LTX 2.3 Quality API Documentation

https://gateway.pixazo.ai/ltx-2-3-quality-text-to-video/v1/ltx-2-3-quality-text-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Quality Text to Video generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-quality-text-to-video/v1/ltx-2-3-quality-text-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic drone shot gliding over a misty mountain valley at sunrise, golden light",
  "num_frames": 121,
  "resolution": "landscape_16_9",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-quality-text-to-video/v1/ltx-2-3-quality-text-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic drone shot gliding over a misty mountain valley at sunrise, golden light",
    "num_frames": 121,
    "resolution": "landscape_16_9",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-quality-text-to-video/v1/ltx-2-3-quality-text-to-video-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "A cinematic drone shot gliding over a misty mountain valley at sunrise, golden light",
  "num_frames": 121,
  "resolution": "landscape_16_9",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
};

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/ltx-2-3-quality-text-to-video/v1/ltx-2-3-quality-text-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic drone shot gliding over a misty mountain valley at sunrise, golden light",
    "num_frames": 121,
    "resolution": "landscape_16_9",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
  }'

Output

{
  "request_id": "ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - LTX 2.3 Quality Text to Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the desired video scene. Must be detailed for best results.
num_frames	No	integer	121	9–481	Total number of frames to generate (9–481) — this sets the clip length. At the default 24 fps, 121 frames ≈ 5 seconds and 481 frames ≈ 20 seconds.
resolution	No	string or object	landscape_16_9	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9	Preset resolution or custom dimensions. Presets: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Custom object: { "width": integer, "height": integer }.
frames_per_second	No	float	24	1–60	Output frame rate. Allowed range: 1–60.
num_inference_steps	No	integer	15	8–30	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	float	1	1–20	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
generate_audio	No	boolean	true	—	Whether to generate native audio synchronized with the video.
negative_prompt	No	string	—	—	Comma-separated terms to avoid in generation (e.g., "blurry, low quality, watermark"). Defaults to a comprehensive built-in negative list.
enable_prompt_expansion	No	boolean	true	—	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_safety_checker	No	boolean	true	—	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
video_quality	No	string	high	low, medium, high, maximum	Final video encode quality. Allowed: low, medium, high, maximum.
video_write_mode	No	string	balanced	fast, balanced, small	Trade-off between encoding speed and file size. Allowed: fast, balanced, small.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	No	boolean	false	—	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Example Request

{
  "prompt": "A cinematic drone shot gliding over a misty mountain valley at sunrise, golden light",
  "num_frames": 121,
  "resolution": "landscape_16_9",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

Response

{
  "request_id": "ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-quality-text-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-quality-text-to-video",
  "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/ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-quality-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-quality-text-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-quality-text-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 Quality API Pricing

Your request will cost $0.0024 per megapixel of output.

1080p × 5s @ 24fps (~250 MP-frames) ≈ $0.60

LTX 2.3 Quality API Documentation

https://gateway.pixazo.ai/ltx-2-3-quality-image-to-video/v1/ltx-2-3-quality-image-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Quality Image to Video generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-quality-image-to-video/v1/ltx-2-3-quality-image-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Subtle cinematic camera move; the scene comes to life with gentle motion",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "image_strength": 0.7,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-quality-image-to-video/v1/ltx-2-3-quality-image-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Subtle cinematic camera move; the scene comes to life with gentle motion",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
    "num_frames": 121,
    "resolution": "auto",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "image_strength": 0.7,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-quality-image-to-video/v1/ltx-2-3-quality-image-to-video-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Subtle cinematic camera move; the scene comes to life with gentle motion",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "image_strength": 0.7,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
};

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/ltx-2-3-quality-image-to-video/v1/ltx-2-3-quality-image-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Subtle cinematic camera move; the scene comes to life with gentle motion",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
    "num_frames": 121,
    "resolution": "auto",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "image_strength": 0.7,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
  }'

Output

{
  "request_id": "ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - LTX 2.3 Quality Image to Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt guiding the video generation. Must describe motion, camera behavior, and scene evolution.
image_url	Yes	string	—	—	URL of the starting image to animate. Must be publicly accessible.
num_frames	No	integer	121	9–481	Total frames to generate — this sets the clip length. At the default 24 fps, 121 frames ≈ 5 seconds.
resolution	No	string or object	"auto"	"auto", "square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9", or custom {width, height} (max 14142 each)	Output resolution preset. Alternative: custom object with width and height.
frames_per_second	No	float	24	1–60	Output frame rate.
num_inference_steps	No	integer	15	8–30	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	float	1	1–20	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
generate_audio	No	boolean	true	—	Include native audio generated from the video content.
image_strength	No	float	0.7	0–1	Conditioning strength on the start image. 1.0 matches the first frame almost exactly; lower values give the model more freedom to depart from the source image.
negative_prompt	No	string	—	—	Terms to steer generation away from. Defaults to a comprehensive built-in negative list.
enable_prompt_expansion	No	boolean	true	—	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_safety_checker	No	boolean	true	—	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
video_quality	No	string	"high"	"low", "medium", "high", "maximum"	Final video encode quality.
video_write_mode	No	string	"balanced"	"fast", "balanced", "small"	Encoding optimization strategy.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	No	boolean	false	—	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG · < 25 MB	Input image.

Example Request

{
  "prompt": "Subtle cinematic camera move; the scene comes to life with gentle motion",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Image.jpeg",
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "image_strength": 0.7,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

Response

{
  "request_id": "ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-quality-image-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-quality-image-to-video",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

GET 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/ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-quality-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-quality-image-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-quality-image-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 Quality API Pricing

Your request will cost $0.0024 per megapixel of output.

1080p × 5s @ 24fps (~250 MP-frames) ≈ $0.60

LTX 2.3 Quality API Documentation

https://gateway.pixazo.ai/ltx-2-3-quality-audio-to-video/v1/ltx-2-3-quality-audio-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Quality Audio to Video generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-quality-audio-to-video/v1/ltx-2-3-quality-audio-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A cinematic music-video montage that matches the rhythm of the audio",
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Audio.mp3",
  "match_audio_length": true,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "image_strength": 0.7,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-quality-audio-to-video/v1/ltx-2-3-quality-audio-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A cinematic music-video montage that matches the rhythm of the audio",
    "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Audio.mp3",
    "match_audio_length": true,
    "num_frames": 121,
    "resolution": "auto",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "image_strength": 0.7,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-quality-audio-to-video/v1/ltx-2-3-quality-audio-to-video-request";

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

const data = {
  "prompt": "A cinematic music-video montage that matches the rhythm of the audio",
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Audio.mp3",
  "match_audio_length": true,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "image_strength": 0.7,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
};

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/ltx-2-3-quality-audio-to-video/v1/ltx-2-3-quality-audio-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A cinematic music-video montage that matches the rhythm of the audio",
    "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Audio.mp3",
    "match_audio_length": true,
    "num_frames": 121,
    "resolution": "auto",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "image_strength": 0.7,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
  }'

