Kling O1

For silent scenes that combine a first frame with character or product reference images. References guide appearance; strict character locking through Elements is unavailable in our integration.

Cost

from 5.5 tokens/s

VideoProvider: Kling

Try Kling O1 in Givon AI

Open a working project for regular creation, or use Playground to inspect the model parameters.

Create in a project Open in playground Use through API

Use through API

Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.

Run generation

IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"kling-o1","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","resolution":"720p","duration":5,"referenceAssetUris":["asset://asset_..."]}}'

Input fields

* required

Field	Type	Default	Allowed
prompt*`prompt` Generation prompt describing the scene, action and direction.	string	—	up to 2500 chars
aspectRatio`aspectRatio`	string	9:16	16:9, 9:16, 1:1
resolution`resolution`	string	720p	720p, 1080p
duration`duration`	number	5	5, 10
Start image`startImage` Asset input for the startImage slot.	string	—	image · asset, https, data
End image`endImage` Asset input for the endImage slot.	string	—	image · asset, https, data
Reference video`referenceVideo` Asset input for the referenceVideo slot.	string	—	video · asset, https, data
Source video`sourceVideo` Asset input for the sourceVideo slot.	string	—	video · asset, https, data
Reference images`referenceAssetUris` Optional reference assets as asset:// URIs, HTTPS URLs, or data URIs. The item limit applies to physical references after repeated owned asset identities and identities already bound to video slots are excluded. URL entries remain distinct; every supplied item is validated.	array	—	image · up to 7 · asset, https, data

prompt*prompt

Generation prompt describing the scene, action and direction.

Type: string
Default: —
Allowed: up to 2500 chars

aspectRatioaspectRatio

Type: string
Default: 9:16
Allowed: 16:9, 9:16, 1:1

resolutionresolution

Type: string
Default: 720p
Allowed: 720p, 1080p

durationduration

Type: number
Default: 5
Allowed: 5, 10

Start imagestartImage

Asset input for the startImage slot.

Type: string
Default: —
Allowed: image · asset, https, data

End imageendImage

Asset input for the endImage slot.

Type: string
Default: —
Allowed: image · asset, https, data

Reference videoreferenceVideo

Asset input for the referenceVideo slot.

Type: string
Default: —
Allowed: video · asset, https, data

Source videosourceVideo

Asset input for the sourceVideo slot.

Type: string
Default: —
Allowed: video · asset, https, data

Reference imagesreferenceAssetUris

Optional reference assets as asset:// URIs, HTTPS URLs, or data URIs. The item limit applies to physical references after repeated owned asset identities and identities already bound to video slots are excluded. URL entries remain distinct; every supplied item is validated.

Type: array
Default: —
Allowed: image · up to 7 · asset, https, data

Cost

from 5.5 tokens/s

720pdefault5.5 tk/s

1080p7.5 tk/s

The variant is selected automatically from request fields, so you do not need to send it.

Capabilities

Modesvideo_editvideo_referenceimage_to_videotext_to_video

Asset slotsstartImage:imageendImage:imagereferenceVideo:videosourceVideo:videoreferenceAssetUris:image[]<=7

Get API key

Where to use this model

AI video generator Image to video