Pixazo API→Models→Image to Video API→Luma Dream Machine
Pixazo API→Models→Image to Video API→Luma Dream Machine

Luma Ray 3.2 API, Luma Uni 1.1 API: Pricing, Documentation

by Luma AI

Luma is a breakthrough AI video generation model known for producing highly realistic, cinematic-quality videos. Through Pixazo's 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
Luma AI API

Models Version

WELCOME BONUS

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

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

Claim Your Cashback →

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.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour 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"
}

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.

HeaderTypeRequiredDescription
X-Webhook-URLstringNoHTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-ModestringNoterminal (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

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text prompt describing the video to generate.
aspect_ratioNostring16:93:4, 4:3, 1:1, 9:16, 16:9, 21:9Aspect ratio of the generated video.
resolutionNostring540p540p, 720p, 1080pOutput resolution. Higher resolutions cost more.
durationNostring5s5s, 10sDuration of the generated video.
loopNobooleanfalsetrue, falseGenerate a seamless loop. Only valid for 5s SDR generations without an end frame.
hdrNobooleanfalsetrue, falseGenerate an HDR-encoded MP4. Requires HDR account access and 720p/1080p; not supported with 10s or loop. Billed at 2x the SDR rate.
exr_exportNobooleanfalsetrue, falseAlso 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

HeaderRequiredDescription
Ocp-Apim-Subscription-KeyYesYour API subscription key.
Content-TypeYesMust be application/json.
X-Webhook-URLNoHTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status CodeMeaning
202 AcceptedRequest queued. Returns request_id, status: "QUEUED", and polling_url.
400 Bad RequestInvalid request body or unknown model.
401 UnauthorizedMissing or invalid subscription key.
402 Payment RequiredInsufficient wallet balance.
403 ForbiddenSubscription not permitted to access this API.
429 Too Many RequestsRate limit exceeded.
500 Internal Server ErrorUnexpected 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

FieldTypeDescription
request_idstringUnique identifier for the request.
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_idstringThe model that handled the request (luma-agent-ray-v3-2-text-to-video).
errorstring | nullError message when the request fails; null otherwise.
output.media_urlstring[]Array of URLs to the generated MP4 video.
output.media_typestringMIME type of the output (video/mp4).
created_atstringISO-8601 timestamp when the request was created.
completed_atstringISO-8601 timestamp when the request reached a terminal state.
polling_urlstringURL to poll for status (returned on submit).

Status Values & Flow

StatusMeaning
QUEUEDRequest accepted and waiting to be processed.
PROCESSINGThe video generation job is running.
COMPLETEDDone — output.media_url contains the generated video.
FAILED / ERRORGeneration 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.

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.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour 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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    "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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
    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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
      "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"
}

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.

HeaderTypeRequiredDescription
X-Webhook-URLstringNoHTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-ModestringNoterminal (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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg", "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

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text prompt describing the motion/scene to generate.
image_urlNostring——URL of the first-frame image. Provide image_url (optionally with end_image_url) OR keyframes — mutually exclusive.
end_image_urlNostring——Optional last-frame image; the model interpolates between image_url and end_image_url. Cannot be combined with keyframes.
aspect_ratioNostring16:93:4, 4:3, 1:1, 9:16, 16:9, 21:9Aspect ratio of the generated video.
resolutionNostring540p540p, 720p, 1080pOutput resolution. Higher resolutions cost more.
durationNostring5s5s, 10sDuration of the generated video. 10s requires multi-keyframe input (keyframes / keyframe_indexes); not supported with a single image_url / end_image_url anchor.
loopNobooleanfalsetrue, falseGenerate a seamless loop. SDR only, no end frame or keyframes.
hdrNobooleanfalsetrue, falseHDR-encoded MP4. Requires HDR account access and 720p/1080p; not supported with loop. Billed at 2x the SDR rate.
exr_exportNobooleanfalsetrue, falseAlso export an EXR sidecar. Requires hdr=true. Billed at 3x the SDR rate.
keyframesNolist<string>—1-64 URLsMulti-keyframe guide frames pinned at keyframe_indexes. Mutually exclusive with image_url/end_image_url/loop; unlocks 10s and HDR.
keyframe_indexesNolist<integer>—1-64Output-frame positions (5s -> 0-120, 10s -> 0-240) for each keyframes[i]. Non-negative, unique, same length as keyframes.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image1JPG, PNG, WEBPStart 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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg",
  "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

HeaderRequiredDescription
Ocp-Apim-Subscription-KeyYesYour API subscription key.
Content-TypeYesMust be application/json.
X-Webhook-URLNoHTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status CodeMeaning
202 AcceptedRequest queued. Returns request_id, status: "QUEUED", and polling_url.
400 Bad RequestInvalid request body or unknown model.
401 UnauthorizedMissing or invalid subscription key.
402 Payment RequiredInsufficient wallet balance.
403 ForbiddenSubscription not permitted to access this API.
429 Too Many RequestsRate limit exceeded.
500 Internal Server ErrorUnexpected 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