Output

{
  "request_id": "ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - LTX 2.3 Quality Audio to Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt guiding the audio-driven video generation. Must be descriptive for best results.
audio_url	Yes	string	—	—	The audio track that drives the generation. Must be in a supported format (e.g., MP3, WAV).
image_url	No	string	—	—	URL of an image to use as the first frame of the video. Must be a static image (JPEG, PNG).
image_strength	No	float	0.7	0.0–1.0	Conditioning strength for the optional first frame (image_url). 1.0 keeps the image strictly; lower values give the model more freedom.
match_audio_length	No	boolean	true	—	When true, the total frame count is automatically derived from the audio duration. When false, num_frames is used.
num_frames	No	integer	121	9–481	Total number of frames to generate — this sets the clip length (at 24 fps, 121 frames ≈ 5 seconds). Used only when match_audio_length is false.
frames_per_second	No	float	24	1.0–60.0	Output frame rate. Higher values produce smoother motion.
resolution	No	string or object	"auto"	"auto", "square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9", or {"width": integer, "height": integer}	Final output size. `auto` matches the input image's aspect ratio when image_url is provided; otherwise a landscape fallback is used. Use a preset or a custom object { "width": integer, "height": integer }.
num_inference_steps	No	integer	15	8–30	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	float	1.0	1.0–20.0	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
generate_audio	No	boolean	true	—	Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.
negative_prompt	No	string	—	—	Comma-separated terms to steer generation away from (e.g., "blurry, low quality, watermark"). Defaults to a built-in long negative list.
enable_prompt_expansion	No	boolean	true	—	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_safety_checker	No	boolean	true	—	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
video_quality	No	enum	"high"	"low", "medium", "high", "maximum"	Final video encoding quality. Higher quality increases file size and processing time.
video_write_mode	No	enum	"balanced"	"fast", "balanced", "small"	Trade-off between speed, file size, and quality. fast prioritizes speed, small minimizes file size.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	No	boolean	false	—	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Content Item Types & Limits

Type	Max	Format / Size	Description
audio	1	MP3, WAV	Driving audio.
image	1	JPG, PNG	Optional reference image.

Example Request

{
  "prompt": "A cinematic music-video montage that matches the rhythm of the audio",
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Audio.mp3",
  "match_audio_length": true,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "image_strength": 0.7,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

Response

{
  "request_id": "ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-quality-audio-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-quality-audio-to-video",
  "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/ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-quality-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-quality-audio-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-quality-audio-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 Quality API Pricing

Your request will cost $0.0024 per megapixel of output.

1080p × 5s @ 24fps (~250 MP-frames) ≈ $0.60

LTX 2.3 Quality API Documentation

https://gateway.pixazo.ai/ltx-2-3-quality-reference-video-to-video/v1/ltx-2-3-quality-reference-video-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Quality Reference Video to Video generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-quality-reference-video-to-video/v1/ltx-2-3-quality-reference-video-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Restyle the scene as a cinematic anime sequence, vivid color grading and dynamic lighting",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4",
  "video_strength": 0.6,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-quality-reference-video-to-video/v1/ltx-2-3-quality-reference-video-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Restyle the scene as a cinematic anime sequence, vivid color grading and dynamic lighting",
    "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4",
    "video_strength": 0.6,
    "num_frames": 121,
    "resolution": "auto",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-quality-reference-video-to-video/v1/ltx-2-3-quality-reference-video-to-video-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 cinematic anime sequence, vivid color grading and dynamic lighting",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4",
  "video_strength": 0.6,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
};

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/ltx-2-3-quality-reference-video-to-video/v1/ltx-2-3-quality-reference-video-to-video-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 cinematic anime sequence, vivid color grading and dynamic lighting",
    "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4",
    "video_strength": 0.6,
    "num_frames": 121,
    "resolution": "auto",
    "frames_per_second": 24,
    "num_inference_steps": 15,
    "guidance_scale": 1,
    "generate_audio": true,
    "enable_prompt_expansion": true,
    "enable_safety_checker": true,
    "video_quality": "high",
    "video_write_mode": "balanced"
}'

Output

{
  "request_id": "ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - LTX 2.3 Quality Reference Video to Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt guiding the generation. Must describe desired style, content, and aesthetic.
video_url	Yes	string	—	—	URL of the reference video that supplies motion and structural cues. Must be publicly accessible.
control_video_url	No	string	—	—	Optional pre-computed control video (for example an already-rendered depth / edge / pose composite). When provided together with skip_control_preprocess, the built-in control estimation is skipped and this video is used directly as the control signal, resampled to the output resolution and frame count.
image_url	No	string	—	—	Optional reference image for style or character anchoring. This is the FIRST-frame keyframe.
mid_image_url	No	string	—	—	Optional middle-frame keyframe image. Anchors the look and appearance around the middle of the clip (in addition to image_url at the start) so the appearance follows a moving camera instead of drifting. Requires image_url.
end_image_url	No	string	—	—	Optional last-frame keyframe image. Anchors the look and appearance at the end of the clip. Useful for shots where the camera travels to a different place than the start image. Requires image_url.
video_strength	No	float	0.6	0–1	Video conditioning strength. Lower values give the model more freedom to change the reference video's motion and structure; higher values follow the reference more closely.
strength	No	float	1	0–1	Sampler denoise strength. With preserve_original_video enabled this is the video-to-video amount: lower values keep more of the original video's pixels (e.g. 0.5 keeps roughly 50%), while 1.0 fully regenerates. Without preserve_original_video it only trims the denoise schedule.
skip_control_preprocess	No	boolean	false	—	Skip the built-in control estimation (depth / edge / pose) and use control_video_url directly as the control signal. Requires control_video_url; ignored if that is not set.
preserve_original_video	No	boolean	false	—	True video-to-video: the base video_url becomes the generation's starting point while control_video_url still drives the structure. How much of the original is preserved is controlled by strength (lower strength keeps more of the original pixels). Requires skip_control_preprocess, video_url and control_video_url.
num_frames	No	integer	121	9–481	Total frames to generate — this sets the clip length (at 24 fps, 121 frames ≈ 5 seconds). This IC-LoRA endpoint caps the resolution × frames volume for stability (~150 frames at 720p-class, more at smaller sizes). A request above the budget returns a 422 — reduce num_frames or use a smaller resolution.
resolution	No	string or object	"auto"	"auto", "square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9"	Output size of the generated video. In direct-control mode (skip_control_preprocess with control_video_url), `auto` follows the source video's size and aspect ratio up to the LTX limits, and explicit sizes are honoured with 64px alignment. In built-in control-estimation mode the output stays near the official control workflow size. Higher resolutions reduce the maximum stable frame count; lower resolutions can run longer. Alternatively provide a custom object with `width` and `height` integers.
frames_per_second	No	float	24	1–60	Output frame rate. Allowed range: 1-60.
num_inference_steps	No	integer	15	8–30	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	float	1	1–20	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
generate_audio	No	boolean	true	—	Include audio from the reference video in the output. If false, output will be silent.
negative_prompt	No	string	—	—	Terms to steer generation away from. Defaults to a comprehensive built-in negative list.
enable_prompt_expansion	No	boolean	true	—	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_safety_checker	No	boolean	true	—	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
video_quality	No	string	"high"	"low", "medium", "high", "maximum"	Output video quality tier. Allowed values: `low`, `medium`, `high`, `maximum`.
video_write_mode	No	string	"balanced"	"fast", "balanced", "small"	Output encoding strategy. Allowed values: `fast` (optimized for speed), `balanced` (default), `small` (optimized for file size).
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	No	boolean	false	—	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Content Item Types & Limits

Type	Max	Format / Size	Description
video	1	MP4, MOV, WEBM, M4V, GIF	Reference video.
image	1	JPG, PNG, WEBP	Optional reference image.

