Skip to main content

Overview

Kling 3.0 Turbo is a fast Kuaishou video generation model on APIXO for short clips from text prompts or a single reference image. Use it when you want the Kling 3.0 family with a simpler surface than Kling 3.0 Std.
CapabilityValue
Model IDkling-3-0-turbo
Modestext-to-video, image-to-video
PromptRequired in both modes
Resolution720p, 1080p
Duration3-15 seconds
Aspect ratios16:9, 9:16, 1:1 for text-to-video
Reference imagesimage-to-video: exactly 1 image URL
OutputVideo URLs in resultJson.resultUrls

Endpoint and authentication

Base URL:
https://api.apixo.ai/api/v1
MethodEndpointPurpose
POST/generateTask/kling-3-0-turboSubmit a generation task
GET/statusTask/kling-3-0-turbo?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/kling-3-0-turbo" \
  -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 with a slow push-in",
      "duration": 12,
      "resolution": "720p",
      "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-turbo?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

Text-to-video

{
  "request_type": "async",
  "input": {
    "mode": "text-to-video",
    "prompt": "a cinematic city skyline at sunset with a slow push-in",
    "duration": 12,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }
}

Image-to-video

{
  "request_type": "async",
  "input": {
    "mode": "image-to-video",
    "prompt": "animate the portrait with a gentle camera move",
    "duration": 15,
    "resolution": "720p",
    "image_urls": [
      "https://example.com/source.png"
    ]
  }
}

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 URL that can receive the final task payload. See Webhooks.
input
object
required
Kling 3.0 Turbo input parameters.

Response format

Submit task response

POST /generateTask/kling-3-0-turbo 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. 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. Present after successful completion 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-turbo" \
  -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 camera move",
      "duration": 8,
      "resolution": "720p",
      "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 Turbo is billed per output second. text-to-video and image-to-video use the same pricing, and total cost is unit price * duration.
ResolutionUnit priceExample total
720p$0.112 / second12s: $1.344
1080p$0.14 / second15s: $2.10
For current route and market comparison pricing, see Pricing.

Latency and polling

Actual latency may vary by prompt complexity, selected resolution, route, and current queue load.
Request shapeTypical generation timeRecommended first pollPoll interval
3-5 second clip60s-90s60s after task creation5s-10s
6-10 second clip90s-120s60s after task creation5s-10s
11-15 second clip120s-180s60s after task creation5s-10s
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.

Errors and troubleshooting

HTTP errors

CodeMeaningWhat to do
400Invalid request body, mode, parameter, or image URLFix the request before retrying
401Missing or invalid API keyCheck the Authorization header
402Insufficient balance or quotaAdd balance or switch account/key
403Key or route cannot access the modelCheck permissions and route strategy
429Rate limit or concurrency limit reachedRetry with exponential backoff
500Server errorRetry with backoff
502Upstream service errorRetry with backoff
504Upstream timeoutRetry or use callback mode for long-running jobs

Task failure codes

Fail codeMeaningWhat to do
CONTENT_VIOLATIONPrompt or input media failed safety checksChange the prompt or input image
INVALID_PARAMETERA required field is missing or a value is unsupportedCheck mode, duration, resolution, aspect_ratio, and image_urls
INVALID_IMAGE_URLThe reference image could not be fetched or decodedUse a direct, publicly accessible image URL
INSUFFICIENT_BALANCEThe account does not have enough balance for the taskAdd balance before retrying
UPSTREAM_ERRORUpstream generation failedRetry with backoff
UNKNOWN_ERRORThe failure could not be mapped to a more specific codeRetry later or contact support with the taskId

Common validation issues

IssueFix
Missing modeSet input.mode to text-to-video or image-to-video
Missing promptProvide a non-empty prompt string
Unsupported durationUse 3 through 15 seconds
Unsupported resolutionUse 720p or 1080p
Aspect ratio has no effectaspect_ratio is only forwarded for text-to-video
image-to-video fails validationProvide exactly 1 image URL in image_urls
See Error Codes for the full error reference.