Runway Aleph 2, Runway Gen 4.5 API: Pricing, Documentation

by Runway

Runway represents the pinnacle of AI video generation, producing Hollywood-quality videos with unprecedented realism and control. Through Pixazo's API, developers can access Runway's industry-leading video generation for creating cinematic content from text and images. The API powers professional video production workflows, offering the quality and features demanded by filmmakers, advertisers, and media companies.

Get API Key
Runway 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 →

Runway Aleph 2 API Documentation

https://gateway.pixazo.ai/aleph-2/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 (Video Editing) - Aleph 2 API

Request Code

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

{
  "prompt": "Edit the video to match the provided reference frame",
  "video_uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.mp4",
  "prompt_images": [
    { "uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg", "position": "first" }
  ]
}
import requests

url = "https://gateway.pixazo.ai/aleph-2/v1/video-to-video"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Edit the video to match the provided reference frame",
    "video_uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.mp4",
    "prompt_images": [
        { "uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg", "position": "first" }
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/aleph-2/v1/video-to-video';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'Edit the video to match the provided reference frame',
  video_uri: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.mp4',
  prompt_images: [
    { uri: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg', position: 'first' }
  ]
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
curl -v -X POST "https://gateway.pixazo.ai/aleph-2/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": "Edit the video to match the provided reference frame",
    "video_uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.mp4",
    "prompt_images": [
      { "uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg", "position": "first" }
    ]
  }'

Output

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

Examples

Common ways to call POST /aleph-2/v1/video-to-video. Each submit returns a request_id (HTTP 202, queued) — poll the status endpoint (see “Retrieving Results”) for the finished video. Output length matches your source video; billing is per second of the produced video.

Simple Video Edit — Apply a text-only edit to an existing video.
const res = await fetch("https://gateway.pixazo.ai/aleph-2/v1/video-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY",
  },
  body: JSON.stringify({
    prompt: "Transform the scene into a golden-hour sunset with warm lighting",
    video_uri: "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4",
  }),
});

const { request_id } = await res.json() as { request_id: string };
// Poll GET /v2/requests/status/{request_id} until status === "COMPLETED"
curl -X POST "https://gateway.pixazo.ai/aleph-2/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Transform the scene into a golden-hour sunset with warm lighting",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4"
  }'
Keyframe-Guided Edit — Edit a video using a reference image anchored to the first frame of the output.
const res = await fetch("https://gateway.pixazo.ai/aleph-2/v1/video-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY",
  },
  body: JSON.stringify({
    prompt: "Edit the video to match the provided reference frame",
    video_uri: "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/nature-close-up.mp4",
    prompt_images: [
      { uri: "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg", position: "first" }
    ],
  }),
});

const { request_id } = await res.json() as { request_id: string };
// Poll GET /v2/requests/status/{request_id} until status === "COMPLETED"
curl -X POST "https://gateway.pixazo.ai/aleph-2/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Edit the video to match the provided reference frame",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/nature-close-up.mp4",
    "prompt_images": [
      { "uri": "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg", "position": "first" }
    ]
  }'
Timed Keyframe Edit — Place a guidance image at a specific timestamp within the input video using keyframes[].seconds.
const res = await fetch("https://gateway.pixazo.ai/aleph-2/v1/video-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY",
  },
  body: JSON.stringify({
    prompt: "Change the background to a futuristic cityscape at night",
    video_uri: "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/simple-text-to-video.mp4",
    keyframes: [
      { uri: "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg", seconds: 2.0 }
    ],
  }),
});

const { request_id } = await res.json() as { request_id: string };
// Poll GET /v2/requests/status/{request_id} until status === "COMPLETED"
curl -X POST "https://gateway.pixazo.ai/aleph-2/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Change the background to a futuristic cityscape at night",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/simple-text-to-video.mp4",
    "keyframes": [
      { "uri": "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_(cropped).jpg", "seconds": 2.0 }
    ]
  }'
Content Moderation Override — Edit a video featuring public figures with relaxed content moderation.
const res = await fetch("https://gateway.pixazo.ai/aleph-2/v1/video-to-video", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY",
  },
  body: JSON.stringify({
    prompt: "Make the background a dramatic stormy sky",
    video_uri: "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4",
    content_moderation: { public_figure_threshold: "low" },
  }),
});

const { request_id } = await res.json() as { request_id: string };
// Poll GET /v2/requests/status/{request_id} until status === "COMPLETED"
curl -X POST "https://gateway.pixazo.ai/aleph-2/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Make the background a dramatic stormy sky",
    "video_uri": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/runwayml__gen-4.5/cinematic-scene.mp4",
    "content_moderation": { "public_figure_threshold": "low" }
  }'