Example Request

{
  "prompt": "Restyle the scene as a cinematic anime sequence, vivid color grading and dynamic lighting",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4",
  "video_strength": 0.6,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

Response

{
  "request_id": "ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-quality-reference-video-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-quality-reference-video-to-video",
  "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/ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-quality-reference-video-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-quality-reference-video-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-quality-reference-video-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 Quality API Pricing

Your request will cost $0.0027 per megapixel of output.

1080p × 5s @ 24fps (~250 MP-frames) ≈ $0.68

LTX 2.3 Quality API Documentation

https://gateway.pixazo.ai/ltx-2-3-quality-hdr/v1/ltx-2-3-quality-hdr-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Quality HDR generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-quality-hdr/v1/ltx-2-3-quality-hdr-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "A sunset over the Pacific Ocean, vibrant orange and purple sky, deep contrast, cinematic HDR",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4"
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-quality-hdr/v1/ltx-2-3-quality-hdr-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "A sunset over the Pacific Ocean, vibrant orange and purple sky, deep contrast, cinematic HDR",
    "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4"
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-quality-hdr/v1/ltx-2-3-quality-hdr-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "A sunset over the Pacific Ocean, vibrant orange and purple sky, deep contrast, cinematic HDR",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4"
};

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/ltx-2-3-quality-hdr/v1/ltx-2-3-quality-hdr-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "A sunset over the Pacific Ocean, vibrant orange and purple sky, deep contrast, cinematic HDR",
    "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4"
  }'

Output

{
  "request_id": "ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - LTX 2.3 Quality HDR generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the desired HDR aesthetic. Must be detailed for best results.
video_url	Yes	string	—	—	URL of the SDR input video to lift into HDR. Must be publicly accessible; this mode is video-conditioned.
num_frames	No	integer	121	9–481	Total frames to generate — this sets the clip length. At the default 24 fps, 121 frames ≈ 5 seconds.
resolution	No	string or object	"auto"	auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {width: integer, height: integer}	Output video size. HDR output is generated at up to ~720p (shorter side capped at 704px); larger requested sizes are scaled down, preserving the aspect ratio. Use a preset or a custom object { "width": integer, "height": integer }.
frames_per_second	No	float	24	1–60	Output frame rate.
num_inference_steps	No	integer	15	8–30	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	float	1	1–20	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
generate_audio	No	boolean	true	—	Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track.
negative_prompt	No	string	—	—	Terms to steer generation away from. Overrides default negative list. Default negative list is long and comprehensive.
enable_prompt_expansion	No	boolean	true	—	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
enable_safety_checker	No	boolean	true	—	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
video_quality	No	string	"high"	low, medium, high, maximum	Output video quality tier.
video_write_mode	No	string	"balanced"	fast, balanced, small	Trade-off mode for video encoding.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
sync_mode	No	boolean	false	—	If on, the finished file is sent back directly instead of as a download link. Handy for quick tests; for normal use, leave it off to get a download link.

Content Item Types & Limits

Type	Max	Format / Size	Description
video	1	MP4, MOV, WEBM, M4V, GIF	Video to upscale (HDR).

Example Request

{
  "prompt": "A sunset over the Pacific Ocean, vibrant orange and purple sky, deep contrast, cinematic HDR",
  "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Video.mp4",
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced"
}

Response

{
  "request_id": "ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-quality-hdr' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-quality-hdr",
  "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/ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-quality-hdr_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-quality-hdr",
  "error": null,
  "output": {
    "preview_video": {
      "url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-quality-hdr_019dxxxx/output.mp4",
      "content_type": "video/mp4",
      "file_name": "output.mp4",
      "file_size": 12456789,
      "width": 1920,
      "height": 1080,
      "fps": 24,
      "duration": 5.04,
      "num_frames": 121
    },
    "exr_frames_url": {
      "url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-quality-hdr_019dxxxx/exr_frames.zip",
      "content_type": "application/zip",
      "file_name": "exr_frames.zip",
      "file_size": 489000000
    }
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 Quality API Pricing

Your request will cost $0.0027 per megapixel of output.

1080p × 5s @ 24fps (~250 MP-frames) ≈ $0.68

LTX 2.3 API Documentation

https://gateway.pixazo.ai/ltx-video/v1/text-to-video

Endpoint URL

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

Authentication

All requests require an API key passed via header.

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

LTX Video Text to Video request

Request Code

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

{
  "prompt": "A red rose blooming in slow motion, golden hour"
}

import requests

url = "https://gateway.pixazo.ai/ltx-video/v1/text-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A red rose blooming in slow motion, golden hour"
}

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

const url = "https://gateway.pixazo.ai/ltx-video/v1/text-to-video";
const headers = {
  "Content-Type": "application/json",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  "prompt": "A red rose blooming in slow motion, golden hour"
};

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/ltx-video/v1/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A red rose blooming in slow motion, golden hour"
  }'

Output

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your request to receive a POST callback instead of polling. The webhook payload mirrors the status-endpoint response. Optionally add X-Webhook-Mode: sync to also receive a progress webhook on every poll cycle (roughly every 20s) while the request is still in flight, in addition to the terminal callback.

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: sync

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Description
X-Webhook-URL	No	HTTPS URL that receives a POST callback when the request reaches a terminal state.
X-Webhook-Mode	No	`terminal` (default) fires once on COMPLETED/FAILED/ERROR. `sync` also fires a progress webhook each poll cycle (~20s cadence).

Request Parameters - LTX Video Text to Video request

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	≤ 4000 chars	Text description of the video to generate.
`seed`	No	integer	42	—	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.
`aspect`	No	string	"auto"	16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 4:5, 2:3, 3:2, or custom W:H	Output aspect ratio; overrides width/height.
`width`	No	integer	1280	divisible by 32, ≤ 1920	Output width; overridden by aspect.
`height`	No	integer	704	divisible by 32, ≤ 1088	Output height; overridden by aspect.
`num_frames`	No	integer	121	8k+1 form, max 241	Number of frames (e.g. 121, 161, 241).
`frame_rate`	No	float	24	1–60	Frames per second.
`enhance_prompt`	No	boolean	false	true/false	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.

Example Request

{
  "prompt": "A red rose blooming in slow motion, golden hour"
}

Response

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-video",
  "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_SUBSCRIPTION_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-08T10:00:00.000Z",
  "completed_at": "2026-06-08T10:00:30.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output (video/mp4)
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 API Pricing

Your request is Free

LTX 2.3 base — free during preview, fair-use rate limit applies.

LTX 2.3 API Documentation

https://gateway.pixazo.ai/ltx-video/v1/image-to-video

Endpoint URL

POST https://gateway.pixazo.ai/ltx-video/v1/image-to-video

Authentication

All requests require an API key passed via header.

