-on-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "The garment is worn naturally, tucked in slightly at the waist",
  "human_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Person.jpeg",
  "garment_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Garment.jpeg",
  "num_inference_steps": 4,
  "output_format": "jpeg",
  "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/flux-pro-v1-virtual-try-on/v1/flux-pro-v1-virtual-try-on-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "The garment is worn naturally, tucked in slightly at the waist",
    "human_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Person.jpeg",
    "garment_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Garment.jpeg",
    "num_inference_steps": 4,
    "output_format": "jpeg",
    "sync_mode": false
}'

Output

{
  "request_id": "flux-pro-v1-virtual-try-on_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-pro-v1-virtual-try-on_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 - FLUX Pro V1 Virtual Try-On generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Natural-language styling instructions describing how the garment should be worn (e.g., "tucked in slightly at the waist", "loose drape", "form-fitting").
human_image_url	Yes	string	—	—	URL of the front-facing person image. Maximum 2 megapixels; recommended under 1 megapixel. Must be publicly accessible.
garment_image_url	Yes	string	—	—	URL of the garment reference image. Maximum 1 megapixel; recommended around 0.5 megapixel. Must be publicly accessible.
num_inference_steps	No	integer	4	1, 2, 3, 4	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
output_format	No	string	"jpeg"	"jpeg", "png"	Output image format.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_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
human_image_url	1	JPG, PNG, WEBP	Person photo (≤ 2 MP).
garment_image_url	1	JPG, PNG, WEBP	Garment image (≤ 1 MP).

Example Request

{
  "prompt": "The garment is worn naturally, tucked in slightly at the waist",
  "human_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png",
  "garment_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/nano-banana_019f1842-c359-7535-a90c-a798a408fbfa3/output.jpg",
  "num_inference_steps": 4,
  "output_format": "jpeg",
  "sync_mode": false
}

Response

{
  "request_id": "flux-pro-v1-virtual-try-on_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-pro-v1-virtual-try-on_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 'flux-pro-v1-virtual-try-on' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-pro-v1-virtual-try-on_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-pro-v1-virtual-try-on",
  "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/flux-pro-v1-virtual-try-on_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-pro-v1-virtual-try-on_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-pro-v1-virtual-try-on",
  "error": null,
  "output": { "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-pro-v1-virtual-try-on_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.

Flux Pro VTO API Pricing

Your request will cost $0.0475 per generation.

Flux 2 Pro API Documentation

https://gateway.pixazo.ai/flux-2-pro-image-to-image-866/v1/flux-2-pro-image-to-image-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

Generate Request - flux 2 pro Image to Image API

Request Code

POST https://gateway.pixazo.ai/flux-2-pro-image-to-image-866/v1/flux-2-pro-image-to-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Place realistic flames emerging from the top of the coffee cup, dancing above the rim",
  "image_size": "auto",
  "safety_tolerance": "2",
  "enable_safety_checker": false,
  "output_format": "jpeg",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg"
  ]
}

import requests

url = "https://gateway.pixazo.ai/flux-2-pro-image-to-image-866/v1/flux-2-pro-image-to-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Place realistic flames emerging from the top of the coffee cup, dancing above the rim",
    "image_size": "auto",
    "safety_tolerance": "2",
    "enable_safety_checker": false,
    "output_format": "jpeg",
    "image_urls": [
        "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg"
    ]
}

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

const url = 'https://gateway.pixazo.ai/flux-2-pro-image-to-image-866/v1/flux-2-pro-image-to-image-request';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'Place realistic flames emerging from the top of the coffee cup, dancing above the rim',
  image_size: 'auto',
  safety_tolerance: '2',
  enable_safety_checker: false,
  output_format: 'jpeg',
  image_urls: [
    'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg'
  ]
};

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/flux-2-pro-image-to-image-866/v1/flux-2-pro-image-to-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Place realistic flames emerging from the top of the coffee cup, dancing above the rim",
    "image_size": "auto",
    "safety_tolerance": "2",
    "enable_safety_checker": false,
    "output_format": "jpeg",
    "image_urls": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg"
    ]
  }'

Output

{
  "request_id": "flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-image-to-image-866_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": "flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-image-to-image-866",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-image-to-image-866_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": "flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-image-to-image-866",
  "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 - Generate Request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	A descriptive text prompt guiding the image transformation (e.g., style, lighting, elements to add or remove)
image_urls	Yes	array[string]	—	—	List of publicly accessible URLs of the input images to edit. All supplied images are passed to the model as editing references.
image_size	No	string or object	auto	auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9; or a custom size object	The size of the generated image. With auto, the size is determined by the model from the input images. A custom object such as {"width": 1024, "height": 768} is also accepted (width and height between 1 and 14142 pixels).
seed	No	integer	—	—	The seed to use for the generation. Reusing the same seed with the same prompt and images reproduces the same result; omit for a random result.
safety_tolerance	No	string	2	1, 2, 3, 4, 5	The safety tolerance level for the generated image. 1 is the most strict and 5 is the most permissive.
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	jpeg	jpeg, png	Format of the generated image output. Supported values: jpeg, png.

Content Item Types & Limits

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

Example Request

{
  "prompt": "Place realistic sparks and glowing embers erupting between the two fighting robots, emphasizing the impact of their clash.",
  "image_size": "auto",
  "safety_tolerance": "2",
  "enable_safety_checker": false,
  "output_format": "jpeg",
  "image_urls": [
    "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg"
  ]
}

Response

{
  "request_id": "flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-image-to-image-866_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 'flux-2-pro-image-to-image-866' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-image-to-image-866",
  "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/flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-pro-image-to-image-866_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-image-to-image-866",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-image-to-image-866_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.

Flux 2 Pro API Pricing

Your request will cost $0.03 per image.

Flux 2 Pro API Documentation

https://gateway.pixazo.ai/flux-2-pro-image-to-image-trainer-831/v1/flux-2-pro-image-to-image-trainer-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

Generate Request - flux 2 pro Image to Image Trainer API

Request Code

POST https://gateway.pixazo.ai/flux-2-pro-image-to-image-trainer-831/v1/flux-2-pro-image-to-image-trainer-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-i2i-demo-dataset.zip",
  "steps": 1200,
  "learning_rate": 0.00007
}

import requests

url = "https://gateway.pixazo.ai/flux-2-pro-image-to-image-trainer-831/v1/flux-2-pro-image-to-image-trainer-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-i2i-demo-dataset.zip",
    "steps": 1200,
    "learning_rate": 0.00007
}

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

const url = "https://gateway.pixazo.ai/flux-2-pro-image-to-image-trainer-831/v1/flux-2-pro-image-to-image-trainer-request";

const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};

const data = {
  image_data_url: "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-i2i-demo-dataset.zip",
  steps: 1200,
  learning_rate: 0.00007
};

