Skip to main content
Black Forest LabsAug 4, 2026

Flux 3

flux-3-text-to-videoAnonymized

Flux 3 is Black Forest Labs’ video model with synchronized audio. This text-to-video variant generates 5- to 20-second clips at up to 4K.

from$0.1872
per second of video
4K
max resolution, 4 sizes
20s
longest clip, from 5s
Mode

Same prompt, other models

Every video model renders the same reference prompts, so their clips line up side by side. Hover a clip to play it.

Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K

Pricing

Billed per clip in USD, by length and resolution. Each resolution is drawn to scale.

Price per clip by length and resolution
720p1080p1440p4K
5s clip$0.94$1.60$1.75$2.56
10s clip$1.87$3.19$3.49$5.11
15s clip$2.81$4.79$5.24$7.67
20s clip$3.74$6.38$6.98$10.22

Every clip comes with audio. Quoted from POST /video/quote on Nov 19, 2026. Prices can change, so quote a job before you queue it.

Estimate a batch

Resolution
Length
$0.94per 5s clip
$9.40for 10 clips

Against other video models

How it comparesamong 59 video models
Price per secondcheaper than 11%$0.1872
Longest cliplonger than 75%20s

Further right is better. Hover a dot for its model.

Capabilities

3 modes, each with its own model ID.

Text to videoflux-3-text-to-video
Takes prompt
Image to videoflux-3-image-to-video
Takes prompt and image
First & last frameflux-3-first-last-frame-to-video
Takes prompt, image and end frame
AudioGenerated with every clip

Aspect ratios

21:916:94:31:13:49:169:21

Specs

Model ID
flux-3-text-to-video
Mode
Text to video
Endpoint
POST /api/v1/video/queue
Resolutions
720p, 1080p, 1440p, 4K
Lengths
5s, 10s, 15s, 20s
Aspect ratios
auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21
Audio
Generated with every clip
Inputs
Prompt
Prompt limit
2,500 characters
Privacy
Anonymized
Weights
Closed
Added
Aug 4, 2026

Quickstart

Video is asynchronous: queue a job, then poll for the clip.

  1. 1QuotePOST /video/quoteOptional. Prices the job in USD without charging for it.
  2. 2QueuePOST /video/queueChecks and charges the job, then returns a queue_id at once.
  3. 3RetrievePOST /video/retrievePoll it with the queue_id until the video is ready.
# 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-text-to-video",
"prompt": "Slow aerial drone shot over a misty mountain valley at golden hour",
"duration": "5s",
"resolution": "720p",
"aspect_ratio": "auto"
}'

# 2. Poll until the MP4 is ready (JSON with the status until then)
curl https://api.venice.ai/api/v1/video/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "flux-3-text-to-video", "queue_id": "<queue_id>" }' --output video.mp4

# If the queue response has a download_url, retrieve only reports the
# status: download the MP4 from that URL once it is COMPLETED.
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelflux-3-text-to-videoRequired
promptUp to 2,500 charactersRequired
duration5s | 10s | 15s | 20sRequired
resolution720p | 1080p | 1440p | 2160pOptional
aspect_ratioauto | 21:9 | 16:9 | 4:3 | 1:1 | 3:4 | 9:16 | 9:21Required