Pixazo API→Models→Luma Dream Machine

Luma Uni 1.1 API, Luma Dream Machine 1.5 API, 1.0 API: Pricing, Documentation

Luma Uni 1.1 API, developers can generate videos from text prompts or images with exceptional visual quality and temporal consistency. The API supports multiple versions including v1.5 for enhanced capabilities, making it ideal for filmmakers, advertisers, and creative professionals.

Get API Key

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

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

Claim Your $5 →

Luma Ray 3.2 API Documentation

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-text-to-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 - Luma Ray v3.2

Request Code

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-text-to-video/v1/text-to-video
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A herd of wild horses galloping across a dusty desert plain under a blazing midday sun; wide tracking shot.",
  "aspect_ratio": "16:9",
  "resolution": "540p",
  "duration": "5s"
}

import requests

url = "https://gateway.pixazo.ai/luma-agent-ray-v3-2-text-to-video/v1/text-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
payload = {
    "prompt": "A herd of wild horses galloping across a dusty desert plain under a blazing midday sun; wide tracking shot.",
    "aspect_ratio": "16:9",
    "resolution": "540p",
    "duration": "5s"
}

resp = requests.post(url, headers=headers, json=payload)
print(resp.json())  # { "request_id": "...", "status": "QUEUED", "polling_url": "..." }

const res = await fetch("https://gateway.pixazo.ai/luma-agent-ray-v3-2-text-to-video/v1/text-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    prompt: "A herd of wild horses galloping across a dusty desert plain under a blazing midday sun; wide tracking shot.",
    aspect_ratio: "16:9",
    resolution: "540p",
    duration: "5s"
  })
});
const data = await res.json();
console.log(data); // { request_id, status: "QUEUED", polling_url }

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-text-to-video/v1/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
      "prompt": "A herd of wild horses galloping across a dusty desert plain under a blazing midday sun; wide tracking shot.",
      "aspect_ratio": "16:9",
      "resolution": "540p",
      "duration": "5s"
    }'

Output

{
  "request_id": "luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Instead of polling, you can receive a callback when the request reaches a terminal state. Pass the webhook headers on the submit request; the gateway will POST the result to your URL.

Header	Type	Required	Description
X-Webhook-URL	string	No	HTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-Mode	string	No	`terminal` (default) fires once on COMPLETED/ERROR; `sync` fires on each status transition.

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-text-to-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/webhooks/pixazo" \
  -H "X-Webhook-Mode: terminal" \
  --data-raw '{"prompt": "A herd of wild horses galloping across a dusty desert plain under a blazing midday sun; wide tracking shot.", "aspect_ratio": "16:9", "resolution": "540p", "duration": "5s"}'

Callback Payload (success)

{
  "request_id": "luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-text-to-video",
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-text-to-video_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  }
}

Failure callback shape

{
  "request_id": "luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "error": "Failed to download the file. Please check if the URL is accessible."
}

terminal mode delivers one callback on COMPLETED or ERROR; sync mode delivers on each status transition.
Deliveries are keyed by request_id — make your handler idempotent.
Respond with HTTP 200 within a few seconds; non-2xx responses are retried.
The webhook URL must be HTTPS and publicly reachable.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the video to generate.
aspect_ratio	No	string	16:9	3:4, 4:3, 1:1, 9:16, 16:9, 21:9	Aspect ratio of the generated video.
resolution	No	string	540p	540p, 720p, 1080p	Output resolution. Higher resolutions cost more.
duration	No	string	5s	5s, 10s	Duration of the generated video.
loop	No	boolean	false	true, false	Generate a seamless loop. Only valid for 5s SDR generations without an end frame.
hdr	No	boolean	false	true, false	Generate an HDR-encoded MP4. Requires HDR account access and 720p/1080p; not supported with 10s or loop. Billed at 2x the SDR rate.
exr_export	No	boolean	false	true, false	Also export an EXR sidecar alongside the MP4. Requires hdr=true. Billed at 3x the SDR rate.

Example Request

{
  "prompt": "A herd of wild horses galloping across a dusty desert plain under a blazing midday sun; wide tracking shot.",
  "aspect_ratio": "16:9",
  "resolution": "540p",
  "duration": "5s"
}

Example Response

{
  "request_id": "luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Required	Description
Ocp-Apim-Subscription-Key	Yes	Your API subscription key.
Content-Type	Yes	Must be `application/json`.
X-Webhook-URL	No	HTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status Code	Meaning
202 Accepted	Request queued. Returns `request_id`, `status: "QUEUED"`, and `polling_url`.
400 Bad Request	Invalid request body or unknown model.
401 Unauthorized	Missing or invalid subscription key.
402 Payment Required	Insufficient wallet balance.
403 Forbidden	Subscription not permitted to access this API.
429 Too Many Requests	Rate limit exceeded.
500 Internal Server Error	Unexpected gateway error.