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/flux-2-pro-image-to-image-trainer-831/v1/flux-2-pro-image-to-image-trainer-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-i2i-demo-dataset.zip",
    "steps": 1200,
    "learning_rate": 0.00007
  }'

Output

{
  "request_id": "flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-image-to-image-trainer-831_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": "flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-image-to-image-trainer-831",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-image-to-image-trainer-831_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": "flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-image-to-image-trainer-831",
  "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 - Generate Request

Parameter	Required	Type	Default	Allowed values / range	Description
image_data_url	Yes	string	—	—	URL to a zip archive of before/after training image pairs named ROOT_start.EXT and ROOT_end.EXT (e.g. photo_start.jpg / photo_end.jpg). Each pair may also include up to four reference images (ROOT_start2.EXT, ROOT_start3.EXT, ...) and an optional ROOT.txt file with the edit instruction; pairs without a text file use default_caption.
steps	No	integer	1000	100–10000	Total number of training steps. Higher values yield more refined models but require longer processing time.
learning_rate	No	number	0.00005	—	Learning rate applied to trainable parameters. Lower values train more slowly but more reliably; higher values train faster but risk unstable results.
default_caption	No	string	—	—	Default caption (edit instruction) to use for image pairs that have no ROOT.txt file in the archive. If omitted and captions are missing, training fails.

Example Request

{
  "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-i2i-demo-dataset.zip",
  "steps": 1200,
  "learning_rate": 0.00007
}

Response

{
  "request_id": "flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-image-to-image-trainer-831_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 'flux-2-pro-image-to-image-trainer-831' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-image-to-image-trainer-831",
  "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/flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-pro-image-to-image-trainer-831_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-image-to-image-trainer-831",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-image-to-image-trainer-831_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.

Flux 2 Pro API Pricing

Your request will cost $8.00 per LoRA training job.

Flux 2 Pro API Documentation

https://gateway.pixazo.ai/flux-2-pro-text-to-image-799/v1/flux-2-pro-text-to-image-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

Generate Request - flux 2 pro Text to Image API

Request Code

POST https://gateway.pixazo.ai/flux-2-pro-text-to-image-799/v1/flux-2-pro-text-to-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "An intense close-up of knight's visor reflecting battle, sword raised, flames in background, chiaroscuro helmet shadows, hyper-detailed armor, square medieval, cinematic lighting",
  "image_size": "landscape_4_3",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg"
}

import requests

url = "https://gateway.pixazo.ai/flux-2-pro-text-to-image-799/v1/flux-2-pro-text-to-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "An intense close-up of knight's visor reflecting battle, sword raised, flames in background, chiaroscuro helmet shadows, hyper-detailed armor, square medieval, cinematic lighting",
    "image_size": "landscape_4_3",
    "safety_tolerance": "2",
    "enable_safety_checker": True,
    "output_format": "jpeg"
}

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

const url = 'https://gateway.pixazo.ai/flux-2-pro-text-to-image-799/v1/flux-2-pro-text-to-image-request';

const data = {
  prompt: "An intense close-up of knight's visor reflecting battle, sword raised, flames in background, chiaroscuro helmet shadows, hyper-detailed armor, square medieval, cinematic lighting",
  image_size: "landscape_4_3",
  safety_tolerance: "2",
  enable_safety_checker: true,
  output_format: "jpeg"
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  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/flux-2-pro-text-to-image-799/v1/flux-2-pro-text-to-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "An intense close-up of knight\'s visor reflecting battle, sword raised, flames in background, chiaroscuro helmet shadows, hyper-detailed armor, square medieval, cinematic lighting",
    "image_size": "landscape_4_3",
    "safety_tolerance": "2",
    "enable_safety_checker": true,
    "output_format": "jpeg"
  }'

Output

{
  "request_id": "flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-text-to-image-799_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": "flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-text-to-image-799",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-text-to-image-799_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": "flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-text-to-image-799",
  "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 - Generate Request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	A detailed text description of the desired image. Be specific about subject, style, lighting, composition, and mood.
image_size	No	string or object	landscape_4_3	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9; or a custom size object	The size of the generated image. Use a preset value or pass a custom object such as {"width": 1024, "height": 768} (width and height between 1 and 14142 pixels).
seed	No	integer	—	—	The seed to use for the generation. Reusing the same seed with the same prompt reproduces the same image; omit for a random result.
safety_tolerance	No	string	2	1, 2, 3, 4, 5	The safety tolerance level for the generated image. 1 is the most strict and 5 is the most permissive.
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	jpeg	jpeg, png	The file format of the generated image. Supported values: jpeg, png.

Example Request

{
  "prompt": "An intense close-up of knight's visor reflecting battle, sword raised, flames in background, chiaroscuro helmet shadows, hyper-detailed armor, square medieval, cinematic lighting",
  "image_size": "landscape_4_3",
  "safety_tolerance": "2",
  "enable_safety_checker": true,
  "output_format": "jpeg"
}

Response

{
  "request_id": "flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-text-to-image-799_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 'flux-2-pro-text-to-image-799' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-text-to-image-799",
  "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/flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-pro-text-to-image-799_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-text-to-image-799",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-text-to-image-799_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.

Flux 2 Pro API Pricing

Your request will cost $0.03 per image.

Flux 2 Pro API Documentation

https://gateway.pixazo.ai/flux-2-pro-text-to-image-trainer-712/v1/flux-2-pro-text-to-image-trainer-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

Generate Request - flux 2 pro Text to Image Trainer API

Request Code

POST https://gateway.pixazo.ai/flux-2-pro-text-to-image-trainer-712/v1/flux-2-pro-text-to-image-trainer-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
  "steps": 1500,
  "learning_rate": 0.00003
}

import requests

url = "https://gateway.pixazo.ai/flux-2-pro-text-to-image-trainer-712/v1/flux-2-pro-text-to-image-trainer-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
    "steps": 1500,
    "learning_rate": 0.00003
}

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

const url = 'https://gateway.pixazo.ai/flux-2-pro-text-to-image-trainer-712/v1/flux-2-pro-text-to-image-trainer-request';

const data = {
  image_data_url: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip',
  steps: 1500,
  learning_rate: 0.00003
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  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/flux-2-pro-text-to-image-trainer-712/v1/flux-2-pro-text-to-image-trainer-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
    "steps": 1500,
    "learning_rate": 0.00003
  }'

Output

{
  "request_id": "flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-text-to-image-trainer-712_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": "flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-text-to-image-trainer-712",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-text-to-image-trainer-712_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": "flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-text-to-image-trainer-712",
  "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 - Generate Request

Parameter	Required	Type	Default	Allowed values / range	Description
image_data_url	Yes	string	—	—	URL to a zip archive of training images in a consistent style. Use at least 10 images; more is better. Captions are effectively required: include a caption .txt per image (named after the image, e.g. photo.txt for photo.jpg), or set default_caption below for any image without one. Because Flux has no separate trigger-word field, put your unique trigger word (for example sks_person) inside these captions — that is the only place it can live, and the trained LoRA needs it to activate the subject.
steps	No	integer	1000	100–10000	Total number of training steps. Higher values improve model quality but increase training time.
learning_rate	No	number	0.00005	—	Learning rate applied to trainable parameters. Lower values train more slowly but more reliably; higher values train faster but risk unstable results.
default_caption	No	string	—	—	Default caption applied to any training image that has no caption .txt in the archive. Captions are mandatory: if an image has neither a per-image .txt caption nor a default_caption, training fails. This caption must contain your trigger word (for example sks_person), since Flux has no trigger field.

