Kling 3.0 Omni API

Overview

Kling 3.0 Omni is a multi-mode Kling video generation API on APIXO. Use it when you need one model ID for standard, pro, and 4K generation from text prompts, images, or visual references.

Capability	Value
Model ID	`kling-3-0-omni`
Modes	`std-text-to-video`, `std-image-to-video`, `std-reference-to-video`, `pro-text-to-video`, `pro-image-to-video`, `pro-reference-to-video`, `4k-text-to-video`, `4k-image-to-video`, `4k-reference-to-video`
Prompt	Required in every mode
Duration	Defaults to `5`; most modes support `3-15` seconds; `pro-text-to-video` and `pro-image-to-video` support `5` or `10`
Aspect ratios	`16:9`, `9:16`, `1:1` for text and reference modes
Image inputs	Image modes require 1-2 images; reference modes support reference images by mode
Video inputs	`std-reference-to-video` and `pro-reference-to-video` can use the first `video_urls` item as a reference video
Output	Video URLs in `resultJson.resultUrls`

Endpoint and authentication

Base URL:

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

Method	Endpoint	Purpose
`POST`	`/generateTask/kling-3-0-omni`	Submit a generation task
`GET`	`/statusTask/kling-3-0-omni?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 standard text-to-video task and returns a taskId.

curl -X POST "https://api.apixo.ai/api/v1/generateTask/kling-3-0-omni" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "std-text-to-video",
      "prompt": "a cinematic city skyline at sunset with a slow camera push",
      "duration": 5,
      "sound": false,
      "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/kling-3-0-omni?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": "INVALID_PARAMETER",
    "failMsg": "One or more input parameters are invalid.",
    "createTime": 1767965610929,
    "completeTime": 1767965620132
  }
}

Parse resultJson after state becomes success:

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

Request body

Standard text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "std-text-to-video",
    "prompt": "a cinematic city skyline at sunset",
    "duration": 5,
    "sound": false,
    "aspect_ratio": "16:9"
  }
}

Pro image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "pro-image-to-video",
    "prompt": "animate the subject walking toward the camera",
    "duration": 10,
    "sound": true,
    "image_urls": [
      "https://example.com/start.png",
      "https://example.com/end.png"
    ]
  }
}

Reference-to-video with a reference video

{
  "request_type": "async",
  "input": {
    "mode": "std-reference-to-video",
    "prompt": "keep the same visual style and motion mood",
    "duration": 6,
    "sound": true,
    "aspect_ratio": "16:9",
    "image_urls": [
      "https://example.com/ref-1.png",
      "https://example.com/ref-2.png"
    ],
    "video_urls": [
      "https://example.com/reference.mp4"
    ]
  }
}

4K reference-to-video

{
  "request_type": "async",
  "input": {
    "mode": "4k-reference-to-video",
    "prompt": "turn these product reference images into a polished 4K product video",
    "duration": 8,
    "sound": true,
    "aspect_ratio": "16:9",
    "image_urls": [
      "https://example.com/ref-1.png",
      "https://example.com/ref-2.png"
    ]
  }
}

Parameters

string

default:"async"

Result delivery mode. Omit this field or use async for polling with statusTask, or use callback for webhook delivery.

string

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

object

required

Kling 3.0 Omni input parameters.

Show properties

string

required

Generation mode. Supported values: std-text-to-video, std-image-to-video, std-reference-to-video, pro-text-to-video, pro-image-to-video, pro-reference-to-video, 4k-text-to-video, 4k-image-to-video, and 4k-reference-to-video.

string

required

Text prompt describing the desired video. APIXO trims whitespace and rejects missing, non-string, or empty prompts.

integer|string

default:"5"

Output duration in seconds. Accepts an integer or integer string. Defaults to 5. Most modes support 3 through 15; pro-text-to-video and pro-image-to-video only support 5 or 10.

boolean

default:"false"

Whether to generate or preserve sound. Must be a JSON boolean when provided. For reference modes with video_urls, sound=true asks APIXO to keep the original sound from the reference video where supported.

string

default:"16:9"

Output aspect ratio for text and reference modes. Supported values: 16:9, 9:16, 1:1. Image modes ignore this field.

string

Optional shot behavior. Supported values: customize, intelligent.

object[]

Optional prompt segments. Provide 1-6 objects. Each item must include a non-empty string prompt and an integer duration.

string[]

Image URLs. Required for image modes with 1-2 images. For std-reference-to-video and pro-reference-to-video, provide 1-7 images when no reference video is provided, or 0-4 images when video_urls is provided. For 4k-reference-to-video, provide 1-7 images. All items must be non-empty strings.

string[]

Reference video URLs. Supported only by std-reference-to-video and pro-reference-to-video. When provided, APIXO uses the first non-empty URL and ignores additional URLs. 4k-reference-to-video ignores video_urls.

Mode behavior

Mode	Required media	Duration	Notes
`std-text-to-video`	none	`3-15`, default `5`	Uses `aspect_ratio` and `sound`.
`std-image-to-video`	1-2 `image_urls`	`3-15`, default `5`	First image is the start frame; second image is optional end frame.
`std-reference-to-video`	1-7 images, or first `video_urls` item with up to 4 images	`3-15`, default `5`	Uses `aspect_ratio`; reference video pricing differs from image-only reference mode.
`pro-text-to-video`	none	`5` or `10`, default `5`	Uses `aspect_ratio` and `sound`.
`pro-image-to-video`	1-2 `image_urls`	`5` or `10`, default `5`	First image is the start frame; second image is optional end frame.
`pro-reference-to-video`	1-7 images, or first `video_urls` item with up to 4 images	`3-15`, default `5`	Uses pro reference pricing.
`4k-text-to-video`	none	`3-15`, default `5`	4K per-second rate; `sound` does not change price.
`4k-image-to-video`	1-2 `image_urls`	`3-15`, default `5`	4K per-second rate.
`4k-reference-to-video`	1-7 `image_urls`	`3-15`, default `5`	Ignores `video_urls`; 4K per-second rate.

