Kling O1

Kling O1 是一款多輸入影片模型,支援文字生影片、圖生影片、首尾幀生成、多模態參考與影片編輯,時長最高可達 10 秒。它適合需要控制鏡頭起止狀態、維持角色或產品特徵、結合多種參考素材,以及對既有影片進行改寫的創作流程。你可以在試驗場中選擇生成或編輯方式,調整輸入素材、時長、解析度與畫面比例,在正式串接前比較動作連貫性、參考一致性、編輯效果、生成速度與成本。具體可用能力與參數範圍以目前頁面為準。

A martial arts performer in red completing a sweeping turn in a modern rehearsal hall
模型識別碼
kling-o1
供應商
Kling
API 端點
/v1/videos
計費
0.176470588235
更新時間
2026-08-13

能力

  • 透過目前公開任務端點生成影片
  • 即時 Schema 提供時支援圖片、參考素材、時長或解析度控制
  • 目前參數包括 prompt, operation, resolution

限制

  • 模型能力與參數範圍可能更新,正式環境應鎖定並驗證使用的參數組合
  • 未出現在即時 Request Schema 中的參數不應假定可用
  • 非同步任務需要處理輪詢、失敗、逾時與內容安全狀態

典型情境

  • 產品原型與自動化內容工作流程
  • 批次媒體生成與程式化創作
  • 需要統一驗證、計費與呼叫記錄的多模型應用

價格與計費範例

  • PRO video editing | 0.176470588235 | input_video_seconds | {"operation":"video.edit","resolution_tier":"pro"}
  • STD video editing | 0.132352941176 | input_video_seconds | {"operation":"video.edit","resolution_tier":"std"}
  • PRO video without references | 0.117647058824 | output_video_seconds | {"input_videos":0,"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"pro"}
  • PRO video with references | 0.176470588235 | output_video_seconds | {"input_videos":{"gte":1},"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"pro"}
  • STD video without references | 0.088235294118 | output_video_seconds | {"input_videos":0,"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"std"}
  • STD video with references | 0.132352941176 | output_video_seconds | {"input_videos":{"gte":1},"operation":["video.generate","video.image_to_video","video.reference_to_video"],"resolution_tier":"std"}

請求參數

參數類型必填預設值可選值
modelstring
prompttextarea
operationselecttext_to_videotext_to_video, image_to_video, first_last_frame, reference_to_video, edit_video
resolutionselectstdstd, pro
durationinteger5
aspect_ratioselect16:916:9, 9:16, 1:1
imageasset_list
last_imageasset_list
reference_image_urlsasset_list
watermarkbooleanfalse

API 串接範例

cURL

curl -X POST 'https://api.uniall.ai/v1/videos' \
  -H 'Authorization: Bearer $UNIALL_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"aspect_ratio":"16:9","duration":5,"model":"kling-o1","operation":"text_to_video","prompt":"Describe the output you want","resolution":"std","watermark":false}'

Python

import json
import requests

payload = json.loads(r'''{"aspect_ratio":"16:9","duration":5,"model":"kling-o1","operation":"text_to_video","prompt":"Describe the output you want","resolution":"std","watermark":false}''')
response = requests.post(
    "https://api.uniall.ai/v1/videos",
    headers={"Authorization": "Bearer " + UNIALL_API_KEY},
    json=payload,
)
response.raise_for_status()
result = response.json()

JavaScript

const response = await fetch("https://api.uniall.ai/v1/videos", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.UNIALL_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({"aspect_ratio":"16:9","duration":5,"model":"kling-o1","operation":"text_to_video","prompt":"Describe the output you want","resolution":"std","watermark":false}),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
const result = await response.json();

常見問題

kling-o1 的 API 端點是甚麼?

端點會依目前模型能力與 Request Schema 自動解析,並顯示於本頁 API 區域。

kling-o1 如何計費?

價格區域直接讀取目前的結構化計費設定;改價後不需要重寫本文。

可以使用 Python 串接嗎?

可以。本頁範例使用目前端點與原始模型程式碼識別碼。

是否提供 JavaScript 與 cURL 範例?

提供。三種範例共用同一個即時請求結構。

支援哪些解析度、時長或參考圖參數?

支援範圍取決於目前 Request Schema,未顯示的欄位不應假定可用。

正式環境串接時要注意甚麼?

請驗證參數、逾時、錯誤處理與非同步影片任務狀態,並在模型更新後重新執行小範圍測試。