Flux 3 Extend
Flux 3 Extend continues an existing clip beyond its final frame, adding 5 to 20 seconds at up to 4K with synchronized audio.
From
By source
priced per second of input
Draft clip
—
Production clip
—
Max resolution
4K
4 options
Duration
5–20s
4 options
Audio
Native
Pricing
USD per clipThis mode bills by the length of the source video you upload. Call POST /video/quote with your video_url for an exact price before queueing.
Examples
Specs
- Model ID
flux-3-extend-video- Endpoint
POST /api/v1/video/queue- Mode
- Video edit
- Inputs
- Prompt, video
- Resolutions
- 720p, 1080p, 1440p, 4K
- Durations
- 5s, 10s, 15s, 20s
- Aspect ratios
- auto21:916:94:31:13:49:169:21
- Audio
- Always generated
- Added
- Aug 4, 2026
POST
/api/v1/video/queue# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "flux-3-extend-video",
"prompt": "Continue the drone shot as it rises above the clouds into clear sky",
"duration": "5s",
"resolution": "720p",
"aspect_ratio": "auto",
"video_url": "https://example.com/source.mp4"
}'
# 2. Poll until the MP4 is ready
curl https://api.venice.ai/api/v1/video/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "flux-3-extend-video", "queue_id": "<queue_id>" }' --output video.mp4Privacy
Tier 1 · this model
Anonymized
Venice hides your identity and stores no prompts. Black Forest Labs still sees the content.
Tier 2
Private
Not available
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available