GIVON AI
← All models

H3 Max Extend

Extends an existing video from a text prompt, returning the source followed by 5–15 seconds of new footage. Accepts a 2–60 second source video and outputs at 480P or 768P.

Cost

from 130 tokens/s

VideoProvider: Fal

Try H3 Max Extend in Givon AI

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

Create in a projectOpen in playgroundUse 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":"minimax-h3-max-extend-video","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"auto","resolution":"768p","duration":5,"sourceVideo":"asset://asset_..."}}'

Input fields

* required
prompt*prompt

Generation prompt describing the scene, action and direction.

Type
string
Default
—
Allowed
up to 7000 chars
aspectRatioaspectRatio
Type
string
Default
auto
Allowed
auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
resolutionresolution
Type
string
Default
768p
Allowed
480p, 768p
durationduration
Type
number
Default
5
Allowed
5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
Source video*sourceVideo

Asset input for the sourceVideo slot.

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

Cost

from 130 tokens/s
480P130 tk/s
768Pdefault270 tk/s

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

Capabilities

Modesvideo_extend
Asset slotssourceVideo:video*
Get API key

Where to use this model

AI video generatorImage to video