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

LTX Video Image to Video request

Request Code

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

{
  "prompt": "Hands dance gracefully, rose petals drift",
  "image_url": "https://example.com/hands.jpg"
}

import requests

url = "https://gateway.pixazo.ai/ltx-video/v1/image-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Hands dance gracefully, rose petals drift",
    "image_url": "https://example.com/hands.jpg"
}

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

const url = "https://gateway.pixazo.ai/ltx-video/v1/image-to-video";
const headers = {
  "Content-Type": "application/json",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  "prompt": "Hands dance gracefully, rose petals drift",
  "image_url": "https://example.com/hands.jpg"
};

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/ltx-video/v1/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Hands dance gracefully, rose petals drift",
    "image_url": "https://example.com/hands.jpg"
  }'

Output

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your request to receive a POST callback instead of polling. The webhook payload mirrors the status-endpoint response. Optionally add X-Webhook-Mode: sync to also receive a progress webhook on every poll cycle (roughly every 20s) while the request is still in flight, in addition to the terminal callback.

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: sync

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Description
X-Webhook-URL	No	HTTPS URL that receives a POST callback when the request reaches a terminal state.
X-Webhook-Mode	No	`terminal` (default) fires once on COMPLETED/FAILED/ERROR. `sync` also fires a progress webhook each poll cycle (~20s cadence).

Request Parameters - LTX Video Image to Video request

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	≤ 4000 chars	Text description of the video to generate.
`image_url`	Yes	string	—	public https URL, ≤ 25MB	Source image to animate.
`strength`	No	float	1.0	0–1	How much the result may differ from the input. Higher values allow bigger changes from the source; lower values keep the output closer to the original.
`seed`	No	integer	42	—	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.
`aspect`	No	string	"auto"	16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 4:5, 2:3, 3:2, or custom W:H	Output aspect ratio; overrides width/height.
`width`	No	integer	1280	divisible by 32, ≤ 1920	Output width; overridden by aspect.
`height`	No	integer	704	divisible by 32, ≤ 1088	Output height; overridden by aspect.
`num_frames`	No	integer	121	8k+1 form, max 241	Number of frames (e.g. 121, 161, 241).
`frame_rate`	No	float	24	1–60	Frames per second.
`enhance_prompt`	No	boolean	false	true/false	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Input image.

Example Request

{
  "prompt": "Hands dance gracefully, rose petals drift",
  "image_url": "https://example.com/hands.jpg"
}

Response

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-video",
  "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_SUBSCRIPTION_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-08T10:00:00.000Z",
  "completed_at": "2026-06-08T10:00:30.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output (video/mp4)
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 API Pricing

Your request is Free

LTX 2.3 base — free during preview, fair-use rate limit applies.

LTX 2.3 API Documentation

https://gateway.pixazo.ai/ltx-video/v1/video-to-video

Endpoint URL

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

Authentication

All requests require an API key passed via header.

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

LTX Video Video to Video request

Request Code

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

{
  "prompt": "Anime Studio Ghibli style, vibrant watercolor",
  "video_url": "https://example.com/source.mp4",
  "aspect": "16:9"
}

import requests

url = "https://gateway.pixazo.ai/ltx-video/v1/video-to-video"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Anime Studio Ghibli style, vibrant watercolor",
    "video_url": "https://example.com/source.mp4",
    "aspect": "16:9"
}

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

const url = "https://gateway.pixazo.ai/ltx-video/v1/video-to-video";
const headers = {
  "Content-Type": "application/json",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  "prompt": "Anime Studio Ghibli style, vibrant watercolor",
  "video_url": "https://example.com/source.mp4",
  "aspect": "16:9"
};

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/ltx-video/v1/video-to-video" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Anime Studio Ghibli style, vibrant watercolor",
    "video_url": "https://example.com/source.mp4",
    "aspect": "16:9"
  }'

Output

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your request to receive a POST callback instead of polling. The webhook payload mirrors the status-endpoint response. Optionally add X-Webhook-Mode: sync to also receive a progress webhook on every poll cycle (roughly every 20s) while the request is still in flight, in addition to the terminal callback.

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: sync

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Description
X-Webhook-URL	No	HTTPS URL that receives a POST callback when the request reaches a terminal state.
X-Webhook-Mode	No	`terminal` (default) fires once on COMPLETED/FAILED/ERROR. `sync` also fires a progress webhook each poll cycle (~20s cadence).

Request Parameters - LTX Video Video to Video request

Parameter	Required	Type	Default	Allowed values / range	Description
`prompt`	Yes	string	—	≤ 4000 chars	Transformation instruction.
`video_url`	Yes	string	—	public https URL, ≤ 100MB	Source video to transform.
`seed`	No	integer	42	—	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.
`aspect`	No	string	—	16:9 (1280×768), 9:16 (768×1280), 1:1 (960×960), 4:3, 3:4	Output aspect ratio.
`width`	No	integer	1280	divisible by 64, ≤ 1920	Output width (v2v requires div-by-64).
`height`	No	integer	768	divisible by 64, ≤ 1088	Output height (v2v requires div-by-64).
`num_frames`	No	integer	121	8k+1 form, max 241	Number of frames.
`frame_rate`	No	float	24	1–60	Frames per second.
`video_strength`	No	float	1.0	0–1	How much the result may differ from the input. Higher values allow bigger changes from the source; lower values keep the output closer to the original.
`skip_stage_2`	No	boolean	false	true/false	Skip upscale → half-res, faster.

Content Item Types & Limits

Type	Max	Format / Size	Description
video	1	MP4, MOV, WEBM	Source video.

Example Request

{
  "prompt": "Anime Studio Ghibli style, vibrant watercolor",
  "video_url": "https://example.com/source.mp4",
  "aspect": "16:9"
}

Response

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-video",
  "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_SUBSCRIPTION_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-08T10:00:00.000Z",
  "completed_at": "2026-06-08T10:00:30.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output (video/mp4)
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX 2.3 API Pricing

Your request is Free

LTX 2.3 base — free during preview, fair-use rate limit applies.

LTX v2.3 API Documentation

https://gateway.pixazo.ai/ltx-2-3-text-to-video/v1/ltx-2-3-text-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX-2.3 (Text to Video) generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-text-to-video/v1/ltx-2-3-text-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Through-the-veil shot of a bride face during an Indian wedding ceremony, embroidered red dupatta texture, eyes lined with kohl, henna-covered hands, marigold garlands in soft bokeh, 85mm f/1.2, warm tungsten and candlelight, cinematic intimacy",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "fps": 25,
  "generate_audio": true
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-text-to-video/v1/ltx-2-3-text-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Through-the-veil shot of a bride face during an Indian wedding ceremony, embroidered red dupatta texture, eyes lined with kohl, henna-covered hands, marigold garlands in soft bokeh, 85mm f/1.2, warm tungsten and candlelight, cinematic intimacy",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "fps": 25,
    "generate_audio": true
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-text-to-video/v1/ltx-2-3-text-to-video-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "prompt": "Through-the-veil shot of a bride face during an Indian wedding ceremony, embroidered red dupatta texture, eyes lined with kohl, henna-covered hands, marigold garlands in soft bokeh, 85mm f/1.2, warm tungsten and candlelight, cinematic intimacy",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "fps": 25,
  "generate_audio": true
};

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/ltx-2-3-text-to-video/v1/ltx-2-3-text-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Through-the-veil shot of a bride face during an Indian wedding ceremony, embroidered red dupatta texture, eyes lined with kohl, henna-covered hands, marigold garlands in soft bokeh, 85mm f/1.2, warm tungsten and candlelight, cinematic intimacy",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "fps": 25,
    "generate_audio": true
  }'

Output

{
  "request_id": "ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-text-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-text-to-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

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

Request Parameters - LTX-2.3 (Text to Video) generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description for video generation. Must be detailed and descriptive for optimal results.
duration	No	enum	6	6, 8, 10	Duration of the generated video in seconds.
resolution	No	enum	1080p	1080p, 1440p, 2160p	Output video resolution.
aspect_ratio	No	enum	16:9	16:9, 9:16	Video aspect ratio.
fps	No	enum	25	24, 25, 48, 50	Frames per second of the output video.
generate_audio	No	boolean	true	—	Whether to generate synchronized audio for the video. When set to false, output will be silent.

