> ## Documentation Index
> Fetch the complete documentation index at: https://apixo.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Kling 3.0 Std API
> Standard-quality video generation API with text-to-video, image-to-video, and motion-control modes
## Overview
Kling 3.0 Std is a standard-quality video generation model for text prompts, reference-image animation, and motion transfer from a reference video. Use this page when you are ready to call the API after trying the model in the APIXO playground.
| Capability | Value |
| ----------------------- | -------------------------------------------------------------------------------- |
| Model ID | `kling-3-0-std` |
| Modes | `text-to-video`, `image-to-video`, `motion-control` |
| Text prompt | Required for `text-to-video` and `image-to-video`; optional for `motion-control` |
| Reference images | `image-to-video`: 1-2 URLs; `motion-control`: exactly 1 URL |
| Reference video | `motion-control`: exactly 1 public MP4, MOV, or M4V URL |
| Duration | `text-to-video` and `image-to-video`: 3-15 seconds, default `5` |
| Motion-control duration | Auto-detected from `video_urls[0]`; videos over 30 seconds are rejected |
| Aspect ratios | `1:1`, `9:16`, `16:9` for `text-to-video` |
## Endpoint and authentication
Base URL:
```text theme={null}
https://api.apixo.ai/api/v1
```
| Method | Endpoint | Purpose |
| ------ | ------------------------------------------- | ------------------------------------- |
| `POST` | `/generateTask/kling-3-0-std` | Submit a generation task |
| `GET` | `/statusTask/kling-3-0-std?taskId={taskId}` | Poll task status and retrieve results |
All requests require your APIXO API key:
```http theme={null}
Authorization: Bearer YOUR_API_KEY
```
Submit requests also require:
```http theme={null}
Content-Type: application/json
```
## Copy-paste async quickstart
This minimal request submits a text-to-video task and returns a `taskId`.
```bash theme={null}
curl -X POST "https://api.apixo.ai/api/v1/generateTask/kling-3-0-std" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"request_type": "async",
"input": {
"mode": "text-to-video",
"prompt": "a cinematic city skyline at sunset, slow camera push-in",
"duration": 5,
"sound": false,
"aspect_ratio": "16:9"
}
}'
```
Successful response:
```json theme={null}
{
"code": 200,
"message": "success",
"data": {
"taskId": "task_12345678"
}
}
```
Save the `taskId`; you need it to poll for the final result.
## Poll for result
```bash theme={null}
curl -X GET "https://api.apixo.ai/api/v1/statusTask/kling-3-0-std?taskId=task_12345678" \
-H "Authorization: Bearer YOUR_API_KEY"
```
Processing response:
```json theme={null}
{
"code": 200,
"message": "success",
"data": {
"taskId": "task_12345678",
"state": "processing",
"createTime": 1767965610929
}
}
```
Success response:
```json theme={null}
{
"code": 200,
"message": "success",
"data": {
"taskId": "task_12345678",
"state": "success",
"resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/video.mp4\"]}",
"createTime": 1767965610929,
"completeTime": 1767965712317,
"costTime": 101388
}
}
```
Failed response:
```json theme={null}
{
"code": 200,
"message": "success",
"data": {
"taskId": "task_12345678",
"state": "failed",
"failCode": "CONTENT_VIOLATION",
"failMsg": "Content does not meet safety guidelines",
"createTime": 1767965610929,
"completeTime": 1767965620132
}
}
```
Parse `resultJson` after `state` becomes `success`:
```javascript theme={null}
const payload = JSON.parse(data.resultJson);
const videoUrls = payload.resultUrls;
```
## Request body
### Text-to-video
```json theme={null}
{
"request_type": "async",
"input": {
"mode": "text-to-video",
"prompt": "a cinematic city skyline at sunset, slow camera push-in",
"negative_prompt": "blur, low quality",
"duration": 5,
"sound": false,
"aspect_ratio": "16:9",
"cfg_scale": 0.5,
"multi_prompt": [
{
"duration": 2,
"prompt": "wide establishing shot"
},
{
"duration": 3,
"prompt": "slow push-in toward glowing skyscrapers"
}
]
}
}
```
### Image-to-video
```json theme={null}
{
"request_type": "async",
"input": {
"mode": "image-to-video",
"prompt": "animate the character waving to the camera",
"duration": 6,
"sound": true,
"image_urls": [
"https://example.com/start.png",
"https://example.com/end.png"
],
"cfg_scale": 0.5
}
}
```
### Motion-control
```json theme={null}
{
"request_type": "async",
"input": {
"mode": "motion-control",
"prompt": "keep the same character identity while following the motion reference",
"negative_prompt": "distorted face, extra limbs",
"sound": true,
"character_orientation": "video",
"image_urls": [
"https://example.com/character.png"
],
"video_urls": [
"https://example.com/motion.mp4"
]
}
}
```
## Parameters
Result delivery mode. Use `async` for polling with `statusTask`, or `callback` for webhook delivery.