Error Responses

Queue-system errors are returned at submit time; generation errors are surfaced via the status endpoint / webhook with status: "ERROR".

// 402 — insufficient balance
{ "error": "Insufficient balance", "message": "Wallet balance is too low for this request." }

// 400 — model not found / invalid body
{ "error": "Model not found", "message": "Model 'luma-agent-ray-v3-2-text-to-video' not found or is disabled" }

// generation failure (via status / webhook)
{ "request_id": "luma-agent-ray-v3-2-text-to-video_019dxxxx...", "status": "ERROR", "error": "Failed to download the input file." }

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or FAILED/ERROR).

curl -X GET "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY"

Completed response

{
  "request_id": "luma-agent-ray-v3-2-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-text-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-text-to-video_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-30T09:20:33.812Z",
  "completed_at": "2026-06-30T09:22:19.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique identifier for the request.
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_id	string	The model that handled the request (`luma-agent-ray-v3-2-text-to-video`).
error	string \| null	Error message when the request fails; null otherwise.
output.media_url	string[]	Array of URLs to the generated MP4 video.
output.media_type	string	MIME type of the output (`video/mp4`).
created_at	string	ISO-8601 timestamp when the request was created.
completed_at	string	ISO-8601 timestamp when the request reached a terminal state.
polling_url	string	URL to poll for status (returned on submit).

Status Values & Flow

Status	Meaning
QUEUED	Request accepted and waiting to be processed.
PROCESSING	The video generation job is running.
COMPLETED	Done — `output.media_url` contains the generated video.
FAILED / ERROR	Generation failed — see `error`.

Typical workflow

Luma Ray 3.2 API Pricing

Your request will cost $0.10 per second of output video (by resolution).

5-second 540p clip ≈ $0.50

Image to Video

Luma Ray 3.2 API Documentation

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-image-to-video/v1/image-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

Image to Video - Luma Ray v3.2

Request Code

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-image-to-video/v1/image-to-video
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
  "image_url": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
  "aspect_ratio": "16:9",
  "resolution": "540p",
  "duration": "5s"
}

import requests

url = "https://gateway.pixazo.ai/luma-agent-ray-v3-2-image-to-video/v1/image-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
payload = {
    "prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
    "image_url": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
    "aspect_ratio": "16:9",
    "resolution": "540p",
    "duration": "5s"
}

resp = requests.post(url, headers=headers, json=payload)
print(resp.json())  # { "request_id": "...", "status": "QUEUED", "polling_url": "..." }

const res = await fetch("https://gateway.pixazo.ai/luma-agent-ray-v3-2-image-to-video/v1/image-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    prompt: "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
    image_url: "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
    aspect_ratio: "16:9",
    resolution: "540p",
    duration: "5s"
  })
});
const data = await res.json();
console.log(data); // { request_id, status: "QUEUED", polling_url }

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-image-to-video/v1/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
      "prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
      "image_url": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
      "aspect_ratio": "16:9",
      "resolution": "540p",
      "duration": "5s"
    }'

Output

{
  "request_id": "luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Instead of polling, you can receive a callback when the request reaches a terminal state. Pass the webhook headers on the submit request; the gateway will POST the result to your URL.

Header	Type	Required	Description
X-Webhook-URL	string	No	HTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-Mode	string	No	`terminal` (default) fires once on COMPLETED/ERROR; `sync` fires on each status transition.

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-image-to-video/v1/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  -H "X-Webhook-URL: https://your-server.com/webhooks/pixazo" \
  -H "X-Webhook-Mode: terminal" \
  --data-raw '{"prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.", "image_url": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png", "aspect_ratio": "16:9", "resolution": "540p", "duration": "5s"}'

Callback Payload (success)

{
  "request_id": "luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-image-to-video",
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-image-to-video_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  }
}

