Skip to content
English

Kling 2.5 Turbo Image-to-Video

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model ID kling-2.5-turbo/image-to-video
Type Video generation (image-to-video)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

Animate a first frame into 5- or 10-second video, optionally guiding the ending with a last frame. No audio track is included.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Frame transitions

Establish the scene with a first frame and guide its ending with a last frame.

promptimage_urls
Landscape, portrait and square

Frame the scene for its destination.

aspect_ratio

Request parameters

model string required

Fixed value kling-2.5-turbo/image-to-video.

example kling-2.5-turbo/image-to-video
input object required

Video generation settings.

prompt string required

Describe the subject, action, setting and camera movement in 1–2500 characters.

image_urls string[] required

Supply 1–2 images in [first frame, last frame] order; the second guides the ending. jpeg/png/webp, up to 10MB each; SVG is not supported.

duration enum optional

Length of the generated video in seconds.

default 5 enum: 510
aspect_ratio enum optional

Video aspect ratio. With a last frame, only 16:9, 9:16 and 1:1 are supported.

default 16:9 enum: 16:99:161:14:33:421:9
negative_prompt string optional

Describe unwanted content, up to 2496 characters.

cfg_scale number optional

Adjust prompt adherence from 0 to 1.

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback
when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Lighthouse in the storm

A first frame establishes the scene; the prompt adds surf, light and a slow push-in.

Request body
{
  "model": "kling-2.5-turbo/image-to-video",
  "input": {
    "prompt": "Waves crash against the rocks below, the lighthouse beam sweeps slowly across the storm clouds, mist drifts over the sea, slow cinematic push-in",
    "image_urls": [
      "https://dev-static.hiapi.ai/gallery/2026/10/f0ee80f89b4a25cc.jpg"
    ],
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated video from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

How do I frame a first/last-frame clip?

Choose 16:9, 9:16 or 1:1 with a last frame. A first frame alone also supports 4:3, 3:4 and 21:9. Keep the subject centered to preserve important details when cropped.

Can I change the resolution?

There is no resolution selector. Output is 1440×1440 for 1:1, 1920×1080 for 16:9 and 1080×1920 for 9:16. Other sizes are 1660×1244 for 4:3, 1244×1660 for 3:4 and 2200×940 for 21:9.

Does the video have sound?

Output has no audio track. Add voice, music or effects in editing.

Next steps