Required when `request_type` is `callback`. Must be a public HTTPS URL that can receive the final task payload. See [Webhooks](/docs/api-reference/webhooks).
Kling 3.0 Std input parameters.
Generation mode. Supported values: `text-to-video`, `image-to-video`, `motion-control`.
Text prompt for the video. Required for `text-to-video` and `image-to-video`; optional for `motion-control`. If provided, it must be a non-empty string.
Optional negative prompt. If provided, it must be a non-empty string.
Output duration in seconds for `text-to-video` and `image-to-video`. Supports integer values or numeric strings from `3` to `15`. Ignored and not forwarded in `motion-control`.
For `text-to-video` and `image-to-video`, controls whether Kling generates audio with the video. For `motion-control`, controls whether the reference video's original audio is retained.
Output aspect ratio for `text-to-video` only. Supported values: `1:1`, `9:16`, `16:9`.
Guidance scale for `text-to-video` and `image-to-video`. Supported range: `0` to `1`.
Reference image URLs. Required for `image-to-video` and `motion-control`. `image-to-video` supports 1-2 images; `motion-control` requires exactly 1 image. Upstream expects JPG, JPEG, or PNG images, with each image under 10 MB.
Required for `motion-control` only. Provide exactly 1 public HTTP/HTTPS MP4, MOV, or M4V URL. APIXO probes `video_urls[0]` to detect duration; videos over 30 seconds are rejected.
`motion-control` only. Supported values: `image`, `video`. Determines whether character orientation follows the character image or the motion reference video.
Optional shot-level prompt segments for `text-to-video` and `image-to-video`. Each item must include a non-empty `prompt` and a `duration` integer or numeric string. `multi_prompt` does not affect billing.
## Response format
### Submit task response
`POST /generateTask/kling-3-0-std` returns a task ID when the task is accepted:
API status code. `200` means the task was accepted.
Human-readable status message.
Unique task identifier used with the status endpoint.
### Status response fields
Unique task identifier.
Current task state: `pending`, `processing`, `success`, or `failed`.
JSON string containing the generated video URLs. Present when `state` is `success`.
Machine-readable failure code. Present when `state` is `failed`.
Human-readable failure message. Present when `state` is `failed`.
Task creation timestamp in Unix milliseconds.
Task completion timestamp in Unix milliseconds. Present after completion.
Processing duration in milliseconds. Present after successful completion.
## Webhook callback mode
Use callback mode when your backend should receive the final result automatically instead of polling.
```bash theme={null}
curl -X POST "https://api.apixo.ai/api/v1/generateTask/kling-3-0-std" \
-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": "image-to-video",
"prompt": "animate the product photo with a slow studio camera move",
"duration": 5,
"sound": true,
"image_urls": [
"https://example.com/product.png"
]
}
}'
```
See [Webhooks](/docs/api-reference/webhooks) for delivery requirements and retry behavior.
