Kuaishou

Kling 2.5

kling-2.5-turbo/image-to-video

An image-to-video model launched by Kuaishou, standing out for its smooth motion and character consistency, with support for negative prompts and CFG adjustment, making it suitable for generating short clips with highly dynamic camera work

kling-2.5-turbo/image-to-video kling-2.5-turbo/text-to-video

Try kling-2.5-turbo/image-to-video

Input

Showcases

View all showcases

Output

video

Fill in the parameters and run — results show up here.

Pricing

kling-2.5-turbo/image-to-video per second

Unit Price	$0.060

Positioning Overview

kling-2.5-turbo/image-to-video is a model for image-to-video tasks: it takes one or two images as the first frame and an optional last frame, combines them with a text prompt, and generates a short 5-second or 10-second video. It supports negative prompts and a prompt-adherence strength adjustment from 0 to 1, and the aspect ratio can be selected based on single-image or dual-image mode. It is suited to developers who need to turn static images into dynamic clips and want to control the visual content through parameters.

Core Highlights

Driven by first and last frame images — you can pass one first-frame image or also add a last-frame image, so the video starts from a specified image and transitions to a specified ending image.
Adjustable prompt adherence strength — cfg_scale adjusts between 0 and 1 how closely the video follows the text description, making it easy to trade off between creative freedom and strict reproduction.
Negative prompts exclude interference — supports negative prompts of up to 2496 characters, used to suppress content you do not want to appear in the frame.

Capability Details

First-frame and optional last-frame input: image_urls accepts 1 to 2 image URLs, supports jpeg/png/webp, with a maximum of 10MB per image; when two images are passed, the video is generated as a transition from the first frame to the last frame.

Duration and aspect ratio selection: duration can be 5 or 10 seconds; in single-image mode the aspect ratio supports 16:9, 9:16, 1:1, 4:3, 3:4, and 21:9, while dual-image mode is limited to 16:9, 9:16, and 1:1.

Prompt and negative prompt: prompt is required and up to 2500 characters, used to describe subject motion, environmental changes, and camera movement; negative_prompt is up to 2496 characters, used to exclude unwanted content.

Adherence adjustment: cfg_scale ranges from 0 to 1; the higher the value, the more closely the video follows the text description, so you can adjust how well the generated result matches the shot requirements.

Use Cases

Ad and product short-video creators: a single product image + motion description — turn a static product image into a short clip with camera movement, for dynamic display assets in brand or e-commerce videos.
Film and TV previsualization: concept images + specified first and last frames — use two concept images to lock the start and end frames, and generate a transition clip as a storyboard or concept preview.
Social media content operations: a vertical image + a short prompt — convert an image into a 5-second or 10-second vertical short video at 9:16, ready for direct publishing on social platforms.

Limitations and Selection Advice

A single generation is capped at 10 seconds, so it is not suitable for directly producing long videos; dual-image mode only supports 16:9, 9:16, and 1:1, while single-image mode may follow the original image's ratio during fallback processing and cannot guarantee an exact match to the requested size. WebP images are not converted automatically, and some fallback processing accepts only jpeg/png. Generation quality depends heavily on prompt writing and cfg_scale tuning. If you need to generate video directly from text, choose a text-to-video model from the same family.

What's new

View changelog →

New model Added kling-2.5-turbo/text-to-video docs Oct 10, 2026
New model New video model docs Oct 8, 2026

Create a generation task

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

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: kling-2.5-turbo/image-to-video

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for kling-2.5-turbo/image-to-video and route default — see the parameter table below.

promptstringRequiredminLength 1maxLength 2500

Text prompt describing the subject's motion, environmental changes, and camera movement, which determines the direction of the generated video content.

durationintegerOptionalDefault: 5min 5max 10

Select the number of seconds for the generated video as an integer, default 5.

Options:510

cfg_scalenumberOptionalmin 0max 1

Adjust how closely the video follows the text description; takes a numeric value, and the higher the value, the more closely it adheres to the prompt.

image_urlsarrayRequiredminItems 1maxItems 2

Array of image URLs for the first frame and an optional last frame, supporting jpeg/png/webp, max 10MB each; some fallback processing accepts only jpeg/png, WebP is not automatically converted, and with two images only 16:9, 9:16, or 1:1 is supported.

Array [ string ]

aspect_ratiostringOptionalDefault: "16:9"

Video aspect ratio, default 16:9; with a single image, fallback processing may follow the original image's ratio, and an exact match to the requested dimensions is not guaranteed; when image_urls is provided, only 16:9, 9:16, or 1:1 is supported.

Options:16:99:161:14:33:421:9

negative_promptstringOptionalmaxLength 2496

Content you do not want to appear in the video, as a string, up to 2496 characters.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-2.5-turbo/image-to-video",
  "input": {
    "prompt": "…",
    "duration": 5,
    "image_urls": "…",
    "aspect_ratio": "16:9"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "kling-2.5-turbo/image-to-video",
    input: {
      "prompt": "…",
      "duration": 5,
      "image_urls": "…",
      "aspect_ratio": "16:9"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "kling-2.5-turbo/image-to-video",
        "input": {
          "prompt": "…",
          "duration": 5,
          "image_urls": "…",
          "aspect_ratio": "16:9"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}