Failure callback shape

{
  "request_id": "luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "error": "Failed to download the file. Please check if the URL is accessible."
}

terminal mode delivers one callback on COMPLETED or ERROR; sync mode delivers on each status transition.
Deliveries are keyed by request_id — make your handler idempotent.
Respond with HTTP 200 within a few seconds; non-2xx responses are retried.
The webhook URL must be HTTPS and publicly reachable.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the motion/scene to generate.
image_url	No	string	—	—	URL of the first-frame image. Provide image_url (optionally with end_image_url) OR keyframes — mutually exclusive.
end_image_url	No	string	—	—	Optional last-frame image; the model interpolates between image_url and end_image_url. Cannot be combined with keyframes.
aspect_ratio	No	string	16:9	3:4, 4:3, 1:1, 9:16, 16:9, 21:9	Aspect ratio of the generated video.
resolution	No	string	540p	540p, 720p, 1080p	Output resolution. Higher resolutions cost more.
duration	No	string	5s	5s, 10s	Duration of the generated video. 10s requires multi-keyframe input (keyframes / keyframe_indexes); not supported with a single image_url / end_image_url anchor.
loop	No	boolean	false	true, false	Generate a seamless loop. SDR only, no end frame or keyframes.
hdr	No	boolean	false	true, false	HDR-encoded MP4. Requires HDR account access and 720p/1080p; not supported with loop. Billed at 2x the SDR rate.
exr_export	No	boolean	false	true, false	Also export an EXR sidecar. Requires hdr=true. Billed at 3x the SDR rate.
keyframes	No	list<string>	—	1-64 URLs	Multi-keyframe guide frames pinned at keyframe_indexes. Mutually exclusive with image_url/end_image_url/loop; unlocks 10s and HDR.
keyframe_indexes	No	list<integer>	—	1-64	Output-frame positions (5s -> 0-120, 10s -> 0-240) for each keyframes[i]. Non-negative, unique, same length as keyframes.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Start or end frame image.

Example Request

{
  "prompt": "Low-angle shot of a majestic tiger prowling through a snowy landscape, leaving paw prints on the white blanket.",
  "image_url": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
  "aspect_ratio": "16:9",
  "resolution": "540p",
  "duration": "5s"
}

Example Response

{
  "request_id": "luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Required	Description
Ocp-Apim-Subscription-Key	Yes	Your API subscription key.
Content-Type	Yes	Must be `application/json`.
X-Webhook-URL	No	HTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status Code	Meaning
202 Accepted	Request queued. Returns `request_id`, `status: "QUEUED"`, and `polling_url`.
400 Bad Request	Invalid request body or unknown model.
401 Unauthorized	Missing or invalid subscription key.
402 Payment Required	Insufficient wallet balance.
403 Forbidden	Subscription not permitted to access this API.
429 Too Many Requests	Rate limit exceeded.
500 Internal Server Error	Unexpected gateway error.

Error Responses

Queue-system errors are returned at submit time; generation errors are surfaced via the status endpoint / webhook with status: "ERROR".

// 402 — insufficient balance
{ "error": "Insufficient balance", "message": "Wallet balance is too low for this request." }

// 400 — model not found / invalid body
{ "error": "Model not found", "message": "Model 'luma-agent-ray-v3-2-image-to-video' not found or is disabled" }

// generation failure (via status / webhook)
{ "request_id": "luma-agent-ray-v3-2-image-to-video_019dxxxx...", "status": "ERROR", "error": "Failed to download the input file." }

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or FAILED/ERROR).

curl -X GET "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY"

Completed response

{
  "request_id": "luma-agent-ray-v3-2-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-image-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-image-to-video_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-30T09:20:33.812Z",
  "completed_at": "2026-06-30T09:22:19.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique identifier for the request.
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_id	string	The model that handled the request (`luma-agent-ray-v3-2-image-to-video`).
error	string \| null	Error message when the request fails; null otherwise.
output.media_url	string[]	Array of URLs to the generated MP4 video.
output.media_type	string	MIME type of the output (`video/mp4`).
created_at	string	ISO-8601 timestamp when the request was created.
completed_at	string	ISO-8601 timestamp when the request reached a terminal state.
polling_url	string	URL to poll for status (returned on submit).

Status Values & Flow

Status	Meaning
QUEUED	Request accepted and waiting to be processed.
PROCESSING	The video generation job is running.
COMPLETED	Done — `output.media_url` contains the generated video.
FAILED / ERROR	Generation failed — see `error`.

Typical workflow

Luma Ray 3.2 API Pricing

Your request will cost $0.03 per second of output video (by resolution).