FieldTypeDescription
request_idstringUnique identifier for the request.
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_idstringThe model that handled the request (luma-agent-ray-v3-2-image-to-video).
errorstring | nullError message when the request fails; null otherwise.
output.media_urlstring[]Array of URLs to the generated MP4 video.
output.media_typestringMIME type of the output (video/mp4).
created_atstringISO-8601 timestamp when the request was created.
completed_atstringISO-8601 timestamp when the request reached a terminal state.
polling_urlstringURL to poll for status (returned on submit).

Status Values & Flow

StatusMeaning
QUEUEDRequest accepted and waiting to be processed.
PROCESSINGThe video generation job is running.
COMPLETEDDone — output.media_url contains the generated video.
FAILED / ERRORGeneration 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.

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.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour 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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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"
}

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.

HeaderTypeRequiredDescription
X-Webhook-URLstringNoHTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-ModestringNoterminal (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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text prompt describing how to edit the source video.
video_urlYesstring——URL of the source video to edit.
start_image_urlNostring——Optional first-frame image (e.g. a restyled opening frame) to steer the edit's look. Leave unset to derive from the source.
resolutionNostring540p540p, 720p, 1080pOutput resolution. Higher resolutions cost more.
durationNostring5s5s, 10sDuration of the edited video.
edit_strengthNostring—adhere_1, adhere_2, adhere_3, flex_1, flex_2, flex_3, reimagine_1, reimagine_2, reimagine_3How closely the edit preserves the source (adhere = closest, reimagine = most divergent). Cannot be combined with auto_controls.
auto_controlsNobooleanfalsetrue, falseLet the model derive the edit conditioning schedule from the source. Cannot be combined with edit_strength.
hdrNobooleanfalsetrue, falseHDR-encoded MP4. Requires HDR account access and 720p/1080p. Billed at 2x the SDR rate.
exr_exportNobooleanfalsetrue, falseAlso export an EXR sidecar. Requires hdr=true. Billed at 3x the SDR rate.
controlsNoobject——Per-signal conditioning controls (pose, depth, normals, trajectory, face) for finer edit control than edit_strength. Cannot be combined with auto_controls.
keyframesNolist<string>—up to 64 URLsMulti-keyframe guide frames pinned at keyframe_indexes. Mutually exclusive with start_image_url.
keyframe_indexesNolist<integer>—1-64Source-frame positions for each keyframes[i]. Non-negative, unique, same length as keyframes.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
video1MP4, MOVSource video to edit.
image1JPG, PNG, WEBPStart frame image.

Example Request

{
  "prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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

HeaderRequiredDescription
Ocp-Apim-Subscription-KeyYesYour API subscription key.
Content-TypeYesMust be application/json.
X-Webhook-URLNoHTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status CodeMeaning
202 AcceptedRequest queued. Returns request_id, status: "QUEUED", and polling_url.
400 Bad RequestInvalid request body or unknown model.
401 UnauthorizedMissing or invalid subscription key.
402 Payment RequiredInsufficient wallet balance.
403 ForbiddenSubscription not permitted to access this API.
429 Too Many RequestsRate limit exceeded.
500 Internal Server ErrorUnexpected 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

FieldTypeDescription
request_idstringUnique identifier for the request.
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_idstringThe model that handled the request (luma-agent-ray-v3-2-video-to-video).
errorstring | nullError message when the request fails; null otherwise.
output.media_urlstring[]Array of URLs to the generated MP4 video.
output.media_typestringMIME type of the output (video/mp4).
created_atstringISO-8601 timestamp when the request was created.
completed_atstringISO-8601 timestamp when the request reached a terminal state.
polling_urlstringURL to poll for status (returned on submit).

Status Values & Flow

StatusMeaning
QUEUEDRequest accepted and waiting to be processed.
PROCESSINGThe video generation job is running.
COMPLETEDDone — output.media_url contains the generated video.
FAILED / ERRORGeneration 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.

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.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour 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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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"
}

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.

HeaderTypeRequiredDescription
X-Webhook-URLstringNoHTTPS URL to receive the callback. Providing it enables webhook delivery.
X-Webhook-ModestringNoterminal (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://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text prompt describing the content to paint into the newly exposed canvas when reframing.
video_urlYesstring—≤30 secondsURL of the source video to reframe.
aspect_ratioYesstring—3:4, 4:3, 1:1, 9:16, 16:9, 21:9Target aspect ratio for the reframed video.
resolutionNostring540p540p, 720p, 1080pOutput resolution. Higher resolutions cost more.
source_positionNoobject——Optional normalized source rectangle controlling where the source video sits in the output canvas.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
video1MP4, MOVVideo to reframe.