Example Request

{
  "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
  "steps": 1500,
  "learning_rate": 0.00003
}

Response

{
  "request_id": "flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-pro-text-to-image-trainer-712_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 'flux-2-pro-text-to-image-trainer-712' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-pro-text-to-image-trainer-712",
  "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/flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-pro-text-to-image-trainer-712_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-pro-text-to-image-trainer-712",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-pro-text-to-image-trainer-712_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.

Flux 2 Pro API Pricing

Your request will cost $8.00 per LoRA training job.

Flux 2 Pro API Documentation

https://gateway.pixazo.ai/flux-2-lora/v1

Authentication

All requests require an API key passed via header.

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

Flux 2 Lora generate request

Request Code

POST https://gateway.pixazo.ai/flux-2-lora/v1/flux-2-lora-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "sks_robot a red toy robot with a yellow antenna standing in a futuristic city",
  "loras": [
    {
      "path": "https://your-bucket.example.com/your-trained-lora.safetensors",
      "scale": 1
    }
  ],
  "image_size": "landscape_4_3",
  "num_images": 1,
  "output_format": "png",
  "acceleration": "regular"
}

import requests

url = "https://gateway.pixazo.ai/flux-2-lora/v1/flux-2-lora-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "sks_robot a red toy robot with a yellow antenna standing in a futuristic city",
    "loras": [
        {
            "path": "https://your-bucket.example.com/your-trained-lora.safetensors",
            "scale": 1
        }
    ],
    "image_size": "landscape_4_3",
    "num_images": 1,
    "output_format": "png",
    "acceleration": "regular"
}

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

const url = "https://gateway.pixazo.ai/flux-2-lora/v1/flux-2-lora-request";
const headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
    "prompt": "sks_robot a red toy robot with a yellow antenna standing in a futuristic city",
    "loras": [
        {
            "path": "https://your-bucket.example.com/your-trained-lora.safetensors",
            "scale": 1
        }
    ],
    "image_size": "landscape_4_3",
    "num_images": 1,
    "output_format": "png",
    "acceleration": "regular"
};

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/flux-2-lora/v1/flux-2-lora-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "sks_robot a red toy robot with a yellow antenna standing in a futuristic city",
    "loras": [
        {
            "path": "https://your-bucket.example.com/your-trained-lora.safetensors",
            "scale": 1
        }
    ],
    "image_size": "landscape_4_3",
    "num_images": 1,
    "output_format": "png",
    "acceleration": "regular"
}'

Output

{
  "request_id": "flux-2-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-lora_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

Billed $0.05 per image. Apply your trained FLUX.2 LoRA by passing its URL in loras[].path (max 3 LoRAs).

Request Parameters - Flux 2 Lora generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description for image generation. Be specific to guide the model’s output.
loras	No	array	[]	—	Array of LoRA weight configurations. Each object must contain `path` and `scale`. Up to 3 LoRAs allowed. Tip: for a trained person or subject LoRA, set scale to about 1.5 — at 1.0 the likeness washes out and the result looks broken. The trigger word is not required at inference; the subject renders from the LoRA alone.
loras[].path	Yes (if loras is provided)	string	—	—	HTTPS URL to a `.safetensors` LoRA weight file. Must be publicly accessible.
loras[].scale	Yes (if loras is provided)	number	1.0	0.0 to 2.0	Strength of the LoRA effect. Range: 0.0 to 2.0. Values above 1.0 amplify the LoRA influence.
image_size	No	string	landscape_4_3	portrait_3_4, landscape_4_3, square_1_1, landscape_16_9, portrait_9_16	Output image dimensions.
num_images	No	integer	1	1–4	Number of images to generate.
output_format	No	string	png	png, jpeg, webp	Output image format.
acceleration	No	string	regular	regular, fast, ultra_fast	Inference optimization mode. `ultra_fast` reduces quality for speed.
seed	No	integer	—	0–4294967295	Optional random seed for reproducible results.

Example Request

{
  "prompt": "sks_robot a red toy robot with a yellow antenna standing in a futuristic city",
  "loras": [
    {
      "path": "https://your-bucket.example.com/your-trained-lora.safetensors",
      "scale": 1
    }
  ],
  "image_size": "landscape_4_3",
  "num_images": 1,
  "output_format": "png",
  "acceleration": "regular"
}

Response

{
  "request_id": "flux-2-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-2-lora_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 'flux-2-lora' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-2-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-2-lora",
  "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/flux-2-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-2-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-2-lora",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-2-lora_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.

Flux 2 Pro API Pricing

Your request will cost $0.021 per image.

Flux Kontext API Documentation

https://gateway.pixazo.ai/flux-kontext-restore-image/v1/flux-kontext-restore-image/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 Restore Request - Flux Kontext Restore Image

Request Code

POST https://gateway.pixazo.ai/flux-kontext-restore-image/v1/flux-kontext-restore-image/generate HTTP/1.1
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "input_image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png"
}

import requests

url = "https://gateway.pixazo.ai/flux-kontext-restore-image/v1/flux-kontext-restore-image/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "input_image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png"
}

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

const url = 'https://gateway.pixazo.ai/flux-kontext-restore-image/v1/flux-kontext-restore-image/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  input_image: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.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/flux-kontext-restore-image/v1/flux-kontext-restore-image/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "input_image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/input_model.png"
  }'

Output

{
  "request_id": "flux-kontext-restore-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-kontext-restore-image_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": "flux-kontext-restore-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-kontext-restore-image",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-kontext-restore-image_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": "flux-kontext-restore-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-kontext-restore-image",
  "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 - Flux Kontext Restore Image

Parameter	Required	Type	Default	Allowed values / range	Description
input_image	Yes	string (URL)	—	—	The image to restore. Supported formats: `jpeg`, `png`, `gif`, `webp`.
seed	No	integer	random	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
output_format	No	string	"png"	jpg , png	Output image format. Allowed values: `jpg`, `png`.
safety_tolerance	No	integer	2	0 – 2	Content safety threshold. Allowed values: `0`–`2`. `0` is the strictest, `2` the most permissive (max allowed).

