Skip to main content
POST

Overview

Extend Video takes a video from your team’s media library and continues it: the model starts from the last frame and generates new footage that follows your prompt. Longer extensions are made of several clips, each one starting from the last frame of the previous one. The output keeps the source video’s aspect ratio.
media is the id of a video in your team’s media library. Add one with Upload Media or Import Media from URL, or find it with List Media; it must be COMPLETED.

Models

model picks the video model that continues the clip (default veo_3_fast). Any model that can start from a frame: targetDuration is rounded to the nearest multiple of 4 and split into clips of these lengths; a remainder shorter than the model’s shortest clip takes that clip, so the extension (and the charge) can be a few seconds longer than asked.
prompt, targetDuration, model, resolution and generateAudio go at the top level of the body. Validation errors name them under extendVideoSettings (for example extendVideoSettings.prompt: Required).


What happens next

The clips are generated one after another, joined to the source video and rendered. Either:
  • poll GET /v1/project/{projectId} until data.video is present and data.video.status is COMPLETED, then download data.video.url; or
  • pass webhook and wait for the COMPLETED (or FAILED) call described in Webhooks:

Credits and your own keys

  • Managed teams (Hooked’s provider keys) pay in credits: a base of 7 credits plus the model’s price per second of generated footage at the resolution it runs at. For the default Veo 3.1 Fast that is 11 credits per second at 1080p and 10 at 720p, so the default 4-second extension at 1080p costs 51 credits. The balance is checked when you create the project and the credits are taken when processing starts. If the project fails, they are refunded automatically.
  • Teams on their own provider keys (BYOK) are not charged credits. They need an OpenRouter key in Settings → AI keys (every extension model runs on it). Without it the request answers 402 missing_credentials before anything is created or charged.

Errors

Send an Idempotency-Key header to retry safely: if a request times out or answers 5xx, sending it again with the same key and body returns the first answer instead of creating (and charging) the project twice.

Project details

Follow the project until its video is ready

Webhooks

Payloads and delivery rules

Add Captions

Caption the extended video

List Videos

Your rendered videos

Authorizations

x-api-key
string
header
required

Headers

Idempotency-Key
string

Makes the request safe to retry. 1-255 printable ASCII characters, one per operation (your job id, or a UUID you store), reused on every retry. Within 24 hours the same key with the same body answers with the first response and the header Idempotent-Replayed: true, without running or charging again. Keys are scoped to your team and the endpoint. 5xx answers and refusals before anything ran (401, 402, 403, 409, 429) are not kept. See Idempotency.

Required string length: 1 - 255
Pattern: ^[\x20-\x7E]+$

Body

application/json
media
string
required

ID of a video in your team's library (add one with POST /v1/media/upload or POST /v1/media/import). The output keeps its aspect ratio. An unknown ID or another team's media answers 400 Media not found; an image answers 400 Media is not a video. A media that is not COMPLETED yet (an import or upload in progress) answers 400 media: Media "<id>" is not ready (status PROCESSING).

prompt
string
required

What happens next in the video

Required string length: 1 - 2000
name
string

Project name (max 100 characters). Generated from the prompt when omitted.

Maximum string length: 100
targetDuration
number
default:4

Seconds to add. Rounded to the nearest multiple of 4, then split into clips of the lengths the model makes (Veo: 4, 6 or 8 s; Kling and Seedance: 5 or 10 s; Wan: 5, 10 or 15 s; Grok: 4, 6, 8, 10 or 15 s). A remainder shorter than the model's shortest clip takes that clip, so the extension (and the charge) can be a few seconds longer than asked.

Required range: 4 <= x <= 60
resolution
enum<string>
default:1080p

Output resolution. A model that does not make the one asked for runs at its own default (720p for Seedance 2.0 Fast and Mini). The price follows the resolution it runs at.

Available options:
720p,
1080p
generateAudio
boolean
default:false

Generate a soundtrack for the new footage. Ignored by models without audio (wan_2_7_i2v).

model
enum<string>
default:veo_3_fast

The video model that continues the clip. Default: Veo 3.1 Fast. veo_3 = Veo 3.1 Standard, veo_3_1_lite = Veo 3.1 Lite, kling_3_0 = Kling 3.0 Standard, kling_3_0_pro = Kling 3.0 Pro, seedance_2_0 / seedance_2_0_fast / seedance_2_0_mini = Seedance 2.0 (Fast and Mini run at 720p at most), grok_imagine_video = Grok Imagine, wan_2_7_i2v = Wan (no audio). Any other value answers 400 extendVideoSettings.model: "<value>" cannot extend a video.

Available options:
veo_3_fast,
veo_3,
grok_imagine_video,
grok_imagine_video_lite,
kling_3_0,
kling_3_0_pro,
seedance_2_0,
seedance_2_5,
wan_2_7_i2v,
seedance_2_0_fast,
veo_3_1_lite,
seedance_2_0_mini
webhook
string<uri>

HTTPS URL on a public host, called when the video is ready or the project fails (max 500 characters). Requests are signed: verify the Hooked-Signature header (HMAC-SHA256 of ".") with the signing secret from Settings → Webhooks; Hooked-Event and Hooked-Delivery headers name the event and the delivery. No redirects are followed; 10 s timeout; 3 immediate attempts. See the Webhooks guide for the payload.

Maximum string length: 500
metadata
object

Any JSON object of your own (max 5 KB). Sent back in the webhook payload. The key automationId is reserved for dashboard automations and is removed.

Response

Project created. Follow it with GET /v1/project/{projectId} or wait for the webhook.

success
enum<boolean>
required
Available options:
true
data
object
required
message
string
required