Example Request

{
  "prompt": "Through-the-veil shot of a bride face during an Indian wedding ceremony, embroidered red dupatta texture, eyes lined with kohl, henna-covered hands, marigold garlands in soft bokeh, 85mm f/1.2, warm tungsten and candlelight, cinematic intimacy",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "fps": 25,
  "generate_audio": true
}

Response

{
  "request_id": "ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-text-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-text-to-video",
  "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/ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-text-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-text-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-text-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2.3 API Pricing

Resolution	Price (USD)
1080p / per second	$0.06
1440p / per second	$0.12
2160p (4K) / per second	$0.24

5-second 1080p clip ≈ $0.30

LTX v2.3 API Documentation

https://gateway.pixazo.ai/ltx-2-3-image-to-video/v1/ltx-2-3-image-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX-2.3 (Image to Video) generate request

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-image-to-video/v1/ltx-2-3-image-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "image_url": "https://v3b.example.com/files/b/0a90dd31/uJG2pMMJMcnVeC4PmwnAF_image_004.png",
  "prompt": "Periscope-level shot of two Maasai warriors mid-leap during an adumu jumping dance, golden savanna sunset, red shuka robes frozen in motion, dust kicked up catching backlight, 85mm f/1.4",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "auto",
  "fps": 25,
  "generate_audio": true
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-image-to-video/v1/ltx-2-3-image-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "image_url": "https://v3b.example.com/files/b/0a90dd31/uJG2pMMJMcnVeC4PmwnAF_image_004.png",
    "prompt": "Periscope-level shot of two Maasai warriors mid-leap during an adumu jumping dance, golden savanna sunset, red shuka robes frozen in motion, dust kicked up catching backlight, 85mm f/1.4",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "auto",
    "fps": 25,
    "generate_audio": true
}

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

fetch("https://gateway.pixazo.ai/ltx-2-3-image-to-video/v1/ltx-2-3-image-to-video-request", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
  },
  body: JSON.stringify({
    "image_url": "https://v3b.example.com/files/b/0a90dd31/uJG2pMMJMcnVeC4PmwnAF_image_004.png",
    "prompt": "Periscope-level shot of two Maasai warriors mid-leap during an adumu jumping dance, golden savanna sunset, red shuka robes frozen in motion, dust kicked up catching backlight, 85mm f/1.4",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "auto",
    "fps": 25,
    "generate_audio": true
  })
})
  .then(response => response.json())
  .then(data => console.log(data));

curl -X POST "https://gateway.pixazo.ai/ltx-2-3-image-to-video/v1/ltx-2-3-image-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "image_url": "https://v3b.example.com/files/b/0a90dd31/uJG2pMMJMcnVeC4PmwnAF_image_004.png",
    "prompt": "Periscope-level shot of two Maasai warriors mid-leap during an adumu jumping dance, golden savanna sunset, red shuka robes frozen in motion, dust kicked up catching backlight, 85mm f/1.4",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "auto",
    "fps": 25,
    "generate_audio": true
  }'

Output

{
  "request_id": "ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-image-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-image-to-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

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

Request Parameters - LTX-2.3 (Image to Video) generate request

Parameter	Required	Type	Default	Allowed values / range	Description
image_url	Yes	string	—	—	URL of the start image to use for the generated video. Must be publicly accessible.
end_image_url	No	string	—	—	URL of an end image. When provided, generates a transition video between start and end frames. Must be publicly accessible.
prompt	Yes	string	—	—	Text prompt describing the desired motion, style, and scene details for the generated video.
duration	No	enum	6	6, 8, 10	Duration of the output video in seconds.
resolution	No	enum	1080p	1080p, 1440p, 2160p	Output video resolution.
aspect_ratio	No	enum	auto	auto, 16:9, 9:16	Aspect ratio of the output video. If auto, the ratio is inferred from the input image.
fps	No	enum	25	24, 25, 48, 50	Frames per second of the output video.
generate_audio	No	boolean	true	—	Whether to generate synchronized audio for the video. If false, output will be silent.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG · < 25 MB	First / last frame image.

Example Request

{
  "image_url": "https://v3b.example.com/files/b/0a90dd31/uJG2pMMJMcnVeC4PmwnAF_image_004.png",
  "prompt": "Periscope-level shot of two Maasai warriors mid-leap during an adumu jumping dance, golden savanna sunset, red shuka robes frozen in motion, dust kicked up catching backlight, 85mm f/1.4",
  "duration": 6,
  "resolution": "1080p",
  "aspect_ratio": "auto",
  "fps": 25,
  "generate_audio": true
}

Response

{
  "request_id": "ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-image-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-image-to-video",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

GET 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/ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-image-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-image-to-video",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-image-to-video_019dxxxx/output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2.3 API Pricing

Resolution	Price (USD)
1080p / per second	$0.06
1440p / per second	$0.12
2160p (4K) / per second	$0.24

5-second 1080p clip ≈ $0.30

LTX v2.3 API Documentation

https://gateway.pixazo.ai/ltx-2-3-audio-to-video/v1/ltx-2-3-audio-to-video-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Audio to Video generate request - LTX 2.3 Audio to Video

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-audio-to-video/v1/ltx-2-3-audio-to-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A musician passionately playing piano in a dimly lit jazz club",
  "audio_url": "https://imagesai.appypie.com/7686410/wGrZmX6DC6QbKdp73zyK_017727945871303.mp3",
  "image_url": "https://imagesai.appypie.com/7686410/PaESYuZM3mrXtc08U2vh_017731442751326.png",
  "guidance_scale": 9
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-audio-to-video/v1/ltx-2-3-audio-to-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A musician passionately playing piano in a dimly lit jazz club",
    "audio_url": "https://imagesai.appypie.com/7686410/wGrZmX6DC6QbKdp73zyK_017727945871303.mp3",
    "image_url": "https://imagesai.appypie.com/7686410/PaESYuZM3mrXtc08U2vh_017731442751326.png",
    "guidance_scale": 9
}