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, GIF, WEBP · < 20 MB	Image to restore.

Example Request

{
  "input_image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/gpt-image-1-5-api-923_019ecf03-5887-7781-659f-bc0d541e2b98a/output.png",
  "seed": 42,
  "output_format": "png",
  "safety_tolerance": 2
}

Response

{
  "request_id": "flux-kontext-restore-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-kontext-restore-image_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 'flux-kontext-restore-image' not found or is disabled"
}

Model Validation Errors (400)

// Examples
{ "error": "input_image is required and must be a string URL" }
{ "error": "input_image must be a valid URL" }
{ "error": "output_format must be one of: jpg, png" }
{ "error": "safety_tolerance must be an integer in [0, 2]" }
{ "error": "seed must be a non-negative integer" }
{ "error": "Invalid webhook URL" }

Error via Status/Webhook

{
  "request_id": "flux-kontext-restore-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-kontext-restore-image",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

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

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/flux-kontext-restore-image_019d42ce-ae71-7999-24c9-5d76447ecafb4"

Response (Completed)

{
  "request_id": "flux-kontext-restore-image_019d42ce-ae71-7999-24c9-5d76447ecafb4",
  "status": "COMPLETED",
  "model_id": "flux-kontext-restore-image",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-kontext-restore-image_019d42ce-ae71-7999-24c9-5d76447ecafb4/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-01T14:30:28.735Z",
  "updated_at": "2026-05-01T14:31:18.000Z",
  "completed_at": "2026-05-01T14:31:18.000Z"
}

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 (image/png or image/jpeg)
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.

Flux Kontext API Pricing

Your request will cost $0.04 per image.

Flux 2 Klein API Documentation

https://gateway.pixazo.ai/flux-2-klein-4b/v1/generateImage

Text to Image - Flux 2 klein 4b

Request Code

POST https://gateway.pixazo.ai/flux-2-klein-4b/v1/generateImage
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A sunset with a dog playing on the beach, golden light reflecting on the water, photorealistic, highly detailed",
  "steps": 25,
  "width": 1024,
  "height": 1024
}

import requests

url = "https://gateway.pixazo.ai/flux-2-klein-4b/v1/generateImage"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A sunset with a dog playing on the beach, golden light reflecting on the water, photorealistic, highly detailed",
    "steps": 25,
    "width": 1024,
    "height": 1024
}

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

const url = 'https://gateway.pixazo.ai/flux-2-klein-4b/v1/generateImage';

const data = {
  prompt: 'A sunset with a dog playing on the beach, golden light reflecting on the water, photorealistic, highly detailed',
  steps: 25,
  width: 1024,
  height: 1024
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/flux-2-klein-4b/v1/generateImage" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
    "prompt": "A sunset with a dog playing on the beach, golden light reflecting on the water, photorealistic, highly detailed",
    "steps": 25,
    "width": 1024,
    "height": 1024
}'

Output

{
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-2-klein-4b/1768578707564-851083.png"
}

Try Now

Request Parameters - Text to Image

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	The text prompt describing the image to generate. Must be a non-empty string.
steps	No	integer	25	No effect (fixed 4-step inference)	Accepted for compatibility but does not change the output: FLUX.2 [klein] is a distilled model that always runs a fixed 4-step inference process, so this value does not alter quality or speed.
width	No	integer	1024	256-1920	The desired width of the generated image, specified in pixels. Default: 1024. Range: 256-1920.
height	No	integer	1024	256-1920	The desired height of the generated image, specified in pixels. Default: 1024. Range: 256-1920.

Example Request

{
  "prompt": "A sunset with a dog playing on the beach, golden light reflecting on the water, photorealistic, highly detailed",
  "steps": 25,
  "width": 1024,
  "height": 1024
}

Response

{
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-2-klein-4b/1768578707564-851083.png"
}

Request Headers

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

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

Flux 2 Klein API Pricing

Resolution	Price (USD)
512x512	$0.0003
1024×1024	$0.0007
1448×1448	$0.0014
2048×2048	$0.0028

Flux 2 Dev API Documentation

https://gateway.pixazo.ai/flux-2-dev/v1/generateT2I

Authentication

All requests require an API key passed via header.

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

generateT2I - Flux 2 dev API

Request Code

POST https://gateway.pixazo.ai/flux-2-dev/v1/generateT2I
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "a sunset at the alps"
}

import requests

url = "https://gateway.pixazo.ai/flux-2-dev/v1/generateT2I"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "a sunset at the alps"
}

# Generation takes ~60-90 seconds; set an appropriate timeout.
response = requests.post(url, json=data, headers=headers, timeout=180)
print(response.json())

const url = 'https://gateway.pixazo.ai/flux-2-dev/v1/generateT2I';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
  prompt: 'a sunset at the alps'
};

// Generation takes ~60-90 seconds; the request stays open until the image is ready.
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/flux-2-dev/v1/generateT2I" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --max-time 180 \
  --data-raw '{
    "prompt": "a sunset at the alps"
  }'

Output

{
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-2-dev-cf/1762439647765-844809.png"
}

Try Now

Synchronous Response

This endpoint is synchronous. The HTTP request remains open until image generation and R2 upload complete, then returns the final image URL in a single response. There is no polling step and no request_id to track. Typical end-to-end time is 60-90 seconds; configure your HTTP client timeout to at least 180 seconds.

Request Parameters - generateT2I

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description of the image to generate. Supports multi-language input and structured JSON prompting (pass a JSON object as a string describing scene, subjects, style, lighting, etc.) for more granular control
steps	No	integer	25	—	Number of inference steps. Higher values may improve quality but increase generation time
width	No	integer	1024	256-1920	Width of the generated image in pixels
height	No	integer	1024	256-1920	Height of the generated image in pixels

Example Request

{
  "prompt": "a sunset at the alps"
}

Response

{
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-2-dev-cf/1762439647765-844809.png"
}

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
200	Success — response body contains the generated image URL
400	Bad Request — invalid or missing prompt
401	Unauthorized — invalid subscription key
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Response Fields

Field	Type	Description
output	string	Public URL of the generated PNG image, hosted on Pixazo's R2 CDN

Flux 2 Dev API Pricing

Your request will cost $0.012 per image.

Flux Pro 1.1 API Documentation

https://gateway.pixazo.ai/pro1.1/v1/pro1.1ultra/generateRequest

Authentication

All requests require an API key passed via header.