Example Request

{
  "prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.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

HeaderRequiredDescription
Ocp-Apim-Subscription-KeyYesYour API subscription key.
Content-TypeYesMust be application/json.
X-Webhook-URLNoHTTPS callback URL (see Webhook section).

Response Handling

Common status codes returned by the submit endpoint.

Status CodeMeaning
202 AcceptedRequest queued. Returns request_id, status: "QUEUED", and polling_url.
400 Bad RequestInvalid request body or unknown model.
401 UnauthorizedMissing or invalid subscription key.
402 Payment RequiredInsufficient wallet balance.
403 ForbiddenSubscription not permitted to access this API.
429 Too Many RequestsRate limit exceeded.
500 Internal Server ErrorUnexpected 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

FieldTypeDescription
request_idstringUnique identifier for the request.
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR.
model_idstringThe model that handled the request (luma-agent-ray-v3-2-reframe).
errorstring | nullError message when the request fails; null otherwise.
output.media_urlstring[]Array of URLs to the generated MP4 video.
output.media_typestringMIME type of the output (video/mp4).
created_atstringISO-8601 timestamp when the request was created.
completed_atstringISO-8601 timestamp when the request reached a terminal state.
polling_urlstringURL to poll for status (returned on submit).

Status Values & Flow

StatusMeaning
QUEUEDRequest accepted and waiting to be processed.
PROCESSINGThe video generation job is running.
COMPLETEDDone — output.media_url contains the generated video.
FAILED / ERRORGeneration 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.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour 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"
}

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
promptYesstring—non-empty; ≤ 6000 charsText description for image generation. Must be 1–6000 characters.
aspect_ratioNoenum—"3:1", "2:1", "16:9", "3:2", "1:1", "2:3", "9:16", "1:2", "1:3"Image aspect ratio.
styleNoenum"auto""auto", "manga"Visual style of the output.
output_formatNoenum—"png", "jpeg"Output file format.
enable_web_searchNobooleanfalse—When true, the model may perform web search to enrich context and improve visual accuracy.
reference_image_urlsNostring[]—up to 9 URLsArray of up to 9 HTTPS URLs to reference images that guide generation. Each URL must be publicly accessible.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
reference_image_urls8JPG, PNG, WEBP, GIF, AVIFReference 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-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal 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

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. 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.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour 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"
}

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
promptYesstring—1–6000 charactersText instruction describing the desired edit (1–6000 characters).
image_urlYesstring——URL of the source image to edit. Supported formats: JPG, JPEG, PNG, WebP, GIF, AVIF.
styleNoenumautoauto, mangaVisual style to apply. Allowed values: auto, manga.
output_formatNoenum—png, jpegOutput encoding format. Allowed values: png, jpeg. If omitted, defaults to the source image format.
reference_image_urlsNostring[]—up to 8 URLsUp to 8 additional reference image URLs to guide the editing process. Each reference image incurs an additional $0.003 charge.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image_url1JPG, PNG, WEBP, GIF, AVIFImage to edit.
reference_image_urls8JPG, PNG, WEBP, GIF, AVIFReference 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-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_API_KEY

Response Handling

Common status codes.

CodeMeaning
202Accepted — Request queued
Bad Request
401Unauthorized
402Insufficient Balance
403Forbidden
Too Many Requests
500Internal 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

FieldTypeDescription
request_idstringUnique request identifier
statusstringQUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_idstringModel that processed the request
errorstring|nullError message if failed
output.media_urlarrayURLs to generated media (R2 CDN)
output.media_typestringMIME type of the output
created_atstringWhen request was created
completed_atstringWhen request completed
polling_urlstringStatus URL (initial response only)

Status Values

StatusDescription
QUEUEDRequest accepted, waiting to be processed
PROCESSINGBeing processed by the model
COMPLETEDDone — output contains the result
FAILEDFailed — check error field
ERRORSystem error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

  1. Send a generate request to the API endpoint
  2. Save the request_id from the response
  3. Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
  4. 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

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

⚡ Performance

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

Show data for the last
Generations
200last 30d
~7 per day
Success rate
100.0%
of completed generations
Generation time
105.0savg
p95 107.0s
Requests
Oct 18max 200Nov 16
Luma Ray 3.2Avg 7/day
Generation Time
Oct 18max 105.0sNov 16
Luma Ray 3.2Avg 105.0s
Error Rate
Oct 18max 5.0%Nov 16
Luma Ray 3.2Avg 0.0%

〰 Uptime

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

Avg. Success Rate (30d)
100.00%
across all generations of this model family
Uptime
Oct 18max 100%Nov 16
SuccessfulAvg 100.00%