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

const url = "https://gateway.pixazo.ai/ltx-2-3-audio-to-video/v1/ltx-2-3-audio-to-video-request";

const data = {
  prompt: "A musician passionately playing piano in a dimly lit jazz club",
  audio_url: "https://imagesai.appypie.com/7686410/wGrZmX6DC6QbKdp73zyK_017727945871303.mp3",
  image_url: "https://imagesai.appypie.com/7686410/PaESYuZM3mrXtc08U2vh_017731442751326.png",
  guidance_scale: 9
};

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

curl -X POST "https://gateway.pixazo.ai/ltx-2-3-audio-to-video/v1/ltx-2-3-audio-to-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A musician passionately playing piano in a dimly lit jazz club",
    "audio_url": "https://imagesai.appypie.com/7686410/wGrZmX6DC6QbKdp73zyK_017727945871303.mp3",
    "image_url": "https://imagesai.appypie.com/7686410/PaESYuZM3mrXtc08U2vh_017731442751326.png",
    "guidance_scale": 9
}'

Output

{
  "request_id": "ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-audio-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-audio-to-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

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

Request Parameters - LTX 2.3 Audio to Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
audio_url	Yes	string	—	2-20 seconds	Publicly accessible URL (or base64 data URI) of the audio file to generate the video from. The audio duration must be between 2 and 20 seconds and drives the length and timing of the output video.
prompt	No	string	—	1-5000 characters	Text description of how the video should be generated. Required if image_url is not provided; when image_url is supplied, it describes how that image should be animated.
image_url	No	string	—	—	URL of an image to use as the first frame of the video. Required if prompt is not provided.
aspect_ratio	No	enum	auto	auto, 16:9, 9:16	Aspect ratio of the generated video. With auto, the ratio is inferred from the input image, or defaults to 16:9 when no image is provided.
guidance_scale	No	number	5 (9 with image_url)	1-50	Controls how closely the output follows the prompt. Higher values follow the prompt more strictly; lower values allow more creative variation. Defaults to 5 for prompt-only generation, or 9 when an image_url is provided.

Content Item Types & Limits

Type	Max	Format / Size	Description
audio	1	MP3, WAV	Driving audio.
image	1	JPG, PNG	Optional reference image.

Minimum Request

{
  "prompt": "A musician passionately playing piano in a dimly lit jazz club",
  "audio_url": "https://imagesai.appypie.com/7686410/wGrZmX6DC6QbKdp73zyK_017727945871303.mp3"
}

Full Request (all options)

{
  "prompt": "A musician passionately playing piano in a dimly lit jazz club",
  "audio_url": "https://imagesai.appypie.com/7686410/wGrZmX6DC6QbKdp73zyK_017727945871303.mp3",
  "image_url": "https://imagesai.appypie.com/7686410/PaESYuZM3mrXtc08U2vh_017731442751326.png",
  "guidance_scale": 9
}

Response

{
  "request_id": "ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for LTX 2.3 Audio to Video generate request.

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

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-audio-to-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-audio-to-video",
  "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/ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-audio-to-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-audio-to-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-audio-to-video_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2.3 API Pricing

Resolution	Price (USD)
All Resolution / per second	$0.10

LTX v2.3 API Documentation

https://gateway.pixazo.ai/ltx-2-3-retake-video/v1/ltx-2-3-retake-video-request

Authentication

All requests require an API key passed via header.

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

LTX 2.3 Retake Video generate request - LTX 2.3 Retake Video

Request Code

POST https://gateway.pixazo.ai/ltx-2-3-retake-video/v1/ltx-2-3-retake-video-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Transform the scene into a vibrant neon-lit cyberpunk environment",
  "video_url": "https://imagesai.appypie.com/7686410/HjRiOy5cjxaM5YMXUY5U_017731482701572.mp4",
  "start_time": 0,
  "duration": 5,
  "retake_mode": "replace_audio_and_video"
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-3-retake-video/v1/ltx-2-3-retake-video-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Transform the scene into a vibrant neon-lit cyberpunk environment",
    "video_url": "https://imagesai.appypie.com/7686410/HjRiOy5cjxaM5YMXUY5U_017731482701572.mp4",
    "start_time": 0,
    "duration": 5,
    "retake_mode": "replace_audio_and_video"
}

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

const url = 'https://gateway.pixazo.ai/ltx-2-3-retake-video/v1/ltx-2-3-retake-video-request';

const data = {
  prompt: 'Transform the scene into a vibrant neon-lit cyberpunk environment',
  video_url: 'https://imagesai.appypie.com/7686410/HjRiOy5cjxaM5YMXUY5U_017731482701572.mp4',
  start_time: 0,
  duration: 5,
  retake_mode: 'replace_audio_and_video'
};

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

curl -X POST "https://gateway.pixazo.ai/ltx-2-3-retake-video/v1/ltx-2-3-retake-video-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Transform the scene into a vibrant neon-lit cyberpunk environment",
    "video_url": "https://imagesai.appypie.com/7686410/HjRiOy5cjxaM5YMXUY5U_017731482701572.mp4",
    "start_time": 0,
    "duration": 5,
    "retake_mode": "replace_audio_and_video"
  }'

Output

{
  "request_id": "ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-retake-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-retake-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

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

Request Parameters - LTX 2.3 Retake Video generate request

Parameter	Required	Type	Default	Allowed values / range	Description
video_url	Yes	string	—	—	Publicly accessible URL of the source video to retake.
prompt	Yes	string	—	1-5000 characters	Text description of the change to apply to the selected segment (for example: Change flower to red rose).
start_time	No	number	0	0-20	Start time, in seconds, of the video segment to retake.
duration	No	number	5	2-20	Duration, in seconds, of the video segment to retake.
retake_mode	No	enum	replace_audio_and_video	replace_audio, replace_video, replace_audio_and_video	Which tracks of the selected segment are regenerated: audio only, video only, or both.

Content Item Types & Limits

Type	Max	Format / Size	Description
video	1	MP4, MOV, WEBM, M4V, GIF	Video to retake.

Minimum Request

{
  "prompt": "Transform the scene into a vibrant neon-lit cyberpunk environment",
  "video_url": "https://imagesai.appypie.com/7686410/HjRiOy5cjxaM5YMXUY5U_017731482701572.mp4",
  "start_time": 0,
  "duration": 5,
  "retake_mode": "replace_audio_and_video"
}

Full Request (all options)

{
  "prompt": "Transform the scene into a vibrant neon-lit cyberpunk environment",
  "video_url": "https://imagesai.appypie.com/7686410/HjRiOy5cjxaM5YMXUY5U_017731482701572.mp4",
  "start_time": 0,
  "duration": 5,
  "retake_mode": "replace_audio_and_video"
}

Response

{
  "request_id": "ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes for LTX 2.3 Retake Video generate request.

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

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-3-retake-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-3-retake-video",
  "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/ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-3-retake-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-3-retake-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-3-retake-video_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2.3 API Pricing

Resolution	Price (USD)
All Resolution / per second	$0.10

LTX v2 Pro API Documentation

https://gateway.pixazo.ai/lightricks/v1/ltx/generate

Authentication

All requests require an API key passed via header.

