LTX 2 19B - APIXO

Overview

LTX 2 19B is a Lightricks video generation model for text-to-video and image-to-video workflows. It also supports LoRA-conditioned variants when you need custom styles, characters, or structural guidance. Use this page when you are ready to call the API after trying the model in the APIXO playground.

Capability	Value
Model ID	`ltx-2-19b`
Modes	`text-to-video`, `image-to-video`, `text-to-video-LoRA`, `image-to-video-LoRA`
Prompt length	1-5000 characters
Reference images	Exactly 1 URL for `image-to-video` and `image-to-video-LoRA`
Aspect ratios	`16:9`, `9:16` for text-to-video modes
Resolution tiers	`480p`, `720p`, `1080p`
Duration	5-20 seconds
LoRA controls	Up to 3 LoRA items, each with `path` and `scale`
Seed	`-1`, or `1` through `2147483647`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/ltx-2-19b`	Submit a generation task
`GET`	`/statusTask/ltx-2-19b?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

This minimal request submits a text-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/ltx-2-19b" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic shot of a small robot walking through a rainy neon street",
      "resolution": "720p",
      "duration": 10,
      "aspect_ratio": "16:9"
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/ltx-2-19b?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/video.mp4\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Failed response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "SensitiveContent",
    "failMsg": "Content violates provider policy, please adjust the prompt",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;

Request body

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a futuristic city with flying cars at sunset",
    "resolution": "1080p",
    "duration": 10,
    "aspect_ratio": "16:9",
    "seed": 54248617
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "make the scene cinematic with a slow camera push and soft motion",
    "image_urls": [
      "https://example.com/source.jpg"
    ],
    "resolution": "720p",
    "duration": 8
  }
}

Image-to-video with LoRA

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video-LoRA",
    "prompt": "animate this character in a stylized studio lighting setup",
    "image_urls": [
      "https://example.com/source.jpg"
    ],
    "resolution": "720p",
    "duration": 8,
    "loras": [
      {
        "path": "https://huggingface.co/username/model.safetensors?download=true",
        "scale": 1.2
      }
    ]
  }
}

Parameters

request_type

string

default:"async"

required

Result delivery mode. Use async for polling with statusTask, or callback for webhook delivery.

callback_url

string

Required when request_type is callback. Must be a public HTTPS endpoint that can receive the final task payload. See Webhooks.

input

object

required

LTX 2 19B input parameters.

Show properties

mode

string

required

Generation mode. Supported values: text-to-video, image-to-video, text-to-video-LoRA, image-to-video-LoRA.

prompt

string

required

Text prompt describing the desired video. Must be non-empty and no longer than 5000 characters.

resolution

string

required

Output resolution tier. Supported values: 480p, 720p, 1080p.

duration

integer

required

Video duration in seconds. Must be a JSON integer from 5 through 20.

image_urls

string[]

Required for image-to-video and image-to-video-LoRA. Provide exactly 1 public, directly accessible image URL.

aspect_ratio

string

default:"16:9"

Applies to text-to-video modes only. Supported values: 16:9, 9:16. If omitted for text-to-video, the backend sends 16:9.

seed

integer

Optional seed. Use -1 to let the provider choose a random seed, or send an integer from 1 through 2147483647.

loras

array

Optional LoRA array, intended for LoRA modes. Supports up to 3 items.

Show item properties

path

string

required

Publicly downloadable LoRA model URL. The value must be a non-empty string.

scale

number

required

LoRA strength. Must be a number from 0.0 through 4.0.

Response format

Submit task response

POST /generateTask/ltx-2-19b returns a task ID when the task is accepted:

code

integer

API status code. 200 means the task was accepted.

message

string

Human-readable status message.

data.taskId

string

Unique task identifier used with the status endpoint.

Status response fields

taskId

string

Unique task identifier.

state

string

Current task state: pending, processing, success, or failed.

resultJson

string

JSON string containing the generated video URLs in resultUrls. Present when state is success.

failCode

string

Machine-readable failure code. Present when state is failed.

failMsg

string

Human-readable failure message. Present when state is failed.

createTime

integer

Task creation timestamp in Unix milliseconds.

completeTime

integer

Task completion timestamp in Unix milliseconds. Present after completion.

costTime

integer

Processing duration in milliseconds when available. Present after completion.

Webhook callback mode

Use callback mode when your backend should receive the final result automatically instead of polling.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/ltx-2-19b" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "callback",
    "callback_url": "https://your-server.com/webhooks/apixo",
    "input": {
      "mode": "text-to-video",
      "prompt": "a clean product reveal video with a slow camera push-in",
      "resolution": "720p",
      "duration": 10,
      "aspect_ratio": "16:9"
    }
  }'

The callback data object uses the same terminal fields as the status response. See Webhooks for delivery requirements and retry behavior.