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

Pro1.1 Ultra generateRequest - Flux pro 1.1

Request Code

POST https://gateway.pixazo.ai/pro1.1/v1/pro1.1ultra/generateRequest
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A futuristic cityscape at sunset",
  "seed": 43,
  "output_format": "jpeg",
  "aspect_ratio": "16:9"
}

import requests

url = "https://gateway.pixazo.ai/pro1.1/v1/pro1.1ultra/generateRequest"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A futuristic cityscape at sunset",
    "seed": 43,
    "output_format": "jpeg",
    "aspect_ratio": "16:9"
}

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

const url = 'https://gateway.pixazo.ai/pro1.1/v1/pro1.1ultra/generateRequest';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'A futuristic cityscape at sunset',
  seed: 43,
  output_format: 'jpeg',
  aspect_ratio: '16:9'
};

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 -v -X POST "https://gateway.pixazo.ai/pro1.1/v1/pro1.1ultra/generateRequest" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
  "prompt": "A futuristic cityscape at sunset",
  "seed": 43,
  "output_format": "jpeg",
  "aspect_ratio": "16:9"
}'

Output

{
  "request_id": "flux-pro-1-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-pro-1-1_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": "flux-pro-1-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-pro-1-1",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-pro-1-1_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": "flux-pro-1-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-pro-1-1",
  "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 - Pro1.1 Ultra generateRequest

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	The instruction or description for the image to be generated. FLUX1.1 [pro] ultra delivers professional-grade image quality with enhanced photo realism and up to 2K resolution
image_url	Optional	string	—	—	URL of an image to use as a visual reference (image prompt). The model blends this image with your text prompt; control its influence with image_prompt_strength.
image_prompt_strength	Optional	number	0.1	0 to 1	How strongly the reference image (image_url) influences the result. 0 ignores the image; higher values follow it more closely.
seed	Optional	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	Optional	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.
num_images	Optional	integer	1	1 to 4	The number of images to generate per request.
enable_safety_checker	Optional	boolean	—	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	Optional	string	jpeg	jpeg, png	The format of the generated image.
safety_tolerance	Optional	string	2	1, 2, 3, 4, 5, 6	The safety tolerance level for generated images. 1 is the most strict and 6 is the most permissive.
enhance_prompt	Optional	boolean	false	true, false	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
aspect_ratio	Optional	string	16:9	21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21	The aspect ratio of the generated image. Also accepts a custom width:height ratio string.
raw	Optional	boolean	false	true, false	Generate less processed, more natural-looking images

Example Request

{
  "prompt": "A futuristic cityscape at sunset",
  "seed": 43,
  "output_format": "jpeg",
  "aspect_ratio": "16:9"
}

Response

{
  "request_id": "flux-pro-1-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-pro-1-1_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 'flux-pro-1-1' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-pro-1-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-pro-1-1",
  "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/flux-pro-1-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

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

Flux Pro 1.1 API Pricing

Your request will cost $0.06 per image.

Flux 1 Schnell API Documentation

https://gateway.pixazo.ai/flux-1-schnell/v1/getData

Get Image - flux-1 Schnell API

Request Code

POST https://gateway.pixazo.ai/flux-1-schnell/v1/getData
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Picture a sleek, futuristic car racing through a neon-lit cityscape, its engine humming efficiently as it blurs past digital billboards. The driver skillfully navigates the glowing streets, aiming for victory in this high-tech, adrenaline-fueled race of tomorrow.",
  "num_steps": 4,
  "seed": 15,
  "height": 512,
  "width": 512
}

import requests

url = "https://gateway.pixazo.ai/flux-1-schnell/v1/getData"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Picture a sleek, futuristic car racing through a neon-lit cityscape, its engine humming efficiently as it blurs past digital billboards. The driver skillfully navigates the glowing streets, aiming for victory in this high-tech, adrenaline-fueled race of tomorrow.",
    "num_steps": 4,
    "seed": 15,
    "height": 512,
    "width": 512
}

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

const url = 'https://gateway.pixazo.ai/flux-1-schnell/v1/getData';

const data = {
  prompt: "Picture a sleek, futuristic car racing through a neon-lit cityscape, its engine humming efficiently as it blurs past digital billboards. The driver skillfully navigates the glowing streets, aiming for victory in this high-tech, adrenaline-fueled race of tomorrow.",
  num_steps: 4,
  seed: 15,
  height: 512,
  width: 512
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/flux-1-schnell/v1/getData" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
    "prompt": "Picture a sleek, futuristic car racing through a neon-lit cityscape, its engine humming efficiently as it blurs past digital billboards. The driver skillfully navigates the glowing streets, aiming for victory in this high-tech, adrenaline-fueled race of tomorrow.",
    "num_steps": 4,
    "seed": 15,
    "height": 512,
    "width": 512
}'

Output

{
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-schnell-cf/prompt-1768311018384-879091.png"
}

Try Now

Request Parameters - Get Image

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–2048 characters	A text description of the image you want to generate. The prompt is lightly sanitized to avoid content-moderation false positives.
num_steps	No	integer	1	1–8	Number of diffusion steps; higher values can improve quality but take longer. The provider supports a maximum of 8 steps.
seed	No	integer	random	—	Random seed for reproducible generation. Reuse the same seed with identical settings to reproduce the same result; omit it to get a different output each time.
height	No	integer	1024	—	The desired height of the generated image, in pixels.
width	No	integer	1024	—	The desired width of the generated image, in pixels.

Example Request

{
  "prompt": "Picture a sleek, futuristic car racing through a neon-lit cityscape, its engine humming efficiently as it blurs past digital billboards. The driver skillfully navigates the glowing streets, aiming for victory in this high-tech, adrenaline-fueled race of tomorrow.",
  "num_steps": 4,
  "seed": 15,
  "height": 512,
  "width": 512
}

Response

{
  "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-schnell-cf/prompt-1768311018384-879091.png"
}

Request Headers

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

Response Handling

Common status codes for Get Image.

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

Flux 1 Schnell API Pricing

Your request is Free

Free during preview — fair-use rate limit of 60 requests/minute applies. See terms.