## Billing
Kling 3.0 Std is billed per generated video second. For `text-to-video` and `image-to-video`, the selected `sound` value determines the unit price. For `motion-control`, APIXO probes the reference video duration and uses a minimum of 3 billable seconds.
| Workflow | Billing input | APIXO price |
| --------------------------------------------------- | ---------------------------------------------------- | ----------------- |
| `text-to-video` or `image-to-video`, `sound: false` | `duration` seconds | `$0.084 / second` |
| `text-to-video` or `image-to-video`, `sound: true` | `duration` seconds | `$0.13 / second` |
| `motion-control` | Detected `video_urls[0]` duration, minimum 3 seconds | `$0.13 / second` |
For current route and market comparison pricing, see [Pricing](https://apixo.ai/pricing).
## Latency and polling
Actual latency may vary by prompt complexity, reference media, sound generation, route, and current queue load.
| Request shape | Typical generation time | Recommended first poll | Poll interval |
| ----------------------------- | ------------------------------------------------ | ----------------------- | ------------- |
| 3-5 second text/image video | 60s-90s | 60s after task creation | 5s-10s |
| 6-10 second text/image video | 90s-120s | 60s after task creation | 5s-10s |
| 11-15 second text/image video | 120s-180s | 60s after task creation | 5s-10s |
| Motion-control | Varies with reference video duration and probing | 60s after task creation | 5s-10s |
Video generation takes longer than image generation. For production workloads, use callback mode to avoid frequent polling.
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](/docs/api-reference/system).
## Errors and troubleshooting
### HTTP errors
| Code | Meaning | What to do |
| ----- | -------------------------------------------------------------- | ------------------------------------------------ |
| `400` | Invalid request body, mode, parameter, image URL, or video URL | 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 |
| `429` | Rate limit or concurrency limit reached | Retry with exponential backoff |
| `500` | Server error | Retry with backoff |
| `502` | Upstream error | Retry with backoff |
| `504` | Upstream timeout | Retry or use callback mode for long-running jobs |
### Task failure codes
| Fail code | Meaning | What to do |
| ---------------------- | -------------------------------------------------------------- | --------------------------------------------------------------------------------- |
| `CONTENT_VIOLATION` | Prompt or reference media failed safety checks | Change the prompt or input media |
| `INVALID_IMAGE_URL` | A reference image URL could not be fetched or decoded | Use a public, direct JPG, JPEG, or PNG URL |
| `INVALID_VIDEO_URL` | A reference video URL could not be fetched, decoded, or probed | Use a public MP4, MOV, or M4V URL |
| `INVALID_PARAMETER` | A model parameter is unsupported or malformed | Check `mode`, `duration`, `sound`, `aspect_ratio`, `image_urls`, and `video_urls` |
| `INSUFFICIENT_BALANCE` | The account does not have enough balance for the task | Add balance before retrying |
| `UPSTREAM_ERROR` | Upstream failure | Retry with backoff |
| `TIMEOUT` | Generation did not finish in time | Retry, simplify inputs, or use callback mode |
### Common fixes
| Symptom | Fix |
| ------------------------------------------ | ---------------------------------------------------------------------------------------------- |
| Request fails with invalid mode | Set `input.mode` to `text-to-video`, `image-to-video`, or `motion-control` |
| Unexpected audio cost | `sound` defaults to `true`; set `sound: false` for text/image video without generated audio |
| `duration` has no effect in motion-control | This mode detects duration from `video_urls[0]` and does not forward `duration` |
| Aspect ratio has no effect | `aspect_ratio` is only forwarded for `text-to-video` |
| Video URL probe fails | Use a direct public HTTP/HTTPS MP4, MOV, or M4V URL that supports range reads or full download |
| Motion-control video is rejected | Keep the reference video at 30 seconds or shorter |
See [Error Codes](/docs/api-reference/errors) for the full error reference.
## Related links
* [Generation API Overview](/docs/models)
* [Video Models](/docs/models/video)
* [Generate Task](/docs/api-reference/generate-task)
* [Status Task](/docs/api-reference/status-task)
* [Webhooks](/docs/api-reference/webhooks)
* [Error Codes](/docs/api-reference/errors)
* [Parameter Specification](/docs/api-reference/parameters)
* [Routing Strategies](/docs/concepts/routing-strategies)
* [Try Kling 3.0 Std in the APIXO Playground](https://apixo.ai/models/kling-3-0-std)
* [Pricing](https://apixo.ai/pricing)