5-second 540p clip ≈ $0.15

Video to Video (Video Editing)

Luma Ray 3.2 API Documentation

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-video-to-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 - Luma Ray v3.2

Request Code

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-video-to-video/v1/video-to-video
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
  "resolution": "540p",
  "duration": "5s"
}

import requests

url = "https://gateway.pixazo.ai/luma-agent-ray-v3-2-video-to-video/v1/video-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
payload = {
    "prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
    "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
    "resolution": "540p",
    "duration": "5s"
}

resp = requests.post(url, headers=headers, json=payload)
print(resp.json())  # { "request_id": "...", "status": "QUEUED", "polling_url": "..." }

const res = await fetch("https://gateway.pixazo.ai/luma-agent-ray-v3-2-video-to-video/v1/video-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    prompt: "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
    video_url: "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
    resolution: "540p",
    duration: "5s"
  })
});
const data = await res.json();
console.log(data); // { request_id, status: "QUEUED", polling_url }

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-video-to-video/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
      "prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
      "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
      "resolution": "540p",
      "duration": "5s"
    }'

Output

{
  "request_id": "luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Instead of polling, you can receive a callback when the request reaches a terminal state. Pass the webhook headers on the submit request; the gateway will POST the result to your URL.

Header	Type	Required	Description
X-Webhook-URL	string	No	HTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-Mode	string	No	`terminal` (default) fires once on COMPLETED/ERROR; `sync` fires on each status transition.

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-video-to-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/webhooks/pixazo" \
  -H "X-Webhook-Mode: terminal" \
  --data-raw '{"prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.", "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4", "resolution": "540p", "duration": "5s"}'

Callback Payload (success)

{
  "request_id": "luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-video-to-video",
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-video-to-video_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  }
}

Failure callback shape

{
  "request_id": "luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "error": "Failed to download the file. Please check if the URL is accessible."
}

terminal mode delivers one callback on COMPLETED or ERROR; sync mode delivers on each status transition.
Deliveries are keyed by request_id — make your handler idempotent.
Respond with HTTP 200 within a few seconds; non-2xx responses are retried.
The webhook URL must be HTTPS and publicly reachable.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing how to edit the source video.
video_url	Yes	string	—	—	URL of the source video to edit.
start_image_url	No	string	—	—	Optional first-frame image (e.g. a restyled opening frame) to steer the edit's look. Leave unset to derive from the source.
resolution	No	string	540p	540p, 720p, 1080p	Output resolution. Higher resolutions cost more.
duration	No	string	5s	5s, 10s	Duration of the edited video.
edit_strength	No	string	—	adhere_1, adhere_2, adhere_3, flex_1, flex_2, flex_3, reimagine_1, reimagine_2, reimagine_3	How closely the edit preserves the source (adhere = closest, reimagine = most divergent). Cannot be combined with auto_controls.
auto_controls	No	boolean	false	true, false	Let the model derive the edit conditioning schedule from the source. Cannot be combined with edit_strength.
hdr	No	boolean	false	true, false	HDR-encoded MP4. Requires HDR account access and 720p/1080p. Billed at 2x the SDR rate.
exr_export	No	boolean	false	true, false	Also export an EXR sidecar. Requires hdr=true. Billed at 3x the SDR rate.
controls	No	object	—	—	Per-signal conditioning controls (pose, depth, normals, trajectory, face) for finer edit control than edit_strength. Cannot be combined with auto_controls.
keyframes	No	list<string>	—	up to 64 URLs	Multi-keyframe guide frames pinned at keyframe_indexes. Mutually exclusive with start_image_url.
keyframe_indexes	No	list<integer>	—	1-64	Source-frame positions for each keyframes[i]. Non-negative, unique, same length as keyframes.

Content Item Types & Limits

Type	Max	Format / Size	Description
video	1	MP4, MOV	Source video to edit.
image	1	JPG, PNG, WEBP	Start frame image.

Example Request

{
  "prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
  "resolution": "540p",
  "duration": "5s"
}

Example Response

{
  "request_id": "luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Required	Description
Ocp-Apim-Subscription-Key	Yes	Your API subscription key.
Content-Type	Yes	Must be `application/json`.
X-Webhook-URL	No	HTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status Code	Meaning
202 Accepted	Request queued. Returns `request_id`, `status: "QUEUED"`, and `polling_url`.
400 Bad Request	Invalid request body or unknown model.
401 Unauthorized	Missing or invalid subscription key.
402 Payment Required	Insufficient wallet balance.
403 Forbidden	Subscription not permitted to access this API.
429 Too Many Requests	Rate limit exceeded.
500 Internal Server Error	Unexpected gateway error.

Error Responses

Queue-system errors are returned at submit time; generation errors are surfaced via the status endpoint / webhook with status: "ERROR".

