> ## 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 2.5 Turbo Pro
> Fast high-quality video generation with text-to-video, image-to-video, and tail-frame control
## Overview
Kling 2.5 Turbo Pro is a Kuaishou video model for fast text-to-video and image-to-video generation. Use this page when you are ready to call the API after trying the model in the APIXO playground.
| Capability | Value |
| ------------------ | ------------------------------------------------------- |
| Model ID | `kling-2-5-turbo-pro` |
| Modes | `text-to-video`, `image-to-video` |
| Prompt length | 1-2500 characters |
| Duration | `5` or `10` seconds |
| Reference images | 1-2 URLs for `image-to-video` |
| Tail-frame control | The second `image_urls` item is used as the final frame |
| Aspect ratios | `16:9`, `9:16`, `1:1` for `text-to-video` |
| Negative prompt | Up to 2500 characters |
| CFG scale | `0` to `1`, step `0.1` |
| Output | MP4 video URLs in `resultJson.resultUrls` |
## Endpoint and authentication
Base URL:
```text theme={null}
https://api.apixo.ai/api/v1
```
| Method | Endpoint | Purpose |
| ------ | ------------------------------------------------- | ------------------------------------- |
| `POST` | `/generateTask/kling-2-5-turbo-pro` | Submit a generation task |
| `GET` | `/statusTask/kling-2-5-turbo-pro?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-2-5-turbo-pro" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"request_type": "async",
"input": {
"mode": "text-to-video",
"prompt": "a cinematic drone shot over snowy mountains at sunrise",
"duration": 5,
"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-2-5-turbo-pro?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/xxx.mp4\"]}",
"createTime": 1767965610929,
"completeTime": 1767965652317,
"costTime": 41388
}
}
```
Failed response:
```json theme={null}
{
"code": 200,
"message": "success",
"data": {
"taskId": "task_12345678",
"state": "failed",
"failCode": "SensitiveContent",
"failMsg": "Content violates the upstream content policy, please adjust the prompt",
"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 drone shot over snowy mountains at sunrise",
"duration": 10,
"aspect_ratio": "16:9",
"negative_prompt": "low quality, jitter, blur",
"cfg_scale": 0.6
}
}
```
### Image-to-video
```json theme={null}
{
"request_type": "async",
"input": {
"mode": "image-to-video",
"prompt": "smooth camera transition from the first frame to the final frame",
"duration": 5,
"image_urls": [
"https://example.com/start.jpg",
"https://example.com/end.jpg"
],
"negative_prompt": "distortion, low quality",
"cfg_scale": 0.4
}
}
```
## 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](/api-reference/webhooks).
Kling 2.5 Turbo Pro input parameters.
Generation mode. Supported values: `text-to-video`, `image-to-video`.
Text prompt describing the video. Must be non-empty after trimming and no longer than 2500 characters.
Output duration in seconds. Supported values: `5`, `10`. Numeric strings such as `"5"` are also accepted.
Required for `image-to-video`. Supports 1-2 public image URLs. The first image is the start frame; the second image, when provided, is the tail frame.
Output aspect ratio for `text-to-video`. Supported values: `16:9`, `9:16`, `1:1`. This field is not forwarded for `image-to-video`.
Negative prompt describing content to avoid. Supports up to 2500 characters. Blank values are ignored.
Prompt guidance scale. Supported values are `0` through `1` in `0.1` steps, for example `0`, `0.4`, `0.7`, or `1`. Numeric strings are accepted.
## Response format
### Submit task response
`POST /generateTask/kling-2-5-turbo-pro` 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 generated video URLs in `resultUrls`. 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 when available.
## 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-2-5-turbo-pro" \
-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": "make the subject turn toward camera with smooth natural motion",
"duration": 5,
"image_urls": [
"https://example.com/start.jpg"
],
"cfg_scale": 0.5
}
}'
```
Webhook delivery uses the same final task payload shape as the status response. See [Webhooks](/api-reference/webhooks) for delivery requirements and retry behavior.
## Billing
Kling 2.5 Turbo Pro is billed by video duration. The public APIXO pricing page lists this model with a starting APIXO price of `$0.06 / second`.
| Duration | Starting APIXO price |
| ------------ | -------------------- |
| `5` seconds | `$0.30 / video` |
| `10` seconds | `$0.60 / video` |
For current route and market comparison pricing, see [Pricing](https://apixo.ai/pricing).
## Latency and polling
Actual latency may vary by prompt complexity, input images, selected route, and current queue load.
| Duration | Typical generation time | Recommended first poll | Poll interval |
| ------------ | ----------------------- | ----------------------- | ------------- |
| `5` seconds | 30s-45s | 30s after task creation | 5s-10s |
| `10` seconds | 45s-60s | 30s after task creation | 5s-10s |
For production video workloads, use callback mode to avoid frequent polling. Download and store important output URLs promptly after 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](/api-reference/system).
## Errors and troubleshooting
### HTTP errors
| Code | Meaning | What to do |
| ----- | --------------------------------------------------------------- | ------------------------------------------------ |
| `400` | Invalid request body, mode, parameter value, or image URL shape | 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, or content was rejected | Check permissions and adjust input |
| `404` | Task ID or route not found | Check the model endpoint and `taskId` |
| `429` | Rate limit or concurrency limit reached | Retry with exponential backoff |
| `500` | Server or upstream error | Retry with backoff |
| `503` | Service temporarily unavailable | Retry with backoff |
| `504` | Upstream timeout | Retry or use callback mode for long-running jobs |
### Parameter validation
| Field | Rule |
| ----------------------- | ----------------------------------------------------------------------------- |
| `input.mode` | Required. Must be `text-to-video` or `image-to-video`. |
| `input.prompt` | Required string, non-empty after trimming, max 2500 characters. |
| `input.duration` | Required. Must be `5` or `10`; integer and numeric string are accepted. |
| `input.image_urls` | Required for `image-to-video`; must be an array of 1-2 strings. |
| `input.aspect_ratio` | Optional for `text-to-video`; must be `16:9`, `9:16`, or `1:1` when provided. |
| `input.negative_prompt` | Optional string, max 2500 characters. |
| `input.cfg_scale` | Optional number or numeric string from `0` to `1`, step `0.1`. |
### Task failure codes
| Fail code | Meaning | What to do |
| ---------------------- | ----------------------------------------------------------------------------- | ---------------------------------------------------- |
| `SensitiveContent` | Prompt, input image, or generated output violated the upstream content policy | Change the prompt or image |
| `PromptInvalid` | Prompt was rejected or malformed | Rewrite the prompt with clearer safe content |
| `PromptLengthExceeded` | Prompt exceeded model limits | Shorten the prompt |
| `ImageFormatIncorrect` | Input image format could not be processed | Use a public JPG, PNG, or WebP URL |
| `Upload error` | Image upload failed or exceeded size limits | Compress the image and retry with a direct URL |
| `RateLimited` | The upstream route rate limited the task | Retry later with backoff |
| `Timeout` | The upstream route did not finish in time | Retry, reduce input complexity, or use callback mode |
| `Unknown error` | The upstream route returned an unmapped failure | Retry with backoff; contact support if it persists |
See [Error Codes](/api-reference/errors) for the full error reference.
## Related links
* [Generation API Overview](/models)
* [Generate Task](/api-reference/generate-task)
* [Status Task](/api-reference/status-task)
* [Webhooks](/api-reference/webhooks)
* [Error Codes](/api-reference/errors)
* [Parameter Specification](/api-reference/parameters)
* [Routing Strategies](/concepts/routing-strategies)
* [Pricing](https://apixo.ai/pricing)