Flux 1 Schnell API Documentation

https://gateway.pixazo.ai/flux-1-schnell/v1/getDataBatch

Get Image Batch - flux-1 Schnell API

Request Code

POST https://gateway.pixazo.ai/flux-1-schnell/v1/getDataBatch
Content-Type: application/json
X-Secret-Key: YOUR_SECRET_KEY
Cache-Control: no-cache

{
  "prompt": "Picture a handsome man dancing",
  "num_steps": 4,
  "seed": 15,
  "height": 512,
  "width": 512,
  "webhook_url": "https://your-domain.com/webhook"
}

import requests

url = "https://gateway.pixazo.ai/flux-1-schnell/v1/getDataBatch"
headers = {
    "Content-Type": "application/json",
    "X-Secret-Key": "YOUR_SECRET_KEY",
    "Cache-Control": "no-cache"
}
data = {
    "prompt": "Picture a handsome man dancing",
    "num_steps": 4,
    "seed": 15,
    "height": 512,
    "width": 512,
    "webhook_url": "https://your-domain.com/webhook"
}

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

const url = 'https://gateway.pixazo.ai/flux-1-schnell/v1/getDataBatch';
const headers = {
  'Content-Type': 'application/json',
  'X-Secret-Key': 'YOUR_SECRET_KEY',
  'Cache-Control': 'no-cache'
};

const data = {
  prompt: 'Picture a handsome man dancing',
  num_steps: 4,
  seed: 15,
  height: 512,
  width: 512,
  webhook_url: 'https://your-domain.com/webhook'
};

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 -v -X POST "https://gateway.pixazo.ai/flux-1-schnell/v1/getDataBatch" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "X-Secret-Key: YOUR_SECRET_KEY" \
  --data-raw '{
    "prompt": "Picture a handsome man dancing",
    "num_steps": 4,
    "seed": 15,
    "height": 512,
    "width": 512,
    "webhook_url": "https://your-domain.com/webhook"
  }'

Output

{
  "requestId": "18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45",
  "status": "queued",
  "message": "Request queued. Result will be sent to the provided webhook URL.",
  "pollingEndpoint": "/checkStatus",
  "pollingInstructions": "POST to /checkStatus with {...}"
}

Try Now

Request Parameters - Get Image Batch

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–2048 characters	A text description of the image you want to generate. The prompt is lightly sanitized to avoid content-moderation false positives.
num_steps	No	integer	1	1–8	Number of diffusion steps; higher values can improve quality but take longer. The provider supports a maximum of 8 steps.
seed	No	integer	random	—	Random seed for reproducible generation. Reuse the same seed with identical settings to reproduce the same result; omit it to get a different output each time.
width	No	integer	1024	—	The desired width of the generated image, in pixels.
height	No	integer	1024	—	The desired height of the generated image, in pixels.
webhook_url	No	string	—	—	URL to receive the result via HTTP POST when processing completes. If provided, the API returns immediately with status 202. If omitted, the API waits internally for up to ~100 seconds and returns the result, or a 504 timeout with instructions to poll /checkStatus.

Example Request

{
  "prompt": "Picture a handsome man dancing",
  "num_steps": 4,
  "seed": 15,
  "height": 512,
  "width": 512,
  "webhook_url": "https://your-domain.com/webhook"
}

Response

{
  "requestId": "18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45",
  "status": "queued",
  "message": "Request queued. Result will be sent to the provided webhook URL.",
  "pollingEndpoint": "/checkStatus",
  "pollingInstructions": "POST to /checkStatus with {\"requestId\": \"18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45\"}"
}

Request Headers

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

Response Handling

Common status codes for Get Image Batch.

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

Checking Job Status

After submitting your request, use this endpoint to check status and retrieve results.

Endpoint

POST https://gateway.pixazo.ai/flux-1-schnell/v1/checkStatus

Request Body

{ "requestId": "18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45" }

Code Examples

POST https://gateway.pixazo.ai/flux-1-schnell/v1/checkStatus
Content-Type: application/json
X-Secret-Key: YOUR_SECRET_KEY
Cache-Control: no-cache

{
  "requestId": "18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45"
}

import requests

url = "https://gateway.pixazo.ai/flux-1-schnell/v1/checkStatus"
headers = {
    "Content-Type": "application/json",
    "X-Secret-Key": "YOUR_SECRET_KEY",
    "Cache-Control": "no-cache"
}
data = {
    "requestId": "18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45"
}

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

const url = 'https://gateway.pixazo.ai/flux-1-schnell/v1/checkStatus';
const headers = {
  'Content-Type': 'application/json',
  'X-Secret-Key': 'YOUR_SECRET_KEY',
  'Cache-Control': 'no-cache'
};

const data = {
  requestId: '18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45'
};

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 -v -X POST "https://gateway.pixazo.ai/flux-1-schnell/v1/checkStatus" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "X-Secret-Key: YOUR_SECRET_KEY" \
  --data-raw '{
    "requestId": "18a36237-f8b2-4c8d-9a3b-d5e8a9f12c45"
  }'

Response Examples

{ "status": "completed", "output": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/flux-schnell-cf/prompt-1768311018384-879091.png", "completedAt": 1768311019767 }

Flux 1 Schnell API Pricing

Your request is Free

Free during preview — fair-use rate limit of 60 requests/minute applies. See terms.

Flux Pro API Documentation

https://gateway.pixazo.ai/flux-pro/v1/pro/textToImage

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 - Flux Pro API

Request Code

POST https://gateway.pixazo.ai/flux-pro/v1/pro/textToImage
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A futuristic cityscape at sunset with flying cars",
  "image_size": "landscape_4_3"
}

import requests

url = "https://gateway.pixazo.ai/flux-pro/v1/pro/textToImage"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A futuristic cityscape at sunset with flying cars",
    "image_size": "landscape_4_3"
}

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

const url = 'https://gateway.pixazo.ai/flux-pro/v1/pro/textToImage';

const data = {
  prompt: 'A futuristic cityscape at sunset with flying cars',
  image_size: 'landscape_4_3'
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/flux-pro/v1/pro/textToImage" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
  "prompt": "A futuristic cityscape at sunset with flying cars",
  "image_size": "landscape_4_3"
}'

Output

{
  "request_id": "flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-pro_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": "flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-pro",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-pro_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": "flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-pro",
  "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	—	—	The instruction or description for the image to be generated
image_size	Optional	string \| object	landscape_4_3	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9	The aspect-ratio preset for the generated image. Also accepts a custom size object with width and height in pixels (max 14142 each), e.g. {"width": 1280, "height": 720}
num_inference_steps	Optional	integer	28	1-50	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	Optional	float	3.5	1-20	CFG scale: controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
seed	Optional	integer	—	—	Random seed that controls the generation. Reuse the same seed with the same prompt to reproduce the same image; omit for a random result.
num_images	Optional	integer	1	1-4	The number of images to generate
enable_safety_checker	Optional	boolean	—	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
safety_tolerance	Optional	string	2	1, 2, 3, 4, 5, 6	The safety tolerance level for the generated image. 1 is the most strict, 6 the most permissive.
output_format	Optional	string	jpeg	jpeg, png	The format of the generated image

Example Request

{
  "prompt": "A futuristic cityscape at sunset with flying cars",
  "image_size": "landscape_4_3"
}

Response

{
  "request_id": "flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-pro_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 'flux-pro' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-pro",
  "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/flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-pro",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-pro_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.

Flux Pro API Pricing

Your request will cost $0.04 per image.

