▣ IMAGE PROCESSING · SMART GENERATION

MasterA AI — GPU Video Generation

What it does

LTX Video Generation creates short AI videos from a text prompt and returns a task ID you can poll until the MP4 is ready.

Use the POST /ltx/generate endpoint to send a prompt and optional generation controls such as cfg, seed, steps, width, height, length, and negative_prompt. The response gives you status, message, and task_id so you can track the job asynchronously. Poll GET /tasks/:task_id to watch the request move through processing, generating, completed, or error; when it completes, the response includes output_url for the finished MP4.

The service also includes an LTX-2 path on RTX 5090 hardware. Its POST /generate endpoint accepts prompt plus optional seed, model, length, quality, and resolution, and returns status, message, and task_id. Poll the matching task endpoint to retrieve output_url once the video is finished.

This is a fit for product demos, concept previews, social clips, and rapid storyboard generation when you need a text-to-video workflow that runs asynchronously and gives you a downloadable result at the end.

▣ ENDPOINT 01 / 04

POST

Generate a short video (LTX, RTX 5080)

https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/ltx/generate

QUICKSTART

GUIDE

Quickstart

Start a video generation job by sending a text prompt.

curl -X POST "https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/ltx/generate" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Ocean waves at sunset, cinematic, slow camera pan"
  }'

What you'll get back

Returns a JSON object with status, message, and task_id fields. status is a string such as "processing", message is a string with the job message, and task_id is the generated task identifier.

{
  "status": "processing",
  "message": "Your video generation job has been queued.",
  "task_id": "a1b2c3d4e5f6"
}

TRY ITLIVE · 10 ATOMS

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Generates a short video from a text prompt. The request body controls the generation settings, and the success response returns a JSON object with the task status, a message, and a task identifier for tracking the job.

Request Body

Parameter	Type	Mandatory	Description
cfg	Number	No	Guidance scale. Default: `1`. `1.0` is recommended for the distilled model.
seed	Integer	No	Random seed for reproducible generation. Default: `0`.
steps	Integer	No	Number of inference steps. Default: `8`. Minimum: `1`; maximum: `15`.
width	Integer	No	Output video width in pixels. Default: `768`. Minimum: `256`; maximum: `1024`.
height	Integer	No	Output video height in pixels. Default: `512`. Minimum: `256`; maximum: `1024`.
length	Integer	No	Video duration in frames at 25 fps. Default: `97`. Minimum: `9`; maximum: `161`. Snapped to a valid `n*8+1` value. `97` frames is about 4 seconds.
prompt	String	Yes	The text description of the video to generate.
negative_prompt	String	No	What to avoid in the generated video. Default: empty string.

Response

Returns a JSON object with status and message string fields, plus a task_id string field used to track the generated video job.

Parameter	Type	Mandatory	Description
status	String	No	Job status.
message	String	No	Status or response message.
task_id	String	No	Identifier for the generation task.

Body

Name

Type

Description

bodyREQUIRED

object

—

▣ ENDPOINT 02 / 04

GET

Poll LTX video status (RTX 5080)

https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/tasks/:task_id

QUICKSTART

GUIDE

Quickstart

Check the status of a task by its task_id path parameter.

curl -X GET "https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/tasks/:task_id/tasks/your-task-id" \
  -H "apy-token: $APY_TOKEN"

What you'll get back

Returns a JSON object with these top-level fields when present: type string, error string, status string, message string, task_id string, and output_url string.

status can be processing, generating, completed, or error.
output_url is the URL to the finished MP4 and is only present when status is completed.

{
  "type": "ltx_t2v",
  "status": "completed",
  "task_id": "your-task-id",
  "output_url": "https://example.com/video.mp4"
}

TRY ITLIVE · 1 ATOM

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Polls the status of an LTX video generation task by task_id and returns the current task state plus any available result information. When the task is completed, the response includes the finished MP4 URL in output_url.

Path Parameter(s)

Attribute	Type	Mandatory	Description
task_id	String	Yes	Identifies the task to poll.

Response

Returns a JSON object with type, error, status, message, task_id, and output_url fields. The status field indicates the task state, and output_url is only present when status is completed.