Use direct, publicly accessible media URLs. For image modes, provide exactly the images you want used as start and optional end frames.

Response format

Submit task response

POST /generateTask/kling-3-0-omni returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: pending, processing, processing_r2, success, or failed.

string

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

string

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

string

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

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds when available.

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/kling-3-0-omni" \
  -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": "pro-image-to-video",
      "prompt": "animate the product photo with a slow cinematic camera move",
      "duration": 10,
      "sound": true,
      "image_urls": [
        "https://example.com/product.png"
      ]
    }
  }'

The callback payload uses the same code, message, and data shape as the status response. See Webhooks for delivery requirements and retry behavior.

Billing

Kling 3.0 Omni is billed per output second. Total cost is:

total cost = duration * selected mode unit price

Mode group	Condition	Unit price
`std-text-to-video`, `std-image-to-video`	`sound=false`	`$0.084 / second`
`std-text-to-video`, `std-image-to-video`	`sound=true`	`$0.112 / second`
`std-reference-to-video`	no `video_urls`, `sound=false`	`$0.084 / second`
`std-reference-to-video`	no `video_urls`, `sound=true`	`$0.112 / second`
`std-reference-to-video`	with `video_urls`	`$0.126 / second`
`pro-text-to-video`, `pro-image-to-video`	`sound=false`	`$0.112 / second`
`pro-text-to-video`, `pro-image-to-video`	`sound=true`	`$0.14 / second`
`pro-reference-to-video`	no `video_urls`, `sound=false`	`$0.112 / second`
`pro-reference-to-video`	no `video_urls`, `sound=true`	`$0.1344 / second`
`pro-reference-to-video`	with `video_urls`	`$0.168 / second`
`4k-text-to-video`, `4k-image-to-video`, `4k-reference-to-video`	fixed 4K rate	`$0.42 / second`

For current route and market comparison pricing, see Pricing.

Latency and polling

Kling 3.0 Omni tasks are asynchronous. Actual latency varies by mode, prompt complexity, media inputs, duration, 4K selection, route queue load, and provider-side processing time.

Workload	Typical generation time	Recommended first poll	Poll interval
Standard text/image clip	60s-120s	60s after task creation	5s-10s
Pro or reference-guided clip	90s-180s	60s-90s after task creation	5s-10s
4K clip	Often longer than standard generation	90s after task creation	10s-15s

For production workloads, use callback mode to avoid frequent polling while video tasks run.

Result URLs are temporary. Download and store important outputs promptly after task completion. 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`, unsupported `mode`, invalid media array, unsupported duration, or invalid optional field	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`
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server error or unknown task failure	Retry with backoff
`502`	Upstream error	Retry with backoff
`504`	Upstream timeout	Retry later or use callback mode for long-running jobs

Validation notes

Condition	Backend behavior
Missing or unsupported `mode`	Request fails before task creation.
Missing, non-string, or empty `prompt`	Request fails before task creation.
Missing `duration`	Defaults to `5`.
`duration` outside `3-15`	Request fails before task creation.
`pro-text-to-video` or `pro-image-to-video` duration other than `5` or `10`	Request fails before task creation.
`sound` is not boolean	Request fails before task creation.
Unsupported `aspect_ratio`	Request fails before task creation. Use `16:9`, `9:16`, or `1:1`.
Image mode without `image_urls`	Request fails before task creation.
Image mode with more than 2 `image_urls`	Request fails before task creation.
Reference mode without `image_urls` or `video_urls`	Request fails before task creation, except text/image modes where references are not used.
Reference mode with `video_urls` and more than 4 images	Request fails before task creation.
`4k-reference-to-video` without `image_urls`	Request fails before task creation.
`shot_type` not `customize` or `intelligent`	Request fails before task creation.
`multi_prompt` has more than 6 items or invalid item objects	Request fails before task creation.

Task failure codes

failCode is generated from APIXO’s mapped provider error. Common values include:

Fail code	Meaning	What to do
`CONTENT_VIOLATION`	Prompt or input/output content was rejected by safety checks	Change the prompt or input media
`INVALID_PARAMETER`	A required field is missing or a value is unsupported	Check `mode`, `duration`, `sound`, `image_urls`, `video_urls`, and `aspect_ratio`
`INVALID_IMAGE_URL`	A reference image could not be fetched or decoded	Use a direct, publicly accessible image URL
`INVALID_VIDEO_URL`	A reference video could not be fetched or decoded	Use a direct, publicly accessible video URL
`INSUFFICIENT_BALANCE`	The account does not have enough balance for the task	Add balance before retrying
`UPSTREAM_ERROR`	Provider-side generation failed	Retry with backoff
`UNKNOWN_ERROR`	The failure could not be mapped to a more specific code	Retry later or contact support with the `taskId`

See Error Codes for the full error reference.

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Standard text-to-video

​Pro image-to-video

​Reference-to-video with a reference video

​4K reference-to-video

​Parameters

​Mode behavior

​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

Standard text-to-video

Pro image-to-video

Reference-to-video with a reference video

4K reference-to-video

Parameters

Mode behavior

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