// 402 — insufficient balance
{ "error": "Insufficient balance", "message": "Wallet balance is too low for this request." }

// 400 — model not found / invalid body
{ "error": "Model not found", "message": "Model 'luma-agent-ray-v3-2-video-to-video' not found or is disabled" }

// generation failure (via status / webhook)
{ "request_id": "luma-agent-ray-v3-2-video-to-video_019dxxxx...", "status": "ERROR", "error": "Failed to download the input file." }

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or FAILED/ERROR).

curl -X GET "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY"

Completed response

{
  "request_id": "luma-agent-ray-v3-2-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-video-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-video-to-video_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-30T09:20:33.812Z",
  "completed_at": "2026-06-30T09:22:19.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique identifier for the request.
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_id	string	The model that handled the request (`luma-agent-ray-v3-2-video-to-video`).
error	string \| null	Error message when the request fails; null otherwise.
output.media_url	string[]	Array of URLs to the generated MP4 video.
output.media_type	string	MIME type of the output (`video/mp4`).
created_at	string	ISO-8601 timestamp when the request was created.
completed_at	string	ISO-8601 timestamp when the request reached a terminal state.
polling_url	string	URL to poll for status (returned on submit).

Status Values & Flow

Status	Meaning
QUEUED	Request accepted and waiting to be processed.
PROCESSING	The video generation job is running.
COMPLETED	Done — `output.media_url` contains the generated video.
FAILED / ERROR	Generation failed — see `error`.

Typical workflow

Luma Ray 3.2 API Pricing

Your request will cost $0.144 per second of output video (by resolution).

5-second 540p clip ≈ $0.72

Video to Video (Reframe)

Luma Ray 3.2 API Documentation

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-reframe/v1/reframe

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 (Reframe) - Luma Ray v3.2

Request Code

POST https://gateway.pixazo.ai/luma-agent-ray-v3-2-reframe/v1/reframe
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
  "aspect_ratio": "21:9",
  "resolution": "540p"
}

import requests

url = "https://gateway.pixazo.ai/luma-agent-ray-v3-2-reframe/v1/reframe"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
payload = {
    "prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.",
    "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
    "aspect_ratio": "21:9",
    "resolution": "540p"
}

resp = requests.post(url, headers=headers, json=payload)
print(resp.json())  # { "request_id": "...", "status": "QUEUED", "polling_url": "..." }

const res = await fetch("https://gateway.pixazo.ai/luma-agent-ray-v3-2-reframe/v1/reframe", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
    prompt: "Extend the scene into cinematic widescreen with matching lighting and background detail.",
    video_url: "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
    aspect_ratio: "21:9",
    resolution: "540p"
  })
});
const data = await res.json();
console.log(data); // { request_id, status: "QUEUED", polling_url }

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-reframe/v1/reframe" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
      "prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.",
      "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
      "aspect_ratio": "21:9",
      "resolution": "540p"
    }'

Output

{
  "request_id": "luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Instead of polling, you can receive a callback when the request reaches a terminal state. Pass the webhook headers on the submit request; the gateway will POST the result to your URL.

Header	Type	Required	Description
X-Webhook-URL	string	No	HTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-Mode	string	No	`terminal` (default) fires once on COMPLETED/ERROR; `sync` fires on each status transition.

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/luma-agent-ray-v3-2-reframe/v1/reframe" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  -H "X-Webhook-URL: https://your-server.com/webhooks/pixazo" \
  -H "X-Webhook-Mode: terminal" \
  --data-raw '{"prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.", "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4", "aspect_ratio": "21:9", "resolution": "540p"}'

Callback Payload (success)

{
  "request_id": "luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-reframe",
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-reframe_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  }
}

Failure callback shape

{
  "request_id": "luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "error": "Failed to download the file. Please check if the URL is accessible."
}

terminal mode delivers one callback on COMPLETED or ERROR; sync mode delivers on each status transition.
Deliveries are keyed by request_id — make your handler idempotent.
Respond with HTTP 200 within a few seconds; non-2xx responses are retried.
The webhook URL must be HTTPS and publicly reachable.

Request Parameters

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the content to paint into the newly exposed canvas when reframing.
video_url	Yes	string	—	≤30 seconds	URL of the source video to reframe.
aspect_ratio	Yes	string	—	3:4, 4:3, 1:1, 9:16, 16:9, 21:9	Target aspect ratio for the reframed video.
resolution	No	string	540p	540p, 720p, 1080p	Output resolution. Higher resolutions cost more.
source_position	No	object	—	—	Optional normalized source rectangle controlling where the source video sits in the output canvas.

Content Item Types & Limits

Type	Max	Format / Size	Description
video	1	MP4, MOV	Video to reframe.