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

HeaderRequiredDefaultDescription
X-Webhook-URLYes (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-ModeNoterminalterminal — 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": "aleph-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "aleph-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/aleph-2_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": "aleph-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "aleph-2",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - Video to Video

Parameter Required Type Default Allowed values / range Description
promptYesstring—1–1000 charactersPlain-language instruction describing the edit to apply to the source video. Describe only what should change (for example, "make it night time, keep the camera move").
video_uriYesstring—HTTPS URL, runway:// URI, or data:video/… URI; source video 2–30 s, under 16 MB, 30 FPS or lowerSource video to edit. The output preserves the source video's length and resolution (up to 1080p) — there is no separate duration or resolution control, and billing is per second of the produced video.
prompt_imagesNoarray—1–5 items, each { uri, position } where position = "first" | "last" | {type:"timestamp",timestampSeconds} | {type:"position",positionPercentage}Optional reference images that guide the edit, each pinned to a position in the video: the first or last frame, an absolute timestamp (seconds), or a fraction of the way through (0–1).
keyframesNoarray—1–5 items, each { uri, seconds } with seconds 0–30, or { uri, at } with at 0–1 (exactly one of seconds or at per item)Optional timed guidance images placed at specific points in the source video (up to 5). Use seconds for an absolute timestamp or at for a fraction of the video duration.
content_moderationNoobject{ "public_figure_threshold": "auto" }{ "public_figure_threshold": "auto" | "low" }Content-moderation settings. Requests default to auto; set public_figure_threshold to low to be less strict about generations that include recognizable public figures.
seedNointegerrandom0–4294967295Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.

Example Request

{
  "prompt": "Edit the video to match the provided reference frame",
  "video_uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/video/input-17s.mp4",
  "prompt_images": [
    { "uri": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/images/input.jpg", "position": "first" }
  ]
}

Response

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

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYOUR_SUBSCRIPTION_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 'aleph-2' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "aleph-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "aleph-2",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

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

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/aleph-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "aleph-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "aleph-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/aleph-2_019dxxxx-xxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-04-07T10:00:00.000Z",
  "updated_at": "2026-04-07T10:02:30.000Z",
  "completed_at": "2026-04-07T10:02:30.000Z"
}

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_atstring|nullWhen 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.

Runway Aleph 2 API Pricing

Your request will cost $0.336 per second of output video.
5-second clip ≈ $1.68
2. Runway Gen-4.5

Runway Gen-4.5 API Documentation

https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/image-to-video

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

Video Generation Request - Runway gen-4.5

Request Code

POST https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/image-to-video
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows"
}
import requests

url = "https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/image-to-video"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/image-to-video';

const data = {
  prompt: 'A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows'
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_API_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/runway-gen-4-5/v1/gen-4.5/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows"
  }'

Output

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

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

HeaderRequiredDefaultDescription
X-Webhook-URLYes (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-ModeNoterminalterminal — 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": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "runway-gen-4-5",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/runway-gen-4-5_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": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "runway-gen-4-5",
  "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 - Video Generation Request

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text prompt describing the video to generate
imageNostring (URI)——Optional first-frame image URL for image-to-video mode (used as the video's first frame). If omitted, the video is generated from the text prompt only
durationNointeger55, 10Length of the generated video in seconds
aspect_ratioNostring16:9"16:9", "9:16", "4:3", "3:4", "1:1", "21:9"Aspect ratio of the output video
seedNointeger——Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.

Content Item Types & Limits

TypeMaxFormat / SizeDescription
image1JPG, PNG, WEBP · < 200 MBInput image to animate.

Example Request

{
  "prompt": "An astronaut gazes through the cupola window of a space station at the glowing curve of Earth below, soft ambient light from control panels illuminates the cabin, the camera slowly drifts forward revealing the full panoramic viewport weightless tools float gently in the background, calm and awe-inspiring cinematic atmosphere",
  "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/iss043e284928~medium.jpg",
  "duration": 10,
  "aspect_ratio": "21:9",
  "seed": 42
}

Response

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYour API subscription 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 'runway-gen-4-5' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "runway-gen-4-5",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

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

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "runway-gen-4-5",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/runway-gen-4-5_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

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_atstring|nullWhen 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.

