> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apipod.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Kling 3.0 图生视频

> Kling 3.0 I2V 是 APIPod 面向快手可灵 Kling 3.0 提供的首尾帧图生视频模式，支持多镜头分镜与可选原生音频。

## 使用说明

* **首尾帧**：`image_urls` 为必填项，需提供 1-2 张图片。`multi_shot` 为 false 时，2 张图依次为首帧（`image_urls[0]`）与尾帧（`image_urls[1]`），1 张图作为首帧；`multi_shot` 为 true 时仅支持首帧。输出画幅跟随首帧。
* **多镜头**：将 `multi_shot` 设为 `true`，并在 `multi_prompt` 中描述最多 5 个镜头（`{prompt, duration}`，每个 1-12 秒、最多 500 字）。镜头总时长不得超过 `duration`；省略 `duration` 时取各镜头时长之和，此时 `prompt` 也可省略。
* **音频**：`generate_audio` 单镜头默认 `false`，多镜头默认 `true`。
* **提示词**：单镜头请求必填；多镜头模式下请把每个镜头的描述写进 `multi_prompt`。
* **不支持**：`kling_elements`、`aspect_ratio`（画幅跟随首帧）、`negative_prompt`（请把排除项写进 prompt）、顶层 `audio_urls`、`video_url`。

## 计费

按输出视频时长逐秒计费。每秒费率分五档：720p / 1080p 各自区分是否开启原生音频，另有 4K 一档（有无音频同价）。具体价格以 [模型页](https://www.apipod.ai/models) 展示为准。

## 任务流程

创建请求返回 `data.task_id`。使用[查询视频任务](/zh-CN/query-video-task)轮询，直到 `status` 变为 `completed`（结果位于 `data.result`）或 `failed`；也可以传入 `callback_url`，在任务进入终态时接收通知。