Billing

LTX 2 19B is billed per second. The backend selects the unit price by resolution and base vs LoRA mode, then multiplies that unit price by the submitted duration.

Resolution	Base modes price	LoRA modes price	Minimum 5s cost
`480p`	`$0.012 / second`	`$0.015 / second`	Base `$0.06`; LoRA `$0.075`
`720p`	`$0.016 / second`	`$0.02 / second`	Base `$0.08`; LoRA `$0.10`
`1080p`	`$0.024 / second`	`$0.03 / second`	Base `$0.12`; LoRA `$0.15`

Formula:

total cost = duration * selected per-second unit price

For current route and market comparison pricing, see Pricing.

Latency and polling

Actual latency may vary by prompt complexity, duration, resolution, LoRA loading, provider queue load, and storage transfer time.

Workload	Typical generation time	Recommended first poll	Poll interval
`480p`	40s-60s	40s after task creation	5s
`720p`	60s-90s	60s after task creation	5s
`1080p`	90s-120s	90s after task creation	5s
LoRA modes	Add about 10s-20s	Add about 10s to the base first poll	5s

For production video workloads, use callback mode to avoid frequent polling while generation is still running.

Result URLs are normally stored for 15 days. Download and store important outputs promptly. For image-to-video modes, provide exactly one source image. Public image URLs should be directly accessible by APIXO; JPG, PNG, or WebP files are the safest choice. For LoRA workflows, use public downloadable model URLs such as Hugging Face or Civitai download links. Each LoRA item must include both path and scale, even if you want a neutral scale like 1.0. Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, missing `input`, missing `mode`, missing `prompt`, invalid `resolution`, invalid `duration`, invalid `seed`, invalid `image_urls`, or invalid `loras`	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`404`	Task not found when polling	Check the `taskId` and model endpoint
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or unknown upstream failure	Retry with backoff
`502`	Upstream provider or network error	Retry with backoff
`503`	Service temporarily unavailable or async queue is full	Retry later
`504`	Upstream timeout	Retry or use callback mode for long-running jobs

Validation notes

Parameter	Backend behavior
`input.mode`	Required for routing. Must be one of `text-to-video`, `image-to-video`, `text-to-video-LoRA`, `image-to-video-LoRA`.
`input.prompt`	Required string. Must not be empty and cannot exceed 5000 characters.
`input.resolution`	Required string. Must be `480p`, `720p`, or `1080p`.
`input.duration`	Required JSON integer. Must be from `5` through `20`; quoted strings are not valid.
`input.image_urls`	Required for image-to-video modes. Must be an array with exactly 1 string URL.
`input.aspect_ratio`	Optional for text-to-video modes. Must be `16:9` or `9:16`; defaults to `16:9` when omitted.
`input.seed`	Optional JSON integer. Must be `-1`, or from `1` through `2147483647`.
`input.loras`	Optional array. If present, it cannot contain more than 3 items.
`input.loras[].path`	Required for each LoRA item. Must be a non-empty string.
`input.loras[].scale`	Required for each LoRA item. Must be numeric and from `0.0` through `4.0`.

Task failure codes

Fail code	Meaning	What to do
`SensitiveContent` / `InputOutputSensitiveContentDetected`	Prompt, input image, or output failed provider safety checks	Change the prompt or input image
`PromptInvalid`	Prompt was rejected or malformed	Adjust the prompt and retry
`ImageFormatIncorrect` / `InvalidImageSize`	Input image failed upstream image validation	Use a public, direct JPG, PNG, or WebP URL
`ImageNotAccess`	APIXO could not fetch an input URL	Use a public HTTP or HTTPS URL that returns `200` or `206`
`RateLimited`	Provider-side rate limit	Retry with exponential backoff
`Timeout`	Provider-side timeout	Retry, simplify the request, or use callback mode
`Unknown error`	Provider returned an unmapped failure	Retry with backoff or contact support with the `taskId`

See Error Codes for the full error reference.

Documentation Index

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Text-to-video

​Image-to-video

​Image-to-video with LoRA

​Parameters

​Response format

​Submit task response

​Status response fields

​Webhook callback mode

​Billing

​Latency and polling

​Errors and troubleshooting

​HTTP errors

​Validation notes

​Task failure codes

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Text-to-video

Image-to-video

Image-to-video with LoRA

Parameters

Response format

Submit task response

Status response fields

Webhook callback mode

Billing

Latency and polling

Errors and troubleshooting

HTTP errors

Validation notes

Task failure codes

Related links