Flux Dev API Documentation

https://gateway.pixazo.ai/flux-dev/v1/dev/imageToImage

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 - flux Dev API

Request Code

POST https://gateway.pixazo.ai/flux-dev/v1/dev/imageToImage
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png",
  "prompt": "Editorial rooftop shot, woman in peach tee and denim, modern urban backdrop, bold blue tones, polished aesthetic."
}

import requests

url = "https://gateway.pixazo.ai/flux-dev/v1/dev/imageToImage"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png",
    "prompt": "Editorial rooftop shot, woman in peach tee and denim, modern urban backdrop, bold blue tones, polished aesthetic."
}

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

const url = 'https://gateway.pixazo.ai/flux-dev/v1/dev/imageToImage';

const data = {
  image_url: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png',
  prompt: 'Editorial rooftop shot, woman in peach tee and denim, modern urban backdrop, bold blue tones, polished aesthetic.'
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/flux-dev/v1/dev/imageToImage" -H "Content-Type: application/json" -H "Cache-Control: no-cache" -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" --data-raw '{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png",
  "prompt": "Editorial rooftop shot, woman in peach tee and denim, modern urban backdrop, bold blue tones, polished aesthetic."
}'

Output

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-dev_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": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-dev_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": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-dev",
  "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 To Image

Parameter	Required	Type	Default	Allowed values / range	Description
image_url	Yes	string	—	—	The URL of the source image to transform
prompt	Yes	string	—	—	The instruction or description for how to transform the image
strength	Optional	float	0.95	0.01 to 1	How much the result may differ from the input. Higher values allow bigger changes from the source; lower values keep the output closer to the original. Higher strength values work best for this model.
num_inference_steps	Optional	integer	40	10 to 50	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	Optional	float	3.5	1 to 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	Optional	integer	1	1 to 4	The number of images to generate
enable_safety_checker	Optional	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	Optional	string	jpeg	jpeg, png	The format of the generated image.
acceleration	Optional	string	none	none, regular, high	The speed of generation. Higher acceleration produces images faster.
seed	Optional	integer	—	—	Random seed for reproducible results. The same seed with the same prompt and model version produces the same image every time.
sync_mode	Optional	boolean	false	true, false	If true, the image is returned inline as a data URI instead of a hosted URL, and the output is not stored in the request history.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Image to transform.

Example Request

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png",
  "prompt": "Editorial rooftop shot, woman in peach tee and denim, modern urban backdrop, bold blue tones, polished aesthetic."
}

Response

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-dev_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 'flux-dev' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-dev",
  "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/flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-dev_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.

Flux Dev API Pricing

Your request will cost $0.025 per image.

Flux Dev API Documentation

https://gateway.pixazo.ai/flux-dev/v1/dev/textToImage

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 - flux Dev API

Request Code

POST https://gateway.pixazo.ai/flux-dev/v1/dev/textToImage
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A futuristic city skyline at sunset with flying cars",
  "image_size": "landscape_4_3"
}

import requests

url = "https://gateway.pixazo.ai/flux-dev/v1/dev/textToImage"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A futuristic city skyline at sunset with flying cars",
    "image_size": "landscape_4_3"
}

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

const url = 'https://gateway.pixazo.ai/flux-dev/v1/dev/textToImage';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'A futuristic city skyline at sunset with flying cars',
  image_size: 'landscape_4_3'
};

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 -v -X POST "https://gateway.pixazo.ai/flux-dev/v1/dev/textToImage" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
  "prompt": "A futuristic city skyline at sunset with flying cars",
  "image_size": "landscape_4_3"
}'

Output

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-dev_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": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-dev_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": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-dev",
  "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	—	—	The instruction or description for the image to be generated
image_size	No	string \| object	landscape_4_3	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or a custom {"width", "height"} object (each side up to 14142 px)	The size / aspect ratio of the generated image. Pass one of the preset values, or a custom object with width and height.
num_inference_steps	No	integer	28	1 to 50	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	float	3.5	1 to 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 to 4	The number of images to generate
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	jpeg	jpeg, png	The format of the generated image.
acceleration	No	string	none	none, regular, high	The speed of generation. Higher acceleration produces images faster.
seed	No	integer	—	—	Random seed for reproducible results. The same seed with the same prompt and model version produces the same image every time.
sync_mode	No	boolean	false	true, false	If true, the image is returned inline as a data URI instead of a hosted URL, and the output is not stored in the request history.

Example Request

{
  "prompt": "A futuristic city skyline at sunset with flying cars",
  "image_size": "landscape_4_3"
}

Response

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-dev_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 'flux-dev' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-dev",
  "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/flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-dev_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.

Flux Dev API Pricing

Your request will cost $0.025 per image.

Flux Dev API Documentation

https://gateway.pixazo.ai/flux-lora-fast-training/v1/train

Authentication

All requests require an API key passed via header.

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

Flux LoRA Fast Training generate request

Request Code

POST https://gateway.pixazo.ai/flux-lora-fast-training/v1/train
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "images_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
  "trigger_word": "sks_subject",
  "steps": 1000
}

import requests

url = "https://gateway.pixazo.ai/flux-lora-fast-training/v1/train"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "images_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
    "trigger_word": "sks_subject",
    "steps": 1000
}

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

const url = "https://gateway.pixazo.ai/flux-lora-fast-training/v1/train";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "images_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
  "trigger_word": "sks_subject",
  "steps": 1000
};

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/flux-lora-fast-training/v1/train" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "images_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
    "trigger_word": "sks_subject",
    "steps": 1000
  }'

Output

{
  "request_id": "flux-lora-fast-training_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-lora-fast-training_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 - Flux LoRA Fast Training generate request

Parameter	Required	Type	Default	Allowed values / range	Description
`images_data_url`	Yes	string	—	publicly accessible URL to a .zip	URL to a zip archive of training images — at least 4, more is generally better. The archive may also contain .txt caption files, each sharing the filename of the image it describes.
`trigger_word`	No	string	—	—	Trigger word to use in the captions. If omitted, no trigger word is used. If no captions are supplied, the trigger word is used in place of captions.
`steps`	No	integer	—	100–5000	Number of training steps. Omit to use the provider default. Billing is $2 up to 1000 steps and scales linearly above that, at $0.002 per additional step.
`create_masks`	No	boolean	true	true, false	If true, segmentation masks are used to weight the training loss. For people a face mask is used where possible.
`is_style`	No	boolean	false	true, false	If true, trains a style LoRA. This deactivates segmentation and captioning and uses the trigger word instead — use the trigger word to name the style.
`is_input_format_already_preprocessed`	No	boolean	false	true, false	Set to true if the archive is already in the preprocessed format. When false (default) raw images are expected, each with a matching .txt caption file of the same name.
`data_archive_format`	No	string	—	—	Format of the archive. Inferred from the URL when not specified.