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

LTX V2 Video Generate - LTX V2 Pro

Request Code

POST https://gateway.pixazo.ai/lightricks/v1/ltx/generate HTTP/1.1

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

{
    "prompt": "A cinematic drone shot of a futuristic city at night with flying cars and neon lights",
    "duration": 10,
    "resolution": "1080p",
    "generate_audio": true
}

import requests
import json

url = "https://gateway.pixazo.ai/lightricks/v1/ltx/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A cinematic drone shot of a futuristic city at night with flying cars and neon lights",
    "duration": 10,
    "resolution": "1080p",
    "generate_audio": True
}

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

const url = 'https://gateway.pixazo.ai/lightricks/v1/ltx/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};

const body = {
  prompt: 'A cinematic drone shot of a futuristic city at night with flying cars and neon lights',
  duration: 10,
  resolution: '1080p',
  generate_audio: true
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(body)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/lightricks/v1/ltx/generate" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
    "prompt": "A cinematic drone shot of a futuristic city at night with flying cars and neon lights",
    "duration": 10,
    "resolution": "1080p",
    "generate_audio": true
}'

Output

{
  "request_id": "lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "lightricks-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lightricks-video",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

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

Request Parameters - LTX V2 Video Generate

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text prompt describing the video to generate. Be specific and descriptive (subject, action, camera movement, lighting) for best results.
image	No	string	—	—	First frame image for image-to-video generation. Must be a publicly accessible URL (JPG, PNG or WEBP). Omit it for text-to-video.
duration	No	integer	6	6, 8, 10	Duration of the generated video in seconds.
resolution	No	string	1080p	1080p, 2k, 4k	Resolution quality of the generated video. Use 2k / 4k — the values 1440p and 2160p are not accepted.
generate_audio	No	boolean	true	true, false	Generate synchronized audio for the video. Applies to text-to-video and image-to-video (audio is preview quality).
webhook	No	string	—	—	Callback URL for completion notification.
webhook_events_filter	No	array	["*"]	—	Events that trigger webhook. Valid values: ["*"] (all), ["completed"] (success/failure only)

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Input image.

Minimum Request

{
  "prompt": "A serene mountain landscape at sunset with clouds moving slowly across the sky"
}

Full Request (all options)

{
  "prompt": "A cinematic drone shot of a futuristic city at night with flying cars and neon lights",
  "image": "https://example.com/input-photo.jpg",
  "duration": 10,
  "resolution": "2160p",
  "generate_audio": true,
  "webhook": "https://yourdomain.com/webhook",
  "webhook_events_filter": [
    "*"
  ]
}

Response

{
  "request_id": "lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for LTX V2 Video Generate.

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

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'lightricks-video' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lightricks-video",
  "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/lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "lightricks-video_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "lightricks-video",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lightricks-video_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2 Pro API Pricing

Resolution	Price (USD)
1080p	$0.06 per second
1440p	$0.12 per second
2160p	$0.24 per second

Example total for a 10s video: 1080p $0.60 · 1440p $1.20 · 2160p $2.40

Valid durations: 6s, 8s, 10s

5-second 1080p clip ≈ $0.30

LTX v2 19B API Documentation

https://gateway.pixazo.ai/ltx-2-19b-api-513/v1/ltx-2-19b-api-request

Authentication

All requests require an API key passed via header.

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

LTX-2 19B API generate request - LTX-2 19B API

Request Code

POST https://gateway.pixazo.ai/ltx-2-19b-api-513/v1/ltx-2-19b-api-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A golden retriever running through a sunlit forest, tail wagging, leaves blowing in the wind",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana.jpeg",
  "num_frames": 121,
  "video_size": "auto",
  "generate_audio": true,
  "use_multiscale": true,
  "fps": 25,
  "acceleration": "none",
  "camera_lora": "none",
  "camera_lora_scale": 1,
  "negative_prompt": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.",
  "enable_safety_checker": true,
  "video_output_type": "X264 (.mp4)",
  "video_quality": "high",
  "video_write_mode": "balanced"
}

import requests
import json

url = "https://gateway.pixazo.ai/ltx-2-19b-api-513/v1/ltx-2-19b-api-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A golden retriever running through a sunlit forest, tail wagging, leaves blowing in the wind",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana.jpeg",
    "num_frames": 121,
    "video_size": "auto",
    "generate_audio": true,
    "use_multiscale": true,
    "fps": 25,
    "acceleration": "none",
    "camera_lora": "none",
    "camera_lora_scale": 1,
    "negative_prompt": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.",
    "enable_safety_checker": true,
    "video_output_type": "X264 (.mp4)",
    "video_quality": "high",
    "video_write_mode": "balanced"
}

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

const url = 'https://gateway.pixazo.ai/ltx-2-19b-api-513/v1/ltx-2-19b-api-request';

const data = {
  prompt: 'A golden retriever running through a sunlit forest, tail wagging, leaves blowing in the wind',
  image_url: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana.jpeg',
  num_frames: 121,
  video_size: 'auto',
  generate_audio: true,
  use_multiscale: true,
  fps: 25,
  acceleration: 'none',
  camera_lora: 'none',
  camera_lora_scale: 1,
  negative_prompt: 'blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.',
  enable_safety_checker: true,
  video_output_type: 'X264 (.mp4)',
  video_quality: 'high',
  video_write_mode: 'balanced'
};

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

curl -X POST "https://gateway.pixazo.ai/ltx-2-19b-api-513/v1/ltx-2-19b-api-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A golden retriever running through a sunlit forest, tail wagging, leaves blowing in the wind",
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana.jpeg",
    "num_frames": 121,
    "video_size": "auto",
    "generate_audio": true,
    "use_multiscale": true,
    "fps": 25,
    "acceleration": "none",
    "camera_lora": "none",
    "camera_lora_scale": 1,
    "negative_prompt": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.",
    "enable_safety_checker": true,
    "video_output_type": "X264 (.mp4)",
    "video_quality": "high",
    "video_write_mode": "balanced"
  }'

Output

{
  "request_id": "ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-19b-api-513",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-19b-api-513_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": "ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-19b-api-513",
  "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 - LTX-2 19B API generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	Text description guiding the video: subject, action, style, and camera or scene context.
image_url	Yes	string	—	—	Publicly accessible URL of the input image to animate. It becomes the first frame of the video.
end_image_url	No	string	—	—	Optional URL of an image to use as the video's final frame. The model interpolates from image_url to this frame.
num_frames	No	integer	121	9 - 481	Number of frames to generate. At the default 25 fps, 121 frames is about 4.8 seconds of video.
video_size	No	string or object	auto	auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or {"width": W, "height": H}	Size of the output video. "auto" derives it from the input image. Pass an object such as {"width": 1280, "height": 720} for a custom size (max 14142 per side).
generate_audio	No	boolean	true	true, false	Whether to generate a synchronized audio track for the video. Disable it to shorten generation time.
use_multiscale	No	boolean	true	true, false	Renders a smaller pass first and uses it to guide the full-size render, improving coherence and detail.
fps	No	number	25	1 - 60	Frames per second of the output video. Higher values give smoother motion.
acceleration	No	string	none	none, regular, high, full	Speed vs. quality trade-off for the render. Higher acceleration is faster but can reduce quality.
camera_lora	No	string	none	dolly_in, dolly_out, dolly_left, dolly_right, jib_up, jib_down, static, none	Applies a camera-movement LoRA. Gives more reliable camera control than describing the move in the prompt.
camera_lora_scale	No	number	1	0 - 1	Strength of the selected camera LoRA. Lower values soften the camera movement.
negative_prompt	No	string	Preset quality-defect list	—	Description of artifacts and qualities to avoid. If omitted, a detailed default (blur, noise, distortion, etc.) is applied.
seed	No	integer	—	—	Seed for the random number generator. Reuse the same seed with the same input to reproduce a result.
enable_prompt_expansion	No	boolean	true	true, false	Automatically enriches a short prompt with extra detail before generation.
enable_safety_checker	No	boolean	true	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
video_output_type	No	string	X264 (.mp4)	X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif)	Container and codec of the output video file.
video_quality	No	string	high	low, medium, high, maximum	Output quality level. Higher quality increases file size and processing time.
video_write_mode	No	string	balanced	fast, balanced, small	Encoder trade-off: "fast" encodes quickest, "small" produces the smallest file, "balanced" sits between the two.
image_strength	No	number	1	0 - 1	How strongly the input image constrains the video. Lower values let the model deviate further from it.
end_image_strength	No	number	1	0 - 1	How strongly end_image_url constrains the final frame.
interpolation_direction	No	string	forward	forward, backward	With end_image_url set, whether to interpolate from the start image to the end image ("forward") or in reverse ("backward").