## OpenAPI

````yaml api-reference/openapi/kling-3.0--kling-3.0-i2v.zh.yaml POST /v1/videos/generations
openapi: 3.1.0
info:
  title: Kling 3.0 Image to Video API
  version: 1.0.0
  description: >-
    Kling 3.0 I2V 是 APIPod 面向快手可灵 Kling 3.0 提供的首尾帧图生视频模式，要求提供首帧，可选提供尾帧。在 APIPod
    中，公开模型 ID 为 kling-3.0-i2v。它支持多镜头和可选原生音频，并通过异步视频任务返回结果。
servers:
  - url: https://api.apipod.ai
    description: 生产环境
security: []
paths:
  /v1/videos/generations:
    post:
      tags:
        - Kling 3.0 Image to Video
      summary: 创建生成任务
      description: >-
        Kling 3.0 I2V 是 APIPod 面向快手可灵 Kling 3.0 提供的首尾帧图生视频模式，要求提供首帧，可选提供尾帧。在
        APIPod 中，公开模型 ID 为 kling-3.0-i2v。它支持多镜头和可选原生音频，并通过异步视频任务返回结果。
      operationId: create-kling-3.0-kling-3.0-i2v
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              title: Kling 3.0 Image to Video
              properties:
                model:
                  type: string
                  title: Model ID
                  description: APIPod 公开模型 ID。
                  const: kling-3.0-i2v
                prompt:
                  type: string
                  title: Prompt
                  description: 描述画面运动的文本提示词，最多 2500 字。未提供 `multi_prompt` 时必填。
                  maxLength: 2500
                image_urls:
                  type: array
                  title: Image Urls
                  description: >-
                    首尾帧图片（必填）。`multi_shot` 为 false 时，2 张图依次为首帧（下标 0）与尾帧（下标 1），1
                    张图作为首帧；`multi_shot` 为 true 时仅支持首帧。也接受 `first_frame_image` /
                    `last_frame_image`。输出宽高比跟随首帧。
                  minItems: 1
                  maxItems: 2
                  items:
                    type: string
                duration:
                  type: integer
                  title: Duration
                  description: 输出时长（秒），3-15，默认 5；多镜头模式下省略时取各镜头时长之和。
                  minimum: 3
                  maximum: 15
                  default: 5
                resolution:
                  type: string
                  title: Resolution
                  description: 输出分辨率（最高 4K），默认 720p。每秒费率取决于分辨率；720p / 1080p 还区分是否开启原生音频。
                  enum:
                    - 720p
                    - 1080p
                    - 4k
                  default: 720p
                generate_audio:
                  type: boolean
                  title: Generate Audio
                  description: 是否生成原生音频（别名 `audio`）。单镜头默认 false，多镜头默认 true。
                multi_shot:
                  type: boolean
                  title: Multi Shot
                  description: 开启多镜头生成（兼容 `multi_shots`）。配合 `multi_prompt` 定义每个镜头。
                multi_prompt:
                  type: array
                  title: Multi Prompt
                  description: >-
                    多镜头分镜列表，最多 5 个镜头。每个镜头为 `{prompt, duration}`，prompt 最多 500
                    字，时长 1-12 秒；总时长不得超过 `duration`。
                  maxItems: 5
                  items:
                    type: object
                    properties:
                      prompt:
                        type: string
                        description: 镜头描述，最多 500 字。
                        maxLength: 500
                      duration:
                        type: integer
                        description: 镜头时长（秒），1-12。
                        minimum: 1
                        maximum: 12
                    required:
                      - prompt
                      - duration
                callback_url:
                  type: string
                  title: Callback URL
                  description: 接收任务终态通知的 HTTPS 地址。
                  default: ''
              required:
                - model
                - image_urls
            examples:
              basic:
                summary: 首尾帧
                value:
                  model: kling-3.0-i2v
                  prompt: >-
                    The camera slowly pushes in as the dancer spins and lands in
                    the final pose.
                  image_urls:
                    - https://cdn.example.com/first-frame.jpg
                    - https://cdn.example.com/last-frame.jpg
                  duration: 5
                  resolution: 1080p
                  generate_audio: false
              multi_shot:
                summary: 首帧 + 多镜头
                value:
                  model: kling-3.0-i2v
                  image_urls:
                    - https://cdn.example.com/first-frame.jpg
                  multi_shot: true
                  multi_prompt:
                    - prompt: >-
                        Wide shot: a lighthouse on a rocky cliff at dawn, waves
                        crashing below.
                      duration: 2
                    - prompt: >-
                        Close-up: the lighthouse keeper opens the door and looks
                        at the sea.
                      duration: 3
                  duration: 5
                  resolution: 720p
      responses:
        '200':
          description: 任务已受理
          content:
            application/json:
              schema:
                type: object
                title: Task Submit Response
                description: Standard response for task submission
                properties:
                  code:
                    type: integer
                    description: HTTP 状态码。
                  data:
                    type: object
                    title: Task Submit Data
                    description: 响应数据。
                    properties:
                      task_id:
                        type: string
                        description: 用于查询任务状态的 APIPod 任务 ID。
                  message:
                    type: string
                    description: 响应消息。
                required:
                  - code
                  - message
                  - data
              example:
                code: 200
                message: success
                data:
                  task_id: vid_task_01JEXAMPLE
      security:
        - bearerAuth: []
      x-codeSamples:
        - lang: Shell
          label: cURL
          source: |-
            curl https://api.apipod.ai/v1/videos/generations \
              -H "Authorization: Bearer $APIPOD_API_KEY" \
              -H "Content-Type: application/json" \
              -d '{
              "model": "kling-3.0-i2v",
              "prompt": "The camera slowly pushes in as the dancer spins and lands in the final pose.",
              "image_urls": [
                "https://cdn.example.com/first-frame.jpg",
                "https://cdn.example.com/last-frame.jpg"
              ],
              "duration": 5,
              "resolution": "1080p",
              "generate_audio": false
            }'
        - lang: Python
          label: Python
          source: |-
            import os
            import requests

            payload = {
              "model": "kling-3.0-i2v",
              "prompt": "The camera slowly pushes in as the dancer spins and lands in the final pose.",
              "image_urls": [
                "https://cdn.example.com/first-frame.jpg",
                "https://cdn.example.com/last-frame.jpg"
              ],
              "duration": 5,
              "resolution": "1080p",
              "generate_audio": False
            }

            response = requests.post(
                "https://api.apipod.ai/v1/videos/generations",
                headers={
                    "Authorization": f"Bearer {os.environ['APIPOD_API_KEY']}",
                    "Content-Type": "application/json",
                },
                json=payload,
                timeout=60,
            )
            response.raise_for_status()
            print(response.json())
        - lang: Go
          label: Go
          source: |-
            package main

            import (
                "bytes"
                "fmt"
                "io"
                "net/http"
                "os"
            )

            func main() {
                body := []byte(`{
              "model": "kling-3.0-i2v",
              "prompt": "The camera slowly pushes in as the dancer spins and lands in the final pose.",
              "image_urls": [
                "https://cdn.example.com/first-frame.jpg",
                "https://cdn.example.com/last-frame.jpg"
              ],
              "duration": 5,
              "resolution": "1080p",
              "generate_audio": false
            }`)

                req, err := http.NewRequest(http.MethodPost, "https://api.apipod.ai/v1/videos/generations", bytes.NewReader(body))
                if err != nil {
                    panic(err)
                }
                req.Header.Set("Authorization", "Bearer "+os.Getenv("APIPOD_API_KEY"))
                req.Header.Set("Content-Type", "application/json")

                resp, err := http.DefaultClient.Do(req)
                if err != nil {
                    panic(err)
                }
                defer resp.Body.Close()
                out, _ := io.ReadAll(resp.Body)
                fmt.Println(resp.Status, string(out))
            }
        - lang: Rust
          label: Rust
          source: |-
            use reqwest::Client;
            use serde_json::json;
            use std::env;

            #[tokio::main]
            async fn main() -> Result<(), Box<dyn std::error::Error>> {
                let payload = json!({
                  "model": "kling-3.0-i2v",
                  "prompt": "The camera slowly pushes in as the dancer spins and lands in the final pose.",
                  "image_urls": [
                    "https://cdn.example.com/first-frame.jpg",
                    "https://cdn.example.com/last-frame.jpg"
                  ],
                  "duration": 5,
                  "resolution": "1080p",
                  "generate_audio": false
                });
                let response = Client::new()
                    .post("https://api.apipod.ai/v1/videos/generations")
                    .bearer_auth(env::var("APIPOD_API_KEY")?)
                    .json(&payload)
                    .send()
                    .await?
                    .error_for_status()?;

                println!("{}", response.text().await?);
                Ok(())
            }
        - lang: JavaScript
          label: JavaScript
          source: >-
            const response = await
            fetch("https://api.apipod.ai/v1/videos/generations", {
              method: "POST",
              headers: {
                Authorization: `Bearer ${process.env.APIPOD_API_KEY}`,
                "Content-Type": "application/json",
              },
              body: JSON.stringify({
                "model": "kling-3.0-i2v",
                "prompt": "The camera slowly pushes in as the dancer spins and lands in the final pose.",
                "image_urls": [
                  "https://cdn.example.com/first-frame.jpg",
                  "https://cdn.example.com/last-frame.jpg"
                ],
                "duration": 5,
                "resolution": "1080p",
                "generate_audio": false
              }),
            });


            if (!response.ok) {
              throw new Error(`APIPod request failed: ${response.status} ${await response.text()}`);
            }


            console.log(await response.json());
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: APIPod API key
      description: 在 Authorization 请求头中以 Bearer Token 形式传入 APIPod API Key。

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.