Black Forest Labs: FLUX 3 Video

FLUX 3 Video turns a scene description into a short video clip. The current five-second, 720p format lends itself to motion sketches, animated concepts, and testing a shot before developing a longer sequence.

Compare models

flux-3-video

AvailableBlack Forest LabsVideoAsync

Price: From $0.17
Modalities: Video

About FLUX 3 Video

FLUX 3 Video is Black Forest Labs' video model in the FLUX.3 family. It turns a written scene description into a short text-to-video clip at 720p and five seconds. The fixed format suits motion sketches, animated concepts, and testing a shot before developing a longer sequence.

Where it works well

Turns a written scene description into a finished 720p clip, with camera move, lighting and subject action all set in the prompt.
The fixed five-second length keeps every test clip comparable, so wording changes show up directly in the result.
One text-to-video operation keeps integration simple: a prompt goes in and a clip comes back.

When to choose another model

Clips are 720p and five seconds long, so longer or higher-resolution output is not available.
It takes text prompts only; it does not start from keyframe images or continue an existing video.
Short clips make it a tool for shot tests, not complete scenes.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image to videoStart and end frames to videoText to videoTokenLab endpoint

POST/v1/videos/generations

curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "duration": 5,
  "operation": "text-to-video",
  "output_audio": false,
  "resolution": "720p",
  "model": "flux-3-video",
  "prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
}'

Parameters

Image to video

Parameter	Values and limits	Default	Notes
`duration`	5	Not provided	Not provided
`image`	Inputs: ≥ 1, ≤ 1	Not provided	First frame: a public image URL or a data URL. image and image_url are aliases; send one.
`image_url`	Inputs: ≥ 1, ≤ 1	Not provided	First frame: a public image URL or a data URL. image and image_url are aliases; send one.
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	720p	Not provided	Not provided

Start and end frames to video

Parameter	Values and limits	Default	Notes
`duration`	5	Not provided	Not provided
`end_image`	Inputs: ≥ 1, ≤ 1	Not provided	Last frame: a public image URL or a data URL. A request with end_image is start-end-to-video.
`image`	Inputs: ≥ 1, ≤ 1	Not provided	First frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.
`image_url`	Inputs: ≥ 1, ≤ 1	Not provided	First frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	720p	Not provided	Not provided
`start_image`	Inputs: ≥ 1, ≤ 1	Not provided	First frame: a public image URL or a data URL. image, image_url and start_image are aliases; send one.

Text to video

Parameter	Values and limits	Default	Notes
`duration`	5	Not provided	Not provided
`operation`	Not provided	Not provided	Not provided
`output_audio`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	720p	Not provided	Not provided

Current qualified configuration: 5-second 720p text-to-video without audio.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to video · 720p

per second

Official price: $0.17
Verified price: —
Discount: —

Text to video · 1080p

per second

Official price: $0.29
Verified price: —
Discount: —

Image to video · 720p

per second

Official price: $0.17
Verified price: —
Discount: —

Image to video · 1080p

per second

Official price: $0.29
Verified price: —
Discount: —

Start and end frames to video · 720p

per second

Official price: $0.17
Verified price: —
Discount: —

Start and end frames to video · 1080p

per second

Official price: $0.29
Verified price: —
Discount: —

	Official priceper second	Verified priceper second	Discount
Text to video · 720p	$0.17	—	—
Text to video · 1080p	$0.29	—	—
Image to video · 720p	$0.17	—	—
Image to video · 1080p	$0.29	—	—
Start and end frames to video · 720p	$0.17	—	—
Start and end frames to video · 1080p	$0.29	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 13, 2026, 4:51 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open FLUX 3 Video in Console with a prompt ready to edit or send.

Help me create with flux-3-video using text-to-video at /v1/videos/generations. Show the result, status, and cost.

Use cases

Best for

Text to Video

Shot testing
Check a camera move, lighting, and subject action in a five-second clip before planning a longer sequence.
Animated concept loops
Make short motion pieces for pitch decks and landing pages from a written scene description.
Prompt comparison
Run the same scene with different wording or camera instructions and compare the five-second results side by side.

Prompt examples

Slow dolly-in on a rain-soaked neon street at night, a cyclist passes through frame.

Macro shot of coffee being poured into a glass cup, steam rising, warm morning light, shallow depth of field.

Aerial view of a fishing village at sunrise, boats leaving the harbour, gentle camera drift to the right.

FAQ

What does FLUX 3 Video generate?

Short video clips from a written scene description. It produces text-to-video output at 720p and five seconds, which is enough to judge camera movement, lighting and action before planning anything longer.

How long are FLUX 3 Video clips?

Five seconds each, at 720p. The format is fixed, so plan longer sequences as several separate clips and keep the scene description consistent between them.

Can FLUX 3 Video start from an image?

No. It takes a text prompt only. Describe the subject, setting, camera move and lighting in the prompt, and the clip is generated from that description.

Can FLUX 3 Video edit existing footage?

No. It creates new clips from text and does not modify a video you already have. For changing existing footage with a written instruction, look at FLUX Video Edit.

How much does FLUX 3 Video cost?

On TokenLab, FLUX 3 Video costs $0.17-$0.29 per second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should FLUX 3 Video use?

Use https://api.tokenlab.sh/v1/videos/generations for FLUX 3 Video. The request example below shows the matching code shape.

Which operations does FLUX 3 Video support?

FLUX 3 Video supports Image to video, Start and end frames to video, Text to video. Select an operation above to see its endpoint and request example.