API docs / Video models

Kling 2.1 API

Generate 5 or 10 second videos from a starting image and text prompt. Requires a starting image as input and produces videos at 720p resolution in standard mode or 1080p resolution in pro mode, both at 24fps. Pro mode additionally supports an optional end image to control the final frame of the video. Accepts negative prompts to specify unwanted elements in the generated video.

Model id
kwaivgi/kling-v2.1
Provider
Kling
Output
Video
Price
From 88 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "kwaivgi/kling-v2.1". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "kwaivgi/kling-v2.1",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light",
    "first_frame": [
      "https://example.com/input.png"
    ]
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptrequiredstring

Text prompt for video generation

first_framerequiredarray of URLs

First frame of the video. You must use a start image with kling-v2.1.

Up to 1 files · Accepts image/*

last_framearray of URLs

Last frame of the video (pro mode is required when this parameter is set)

Up to 1 files · Accepts image/*

duration_secondsnumber

Default: 5

One of: 5, 10

negative_promptstring

Things you do not want to see in the video

Default:

modestring

Default: standard

One of: standard, pro