Parameter	Type	Mandatory	Description
type	String	No	Task type. Example: `ltx_t2v`.
error	String	No	Error message, if present.
status	ENUM	No	Task status. Allowed values: `processing`, `generating`, `completed`, `error`.
message	String	No	Additional status or error message.
task_id	String	No	The task identifier.
output_url	String	No	URL to the finished MP4. Present only when `status` is `completed`.

Path parameters

Name

Type

Description

task_idREQUIRED

string

—

▣ ENDPOINT 03 / 04

POST

Generate a short video (LTX-2, RTX 5090)

https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/generate

QUICKSTART

GUIDE

Quickstart

Generate a video from a single text prompt.

curl -X POST "https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/generate" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A red fox running through fresh snow, slow motion, cinematic lighting"}'

What you'll get back

Returns a JSON object with status, message, and task_id string fields. status indicates the job state, message provides a human-readable note, and task_id is the identifier for the queued generation task.

{
  "status": "queued",
  "message": "Your video generation request has been queued.",
  "task_id": "task_123abc"
}

TRY ITLIVE · 10 ATOMS

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Generates a short video from a text prompt. The request body supplies the generation settings, and the response returns the task status, a message, and a task identifier.

Request Body

Parameter	Type	Mandatory	Description
prompt	String	Yes	Text description of the video to generate.
seed	Integer	No	Random seed for reproducible generation. Default: `0`.
model	ENUM	No	Video model to use. Allowed value: `ltx2`. Default: `ltx2`.
length	ENUM	No	Approximate duration. Allowed values: `3s`, `5s`, `10s`. Default: `5s`.
quality	ENUM	No	Generation quality (inference steps). Allowed values: `fast`, `balanced`, `best`. Default: `fast`.
resolution	ENUM	No	Output resolution. Allowed values: `sd` (SD 480p), `hd` (HD 720p). Default: `sd`.

Response

Returns a JSON object with status, message, and task_id string fields. The status field indicates the task state, and task_id identifies the submitted generation job.

Parameter	Type	Mandatory	Description
status	String	No	Task status.
message	String	No	Informational message about the request or task.
task_id	String	No	Identifier for the submitted task.

Body

Name

Type

Description

bodyREQUIRED

object

—

▣ ENDPOINT 04 / 04

GET

Poll LTX-2 video status (RTX 5090)

https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/video/tasks/:task_id

QUICKSTART

GUIDE

Quickstart

Check the status of a video generation task by its task_id.

curl -X GET "https://api.eu.apyverse.com/pankajretestflows/mastera-ai-gpu-video-generation/video/tasks/:task_id"

What you'll get back

Returns a JSON object with these top-level fields: type (string), error (string), status (queued, generating, completed, or error), task_id (string), elapsed_s (number), and output_url (string, present when status is completed).

{
  "type": "ltx2",
  "status": "completed",
  "task_id": "task-123",
  "elapsed_s": 12.5,
  "output_url": "https://example.com/video.mp4"
}

TRY ITLIVE · 1 ATOM

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Polls the status of an LTX-2 video generation task by task ID and returns the current task state. When the task reaches completed, the response may include an output_url for the finished MP4.

Path Parameter(s)

Attribute	Type	Mandatory	Description
task_id	String	Yes	Identifies the video generation task to poll.

Response

Returns a JSON object with type, error, status, task_id, elapsed_s, and output_url fields. The status field indicates the task state, and output_url is returned only when status is completed.

Parameter	Type	Mandatory	Description
type	String	No	Task type identifier.
error	String	No	Error message returned when the task fails.
status	ENUM	No	Current task status: `queued`, `generating`, `completed`, or `error`.
task_id	String	No	Identifier of the task being polled.
elapsed_s	Number	No	Elapsed time in seconds.
output_url	String	No	URL to the finished MP4, returned only when `status` is `completed`.

Notes

Poll this endpoint with the task_id returned by the submit call. The status field cycles through transitional values (queued, generating) before reaching a terminal state (completed or error). The result field output_url is only populated once status is completed; treat it as absent otherwise.

Path parameters

Name

Type

Description

task_idREQUIRED

string

—

▣ COMMON ERRORS

Errors any endpoint can return

400bad_request

Required parameter missing or malformed body.

401unauthorized

API key missing, revoked, or not authorized for this service.

429rate_limited

Your plan's per-second rate exceeded. Retry with exponential backoff.

503upstream_busy

Backend temporarily unavailable. Try again in a few seconds.