Example Request

{
  "prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
  "aspect_ratio": "21:9",
  "resolution": "540p"
}

Example Response

{
  "request_id": "luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Required	Description
Ocp-Apim-Subscription-Key	Yes	Your API subscription key.
Content-Type	Yes	Must be `application/json`.
X-Webhook-URL	No	HTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status Code	Meaning
202 Accepted	Request queued. Returns `request_id`, `status: "QUEUED"`, and `polling_url`.
400 Bad Request	Invalid request body or unknown model.
401 Unauthorized	Missing or invalid subscription key.
402 Payment Required	Insufficient wallet balance.
403 Forbidden	Subscription not permitted to access this API.
429 Too Many Requests	Rate limit exceeded.
500 Internal Server Error	Unexpected gateway error.

Error Responses

Queue-system errors are returned at submit time; generation errors are surfaced via the status endpoint / webhook with status: "ERROR".

// 402 — insufficient balance
{ "error": "Insufficient balance", "message": "Wallet balance is too low for this request." }

// 400 — model not found / invalid body
{ "error": "Model not found", "message": "Model 'luma-agent-ray-v3-2-reframe' not found or is disabled" }

// generation failure (via status / webhook)
{ "request_id": "luma-agent-ray-v3-2-reframe_019dxxxx...", "status": "ERROR", "error": "Failed to download the input file." }

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or FAILED/ERROR).

curl -X GET "https://gateway.pixazo.ai/v2/requests/status/luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY"

Completed response

{
  "request_id": "luma-agent-ray-v3-2-reframe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-ray-v3-2-reframe",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-ray-v3-2-reframe_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-30T09:20:33.812Z",
  "completed_at": "2026-06-30T09:22:19.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique identifier for the request.
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_id	string	The model that handled the request (`luma-agent-ray-v3-2-reframe`).
error	string \| null	Error message when the request fails; null otherwise.
output.media_url	string[]	Array of URLs to the generated MP4 video.
output.media_type	string	MIME type of the output (`video/mp4`).
created_at	string	ISO-8601 timestamp when the request was created.
completed_at	string	ISO-8601 timestamp when the request reached a terminal state.
polling_url	string	URL to poll for status (returned on submit).

Status Values & Flow

Status	Meaning
QUEUED	Request accepted and waiting to be processed.
PROCESSING	The video generation job is running.
COMPLETED	Done — `output.media_url` contains the generated video.
FAILED / ERROR	Generation failed — see `error`.

Typical workflow

QUEUED → PROCESSING → COMPLETED (or FAILED / ERROR). Submit the request, then poll GET /v2/requests/status/{request_id} (or use a webhook) until the status is terminal, then download the video from output.media_url. Reframe has no duration parameter — the output length matches the source video length, and the request is billed per started source second.

Luma Ray 3.2 API Pricing

Your request will cost $0.06 per second of source video (by resolution).

5-second 540p source ≈ $0.30

2. Luma Uni 1.1

Luma Uni 1.1 API Documentation

https://gateway.pixazo.ai/luma-agent-uni-1-text-to-image/v1/luma-agent-uni-1-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

Luma Agent Uni-1 Text to Image generate request

Request Code

POST https://gateway.pixazo.ai/luma-agent-uni-1-text-to-image/v1/luma-agent-uni-1-text-to-image-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A retro-futurist subway station with chrome arches and warm overhead lighting, cinematic",
  "aspect_ratio": "16:9",
  "style": "auto",
  "output_format": "png",
  "enable_web_search": false
}

import requests

url = "https://gateway.pixazo.ai/luma-agent-uni-1-text-to-image/v1/luma-agent-uni-1-text-to-image-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A retro-futurist subway station with chrome arches and warm overhead lighting, cinematic",
    "aspect_ratio": "16:9",
    "style": "auto",
    "output_format": "png",
    "enable_web_search": false
}

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

const url = "https://gateway.pixazo.ai/luma-agent-uni-1-text-to-image/v1/luma-agent-uni-1-text-to-image-request";
const headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
    "prompt": "A retro-futurist subway station with chrome arches and warm overhead lighting, cinematic",
    "aspect_ratio": "16:9",
    "style": "auto",
    "output_format": "png",
    "enable_web_search": 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/luma-agent-uni-1-text-to-image/v1/luma-agent-uni-1-text-to-image-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A retro-futurist subway station with chrome arches and warm overhead lighting, cinematic",
    "aspect_ratio": "16:9",
    "style": "auto",
    "output_format": "png",
    "enable_web_search": false
}'