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Input image.

Example Request

{
  "prompt": "A golden retriever running through a sunlit forest, tail wagging, leaves blowing in the wind",
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/nano-banana.jpeg",
  "num_frames": 121,
  "video_size": "auto",
  "generate_audio": true,
  "use_multiscale": true,
  "fps": 25,
  "acceleration": "none",
  "camera_lora": "none",
  "camera_lora_scale": 1,
  "negative_prompt": "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.",
  "enable_safety_checker": true,
  "video_output_type": "X264 (.mp4)",
  "video_quality": "high",
  "video_write_mode": "balanced"
}

Response

{
  "request_id": "ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

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

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-19b-api-513' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-19b-api-513",
  "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/ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-19b-api-513_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-19b-api-513",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-19b-api-513_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2 19B API Pricing

Your request will cost $0.0896 per second.

5-second clip ≈ $0.45

LTX v2 API Documentation

https://gateway.pixazo.ai/ltx-2-video-api-581/v1/ltx-2-video-api-request

Authentication

All requests require an API key passed via header.

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

LTX-2 Video API generate request - LTX-2 Video API

Request Code

POST https://gateway.pixazo.ai/ltx-2-video-api-581/v1/ltx-2-video-api-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_url": "https://example.com/example_inputs/ltxv-2-i2v-input.jpg",
  "prompt": "A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket."
}

import requests

url = "https://gateway.pixazo.ai/ltx-2-video-api-581/v1/ltx-2-video-api-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_url": "https://example.com/example_inputs/ltxv-2-i2v-input.jpg",
    "prompt": "A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket."
}

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

const url = "https://gateway.pixazo.ai/ltx-2-video-api-581/v1/ltx-2-video-api-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  "image_url": "https://example.com/example_inputs/ltxv-2-i2v-input.jpg",
  "prompt": "A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket."
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error("Error:", error));

curl -X POST "https://gateway.pixazo.ai/ltx-2-video-api-581/v1/ltx-2-video-api-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image_url": "https://example.com/example_inputs/ltxv-2-i2v-input.jpg",
    "prompt": "A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket."
  }'

Output

{
  "request_id": "ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-video-api-581",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-video-api-581_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": "ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-video-api-581",
  "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 - LTX-2 Video API generate request

Parameter	Required	Type	Default	Allowed values / range	Description
image_url	Yes	string	—	PNG, JPEG, WebP, AVIF, HEIF	Public URL (or base64 data URI) of the input image the video is generated from. Must be reachable by the service.
prompt	Yes	string	—	—	Detailed textual description of the desired motion, camera movement, and visual context for the generated video.
duration	No	integer	6	6, 8, 10	Duration of the generated video in seconds.
resolution	No	string	1080p	1080p, 1440p, 2160p	Resolution of the generated video.
fps	No	integer	25	25, 50	Frames per second of the generated video.
generate_audio	No	boolean	true	true, false	Whether to generate synchronized audio for the generated video.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP	Input image.

Minimum Request

{
  "image_url": "https://example.com/example_inputs/ltxv-2-i2v-input.jpg",
  "prompt": "A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket."
}

Full Request (all options)

{
  "image_url": "https://example.com/example_inputs/ltxv-2-i2v-input.jpg",
  "prompt": "A woman stands still amid a busy neon-lit street at night. The camera slowly dollies in toward her face as people blur past, their motion emphasizing her calm presence. City lights flicker and reflections shift across her denim jacket.",
  "duration": 6,
  "resolution": "1080p",
  "fps": 25,
  "generate_audio": true
}

Response

{
  "request_id": "ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for LTX-2 Video API generate request.

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

Error Responses

Queue system errors and model validation errors.

Queue System Errors

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

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ltx-2-video-api-581' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ltx-2-video-api-581",
  "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/ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ltx-2-video-api-581_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ltx-2-video-api-581",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ltx-2-video-api-581_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

LTX v2 API Pricing

Resolution	Price (USD)
1080p	$0.06 per second
1440p	$0.12 per second
2160p	$0.24 per second

5-second 1080p clip ≈ $0.30

LTX 2.3 Quality API, LTX 2.3 (FREE) API, LTX 2.3, 2 Pro API: Pricing, Documentation

Models Version

Get $5 Free Credit on First Payment

LTX 2.3 Quality API Documentation

Authentication

LTX 2.3 Quality Text to Video generate request

Request Code

Output

Webhook (Optional)

Request Parameters - LTX 2.3 Quality Text to Video generate request

Example Request

Response

Request Headers

Response Handling

Error Responses

Queue System Errors

Error via Status/Webhook

Retrieving Results

Endpoint

cURL Example

Response (Completed)

Response Fields

Status Values

Status Flow

Typical Workflow

LTX 2.3 Quality API Pricing

LTX 2.3 Quality API Documentation

Authentication

LTX 2.3 Quality Image to Video generate request

Request Code

Output

Webhook (Optional)

Request Parameters - LTX 2.3 Quality Image to Video generate request

Content Item Types & Limits

Example Request

Response

Request Headers

Response Handling

Error Responses

Queue System Errors

Error via Status/Webhook

Retrieving Results

Endpoint

cURL Example

Response (Completed)

Response Fields

Status Values

Status Flow

Typical Workflow

LTX 2.3 Quality API Pricing

LTX 2.3 Quality API Documentation

Authentication

LTX 2.3 Quality Audio to Video generate request

Request Code

Output

Webhook (Optional)

Request Parameters - LTX 2.3 Quality Audio to Video generate request

Content Item Types & Limits

Example Request

Response

Request Headers

Response Handling

Error Responses

Queue System Errors

Error via Status/Webhook

Retrieving Results

Endpoint

cURL Example

Response (Completed)

Response Fields

Status Values

Status Flow

Typical Workflow

LTX 2.3 Quality API Pricing

LTX 2.3 Quality API Documentation

Authentication

LTX 2.3 Quality Reference Video to Video generate request

Request Code

Output

Webhook (Optional)