Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://toapis.com/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "kling-2-6",
    "prompt": "A golden cat running on a sunlit meadow, slow motion, cinematic quality",
    "mode": "std",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

{
  "id": "video_01J9HA7JPQ9A0Z6JZ3V8M9W6PZ",
  "object": "generation.task",
  "model": "kling-2-6",
  "status": "queued",
  "progress": 0,
  "created_at": 1768380224,
  "metadata": {}
}
  • Async processing mode, returns task ID for subsequent queries
  • Supports text-to-video, image-to-video (first frame / first-last frame control)
  • Supports standard mode (720P) and professional mode (1080P)
  • Professional mode supports automatic audio generation

​
Authorization

​
Authorization
string
required
All API endpoints require Bearer Token authenticationGet your API Key: Visit the API Key Management Page to get your API KeyAdd it to the request header:
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

​
model
string
required
Video generation model name, fixed as kling-2-6
​
prompt
string
required
Text prompt, maximum 2500 charactersDescribe scenes, actions, and styles in detail for better generation resultsExample: "A golden cat running on a sunlit meadow, slow motion, cinematic quality"
​
mode
string
default:"std"
Generation modeOptions:
  • std - Standard mode (720P, silent video only)
  • pro - Professional mode (1080P, supports automatic audio generation)
Default: std
Standard mode limitation: std mode only supports silent video. The audio parameter requires pro mode.
​
duration
integer
default:"5"
Video duration (seconds)Options: 5 or 10Default: 5
​
aspect_ratio
string
default:"16:9"
Video aspect ratioOptions:
  • 16:9 - Landscape (default)
  • 9:16 - Portrait
  • 1:1 - Square
Default: 16:9
​
negative_prompt
string
Negative prompt to exclude unwanted contentExample: "blurry, low quality, distorted"
​
image_urls
string[]
Image URL array for image-to-video generation
  • Pass 1 image: used as first frame
  • Pass 2 images: automatically assigned as first frame + last frame (requires mode: "pro")
Maximum 2 images supportedExample: ["https://example.com/first.jpg"]
  • Maximum 2 images supported
  • Last frame (2 images) requires pro mode only; std mode only supports first frame (1 image)
  • Last frame and audio are mutually exclusive: In pro mode, last frame (2 images) and audio (audio: true) cannot be used together
  • In image-to-video mode, aspect_ratio may be overridden by the actual image ratio
​
audio
boolean
default:"false"
Whether to automatically generate audioDefault: false
  • Only available in mode: "pro"
  • Mutually exclusive with last frame: Audio cannot be used together with last frame (2 images)
​
watermark
boolean
Whether to add watermark

​
Pricing

Billed per second, price varies by mode and audio setting:
ModeResolutionAudioPrice
std720PNot supported$0.0368 / sec
pro1080POff$0.0625 / sec
pro1080POn$0.125 / sec
Example: pro mode, 10-second video without audio = 10 × 0.0625=0.0625 = 0.625

​
Feature Support Matrix

TypeFeaturestd 5sstd 10spro 5spro 10s
Text-to-VideoGeneration✅ (silent only)✅ (silent only)✅✅
Text-to-VideoAuto Audio--✅✅
Image-to-VideoGeneration✅ (silent only)✅ (silent only)✅✅
Image-to-VideoFirst Frame✅✅✅✅
Image-to-VideoLast Frame--✅✅
Image-to-VideoAuto Audio--✅✅
In pro mode, last frame and audio control are mutually exclusive and cannot be used together.

​
Response

​
id
string
Unique task identifier for querying task status
​
object
string
Object type, fixed as generation.task
​
model
string
Model name used for generation
​
status
string
Task status
  • queued - Waiting to be processed
  • in_progress - Processing
  • completed - Successfully completed
  • failed - Failed
​
progress
integer
Task progress percentage (0-100)
​
created_at
integer
Task creation Unix timestamp

​
Use Cases

​
Case 1: Text-to-Video (Standard Mode)

{
  "model": "kling-2-6",
  "prompt": "A golden cat running on a sunlit meadow, slow motion, cinematic quality",
  "mode": "std",
  "duration": 5,
  "aspect_ratio": "16:9"
}

​
Case 2: Text-to-Video (Pro Mode + Negative Prompt)

{
  "model": "kling-2-6",
  "prompt": "Tokyo Shibuya crossing at night, neon lights reflected on wet ground, people walking with umbrellas",
  "negative_prompt": "blurry, low quality, distorted",
  "mode": "pro",
  "duration": 10,
  "aspect_ratio": "16:9"
}

​
Case 3: Image-to-Video (First Frame)

{
  "model": "kling-2-6",
  "prompt": "The person in the frame turns and smiles",
  "image_urls": ["https://example.com/portrait.jpg"],
  "mode": "std",
  "duration": 5
}

​
Case 4: Image-to-Video (First + Last Frame Control)

{
  "model": "kling-2-6",
  "prompt": "City timelapse transitioning from day to night",
  "image_urls": ["https://example.com/day-city.jpg", "https://example.com/night-city.jpg"],
  "mode": "pro",
  "duration": 5
}

​
Case 5: Pro Mode + Auto Audio

{
  "model": "kling-2-6",
  "prompt": "Waves crashing against rocks, seagulls circling in the sky, lighthouse in the distance",
  "mode": "pro",
  "duration": 10,
  "audio": true,
  "aspect_ratio": "16:9"
}
Query Task ResultsVideo generation is an async task that returns a task ID upon submission. Use the Get Task Status endpoint to query generation progress and results.
curl --request POST \
  --url https://toapis.com/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "kling-2-6",
    "prompt": "A golden cat running on a sunlit meadow, slow motion, cinematic quality",
    "mode": "std",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

{
  "id": "video_01J9HA7JPQ9A0Z6JZ3V8M9W6PZ",
  "object": "generation.task",
  "model": "kling-2-6",
  "status": "queued",
  "progress": 0,
  "created_at": 1768380224,
  "metadata": {}
}