Output

{
  "request_id": "luma-agent-uni-1-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-uni-1-text-to-image_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 - Luma Agent Uni-1 Text to Image generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	non-empty; ≤ 6000 chars	Text description for image generation. Must be 1–6000 characters.
aspect_ratio	No	enum	—	"3:1", "2:1", "16:9", "3:2", "1:1", "2:3", "9:16", "1:2", "1:3"	Image aspect ratio.
style	No	enum	"auto"	"auto", "manga"	Visual style of the output.
output_format	No	enum	—	"png", "jpeg"	Output file format.
enable_web_search	No	boolean	false	—	When true, the model may perform web search to enrich context and improve visual accuracy.
reference_image_urls	No	string[]	—	up to 9 URLs	Array of up to 9 HTTPS URLs to reference images that guide generation. Each URL must be publicly accessible.

Content Item Types & Limits

Type	Max	Format / Size	Description
reference_image_urls	8	JPG, PNG, WEBP, GIF, AVIF	Reference image(s), up to 8.

Example Request

{
  "prompt": "A retro-futurist subway station with chrome arches and warm overhead lighting, cinematic",
  "aspect_ratio": "16:9",
  "style": "auto",
  "output_format": "png",
  "enable_web_search": false
}

Response

{
  "request_id": "luma-agent-uni-1-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-uni-1-text-to-image_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 'luma-agent-uni-1-text-to-image' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "luma-agent-uni-1-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "luma-agent-uni-1-text-to-image",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

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

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/luma-agent-uni-1-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "luma-agent-uni-1-text-to-image_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-uni-1-text-to-image",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-uni-1-text-to-image_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.

Luma Uni 1.1 API Pricing

Your request will cost $0.042 per image.

Image to Image (Image Editing)

Luma Uni 1.1 API Documentation

https://gateway.pixazo.ai/luma-agent-uni-1-edit/v1/luma-agent-uni-1-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

Luma Agent Uni-1 Edit generate request

Request Code

POST https://gateway.pixazo.ai/luma-agent-uni-1-edit/v1/luma-agent-uni-1-edit-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Restyle the scene as a vibrant manga panel with bold ink lines and soft color washes",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg",
  "style": "auto",
  "output_format": "png"
}

import requests

url = "https://gateway.pixazo.ai/luma-agent-uni-1-edit/v1/luma-agent-uni-1-edit-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Restyle the scene as a vibrant manga panel with bold ink lines and soft color washes",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg",
    "style": "auto",
    "output_format": "png"
}

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

const url = "https://gateway.pixazo.ai/luma-agent-uni-1-edit/v1/luma-agent-uni-1-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 as a vibrant manga panel with bold ink lines and soft color washes",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg",
  "style": "auto",
  "output_format": "png"
};

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/luma-agent-uni-1-edit/v1/luma-agent-uni-1-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 as a vibrant manga panel with bold ink lines and soft color washes",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
    "style": "auto",
    "output_format": "png"
  }'

Output

{
  "request_id": "luma-agent-uni-1-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-uni-1-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 - Luma Agent Uni-1 Edit generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	1–6000 characters	Text instruction describing the desired edit (1–6000 characters).
image_url	Yes	string	—	—	URL of the source image to edit. Supported formats: JPG, JPEG, PNG, WebP, GIF, AVIF.
style	No	enum	auto	auto, manga	Visual style to apply. Allowed values: auto, manga.
output_format	No	enum	—	png, jpeg	Output encoding format. Allowed values: png, jpeg. If omitted, defaults to the source image format.
reference_image_urls	No	string[]	—	up to 8 URLs	Up to 8 additional reference image URLs to guide the editing process. Each reference image incurs an additional $0.003 charge.

Content Item Types & Limits

Type	Max	Format / Size	Description
image_url	1	JPG, PNG, WEBP, GIF, AVIF	Image to edit.
reference_image_urls	8	JPG, PNG, WEBP, GIF, AVIF	Reference image(s), up to 8.

Example Request

{
  "prompt": "Restyle the scene as a vibrant manga panel with bold ink lines and soft color washes",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana/nano-banana-a382a80b-f8df-4de1-a0c1-a5dcfd42dae4-1758783383399.jpg",
  "style": "auto",
  "output_format": "png"
}

Response

{
  "request_id": "luma-agent-uni-1-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/luma-agent-uni-1-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 'luma-agent-uni-1-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "luma-agent-uni-1-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "luma-agent-uni-1-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/luma-agent-uni-1-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "luma-agent-uni-1-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-agent-uni-1-edit",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-agent-uni-1-edit_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.