Example Request

{
  "images_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/trainers/flux-t2i-demo-dataset.zip",
  "trigger_word": "sks_subject",
  "steps": 1000
}

Response

{
  "request_id": "flux-lora-fast-training_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-lora-fast-training_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 'flux-lora-fast-training' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-lora-fast-training_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-lora-fast-training",
  "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/flux-lora-fast-training_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-lora-fast-training_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-lora-fast-training",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-lora-fast-training_019dxxxx/output.safetensors",
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-lora-fast-training_019dxxxx/config.json"
    ],
    "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	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.

Flux Dev API Pricing

Your request will cost $2.00 per LoRA training job.

Flux Fill Dev API Documentation

https://gateway.pixazo.ai/flux-fill-dev/v1/flux-fill/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 Generation Request - Flux Fill Dev API

Request Code

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

{
  "prompt": "a futuristic spaceship with neon lights",
  "image": "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog.png",
  "mask": "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog-mask.png"
}

import requests

API_KEY = "your-api-key-here"
BASE_URL = "https://gateway.pixazo.ai/flux-fill-dev/v1"

response = requests.post(
    f"{BASE_URL}/flux-fill/generate",
    headers={
        "Content-Type": "application/json",
        "Ocp-Apim-Subscription-Key": API_KEY
    },
    json={
        "prompt": "a futuristic spaceship with neon lights",
        "image": "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog.png",
        "mask": "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog-mask.png"
    }
)

result = response.json()
print(result)

async function generateImage() {
  const response = await fetch(
    'https://gateway.pixazo.ai/flux-fill-dev/v1/flux-fill/generate',
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'Ocp-Apim-Subscription-Key': process.env.API_KEY
      },
      body: JSON.stringify({
        prompt: 'a futuristic spaceship with neon lights',
        image: 'https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog.png',
        mask: 'https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog-mask.png'
      })
    }
  );

  const result = await response.json();
  console.log(result);
}

generateImage();

curl -v -X POST "https://gateway.pixazo.ai/flux-fill-dev/v1/flux-fill/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "a futuristic spaceship with neon lights",
    "image": "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog.png",
    "mask": "https://pub-1fb693cb11cc46b2b2f656f51e015a2c.r2.dev/dog-mask.png"
  }'

Output

{
  "request_id": "flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-fill-dev_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": "flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-fill-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-fill-dev_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": "flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-fill-dev",
  "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 Generation Request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description of what to generate in the masked area
image	Yes	string	—	—	URL of the source image to inpaint (must be publicly accessible). Can contain an alpha mask. Width/height are scaled to the closest multiple of 32, and images larger than 1440x1440 are scaled down to fit.
mask	Yes	string	—	—	URL of a black-and-white mask image: white areas are inpainted (regenerated), black areas are preserved. Required — a request without a mask is rejected with `400 'mask' is required` before any charge.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
guidance	No	number	30	0 – 100	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_outputs	No	integer	1	1 – 4	Number of output images to generate.
num_inference_steps	No	integer	28	1 – 50	Number of refinement (denoising) steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster. Recommended range: 28-50.
megapixels	No	string	"1"	"1", "0.25", "match_input"	Approximate resolution of the generated image, in megapixels. Use "match_input" to match the size of the input image (with an upper limit of 1440x1440 pixels).
output_format	No	string	webp	webp, jpg, png	Format of the output images.
output_quality	No	integer	80	0 – 100	Compression quality of the saved file, from 0 (smallest file, lowest quality) to 100 (largest file, best quality). No effect on lossless formats like PNG.
lora_weights	No	string	—	—	Optional LoRA weights to load. Accepts a hosted model reference (owner/model or owner/model/version), a Hugging Face URL (huggingface.co/owner/model-name), a CivitAI URL (civitai.com/models/id), or a direct .safetensors URL. Example: 'fofr/flux-pixar-cars'.
lora_scale	No	number	1	-1 – 3	How strongly the selected style add-on (LoRA) is applied. Higher values make its effect more pronounced; lower values make it subtler. Sane results are usually between 0 and 1.
disable_safety_checker	No	boolean	false	true, false	Disable the safety checker (NSFW filter) for generated images.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Image + mask (area to fill).

Example Request

{
  "prompt": "a futuristic spaceship with neon lights",
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/recraft/a-red-cat-1781619282400-0.webp",
  "mask": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/seedream-5-0-lite-text-to-image_019ecace-485b-7447-c8d1-ce0344929afed/output.png",
  "seed": 42,
  "guidance": 35,
  "num_outputs": 2,
  "num_inference_steps": 35,
  "output_format": "png",
  "output_quality": 95
}

Response

{
  "request_id": "flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/flux-fill-dev_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. Required: $0.01"
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'flux-fill-dev' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "flux-fill-dev",
  "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/flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "flux-fill-dev",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/flux-fill-dev_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-04-14T10:00:00.000Z",
  "updated_at": "2026-04-14T10:00:30.000Z",
  "completed_at": "2026-04-14T10:00:30.000Z"
}

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 (image/png)
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.

Flux Fill Dev API Pricing

Your request will cost $0.04 per image.

Flux 3 API, Flux 2 Max API, Flux 2 Pro API, Flux Kontext API, Flux Pro VTO API, Flux 1.0 (Free) API: Pricing, Documentation

Models Version

Get $5 Free Credit on First Payment

Flux Video Upscale API Documentation

Authentication

Flux Video Upscale generate request

Request Code

Output

Webhook (Optional)

Request Parameters - Flux Video Upscale generate request

Example Request

Response

Request Headers

Response Handling

Error Responses

Queue System Errors

Error via Status/Webhook

Retrieving Results

Endpoint

cURL Example

Response (Completed)

Response Fields

Status Values

Status Flow

Typical Workflow

Flux Video Upscale API Pricing

FLUX 3 Video API Documentation

Authentication

Text to Video - FLUX 3 Video

Request Code

Output

Webhook (Optional)

Example: enable Webhook

Callback Payload (success)

Failure callback shape

Delivery semantics

Request Parameters

Notes

Example Request

Example Response

Request Headers

Response Handling

Retrieving Results

Completed response

Response Fields

Status Values & Flow

Pricing

FLUX 3 Video API Pricing

FLUX 3 Video API Documentation

Authentication

Keyframes to Video - FLUX 3 Video

Request Code

Output

Webhook (Optional)

Example: enable Webhook

Callback Payload (success)

Failure callback shape

Delivery semantics

Request Parameters

Notes

Using more than one keyframe

1. A single image — the opening frame

2. Two images — start and end

3. Several untimed images — spread evenly

4. Timed [seconds, image] pairs — exact placement

Limits

Example Request

Example Response

Request Headers

Response Handling

Retrieving Results

Completed response

Response Fields

Status Values & Flow

Pricing

FLUX 3 Video API Pricing

FLUX 3 Video API Documentation

Authentication

Video to Video - FLUX 3 Video

Request Code

4. Timed `[seconds, image]` pairs — exact placement