Runway Gen-4.5 API Pricing

Your request will cost $0.12 per second of output video.
10-second clip ≈ $1.20
Text to Video

Runway Gen-4.5 API Documentation

https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/text-to-video

Authentication

All requests require an API key passed via header.

HeaderTypeRequiredDescription
Ocp-Apim-Subscription-KeystringYesYour API subscription key

Text to Video Request - Runway gen-4.5

Request Code

POST https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/text-to-video
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows"
}
import requests

url = "https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/text-to-video"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
const url = 'https://gateway.pixazo.ai/runway-gen-4-5/v1/gen-4.5/text-to-video';

const data = {
  prompt: 'A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows'
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_API_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/runway-gen-4-5/v1/gen-4.5/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A golden retriever puppy chasing butterflies through a sunlit lavender field, slow motion, cinematic depth of field, warm afternoon light casting long shadows"
  }'

Output

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

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

HeaderRequiredDefaultDescription
X-Webhook-URLYes (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-ModeNoterminalterminal — 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": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "runway-gen-4-5",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/runway-gen-4-5_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": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "runway-gen-4-5",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

  • terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
  • sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
  • Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
  • Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
  • HTTPS required — plain http:// URLs are rejected.

Request Parameters - Text to Video Request

ParameterRequiredTypeDefaultAllowed values / rangeDescription
promptYesstring——Text prompt describing the video to generate
durationNointeger55, 10Length of the generated video in seconds
aspect_ratioNostring16:9"16:9", "9:16", "4:3", "3:4", "1:1", "21:9"Aspect ratio of the output video
seedNointeger——Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.

Example Request

{
  "prompt": "An astronaut gazes through the cupola window of a space station at the glowing curve of Earth below, soft ambient light from control panels illuminates the cabin, the camera slowly drifts forward revealing the full panoramic viewport weightless tools float gently in the background, calm and awe-inspiring cinematic atmosphere",
  "duration": 10,
  "aspect_ratio": "21:9",
  "seed": 42
}

Response

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header Value
Content-Typeapplication/json
Cache-Controlno-cache
Ocp-Apim-Subscription-KeyYour API subscription 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 'runway-gen-4-5' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "runway-gen-4-5",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

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

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "runway-gen-4-5_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "runway-gen-4-5",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/runway-gen-4-5_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

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_atstring|nullWhen 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.

Runway Gen-4.5 API Pricing

Your request will cost $0.12 per second of output video.
10-second clip ≈ $1.20

⚡ 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
600last 30d
~20 per day
Success rate
83.3%
of completed generations
Generation time
3.3minavg
p95 3.5min
Requests
Oct 18max 500Nov 16
Runway Aleph 2Avg 20/day
Generation Time
Oct 18max 3.4minNov 16
Runway Aleph 2Avg 3.3min
Error Rate
Oct 18max 20.0%Nov 16
Runway Aleph 2Avg 16.7%

〰 Uptime

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

Avg. Success Rate (30d)
83.33%
across all generations of this model family
Uptime
Oct 18max 100%Nov 16
SuccessfulAvg 83.33%

Frequently Asked Questions

What is the Runway API?

Runway is an industry-leading video generation family, available through Pixazo. It includes Gen-4.5 for generating video and Aleph 2 for editing video, reachable from one endpoint.

What can Runway Gen-4.5 do?

Gen-4.5 produces cinematic video from a text prompt (text-to-video) or animates a still image (image-to-video), with the realism and motion quality Runway is known for.

What is Runway Aleph 2?

Aleph 2 is Runway's video-to-video editing model: give it a source video and a prompt and it transforms or restyles the footage, so you can edit existing clips rather than only generate new ones.

How do I call the Runway API on Pixazo?

Send one authenticated request with your Pixazo API key, then poll the job (or use a webhook) for the result. Switch between Gen-4.5 and Aleph 2 by changing the model parameter.

How much does the Runway API cost?

Runway is billed per generation with no subscription, and prices vary by model and operation. The exact per-call price is shown in the Pricing section on this page, and your first top-up earns 10% cashback.

Can I use Runway output commercially?

Yes, the API is built for production use in commercial apps. Output licensing follows Runway's terms, so confirm the provider's licensing for your use case before release.