Luma Uni 1.1 API Pricing

Usage	Price (USD)
Per edit (base)	$0.042
Per source / reference image	$0.003

3. Luma Dream Machine Ray 2 Flash

Luma Dream Machine Ray 2 Flash API Documentation

https://gateway.pixazo.ai/luma-dream-machine-ray-2-flash-image-to-video/v1/luma-dream-machine-ray-2-flash-image-to-video-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

Luma Dream Machine Ray 2 Flash Image to Video generate request - Luma Dream Machine Ray 2 Flash Image to Video

Request Code

POST /luma-dream-machine-ray-2-flash-image-to-video-request HTTP/1.1
Host: gateway.pixazo.ai
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/luma-dream-machine-ray-2-flash-image-to-video.jpg",
  "end_image_url": "",
  "aspect_ratio": "16:9",
  "loop": false,
  "resolution": "540p",
  "duration": "5s"
}

import requests

url = "https://gateway.pixazo.ai/luma-dream-machine-ray-2-flash-image-to-video/v1/luma-dream-machine-ray-2-flash-image-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/luma-dream-machine-ray-2-flash-image-to-video.jpg",
    "end_image_url": "",
    "aspect_ratio": "16:9",
    "loop": False,
    "resolution": "540p",
    "duration": "5s"
}

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

const url = 'https://gateway.pixazo.ai/luma-dream-machine-ray-2-flash-image-to-video/v1/luma-dream-machine-ray-2-flash-image-to-video-request';

const data = {
  prompt: "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
  image_url: "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/luma-dream-machine-ray-2-flash-image-to-video.jpg",
  end_image_url: "",
  aspect_ratio: "16:9",
  loop: false,
  resolution: "540p",
  duration: "5s"
};

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/luma-dream-machine-ray-2-flash-image-to-video/v1/luma-dream-machine-ray-2-flash-image-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/luma-dream-machine-ray-2-flash-image-to-video.jpg",
    "end_image_url": "",
    "aspect_ratio": "16:9",
    "loop": false,
    "resolution": "540p",
    "duration": "5s"
  }'

Output

{
  "request_id": "luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/luma-dream-machine-ray-2-flash-image-to-video_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": "luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-dream-machine-ray-2-flash-image-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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": "luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "luma-dream-machine-ray-2-flash-image-to-video",
  "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 - Luma Dream Machine Ray 2 Flash Image to Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Detailed text description guiding the video transformation. Include style, lighting, motion, and mood for best results.
image_url	Yes	string	—	—	The starting image. Must be a valid HTTP/HTTPS link to a JPEG, PNG, or WebP image.
end_image_url	No	string	""	—	The ending image. If provided, the video will transition from the start image to this end image. Leave empty for single-image generation.
aspect_ratio	No	string	"16:9"	"16:9", "9:16", "4:3", "3:4", "21:9", "9:21"	Aspect ratio of the output video. Supported values: "16:9", "9:16", "4:3", "3:4", "21:9", "9:21".
loop	No	boolean	false	true, false	If true, the generated video will loop seamlessly. Recommended for background animations or social media content.
resolution	No	string	"540p"	"540p", "720p", "1080p"	Output video resolution. Supported values: "540p", "720p", "1080p". Higher resolutions increase processing time.
duration	No	string	"5s"	"5s", "9s"	Duration of the output video. Supported values: "5s", "9s". Longer durations allow for more complex transitions.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Start or end frame image.

Minimum Request

{
  "prompt": "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/luma-dream-machine-ray-2-flash-image-to-video.jpg"
}

Full Request (all options)

{
  "prompt": "Create a magical timelapse transition. The snow melts rapidly to reveal green grass, and the tree branches burst into bloom with pink flowers in real-time. The lighting shifts from cold winter light to warm spring sunshine. The camera pushes in slowly towards the tree. Disney-style magical transformation, cinematic, 8k.",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/luma-dream-machine-ray-2-flash-image-to-video.jpg",
  "end_image_url": "",
  "aspect_ratio": "16:9",
  "loop": false,
  "resolution": "540p",
  "duration": "5s"
}

Response

{
  "request_id": "luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/luma-dream-machine-ray-2-flash-image-to-video_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 for Luma Dream Machine Ray 2 Flash Image to Video generate request.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'luma-dream-machine-ray-2-flash-image-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "luma-dream-machine-ray-2-flash-image-to-video",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

GET /v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "/v2/requests/status/luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "luma-dream-machine-ray-2-flash-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "luma-dream-machine-ray-2-flash-image-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/luma-dream-machine-ray-2-flash-image-to-video_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.

Luma Dream Machine Ray 2 Flash API Pricing

Resolution	Price (USD)
All Resolution / per second	$0.04