black-forest-labs/flux-3-video

OfficialView on Replicate →

FLUX 3 is Black Forest Labs' frontier video model. This endpoint generates video directly from a text prompt, translating a written description into motion, composition, and scene.

Capabilities

auto21:92:116:94:31:13:49:16

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`prompt`*	string	The text prompt describing the video you want to generate.	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated video. `auto` lets the model choose.	`"auto"`	auto21:92:116:94:31:13:49:16
`duration`	enum	Duration of the generated video in seconds. `auto` lets the model choose.	`"auto"`	auto567891011121314151617181920
`generate_audio`	boolean	Whether to generate audio for the video.	`true`	—
`resolution`	string	Resolution of the generated video. `1080p`, `1440p` (2K) and `2160p` (4K) are finished by the video upsampler; exact dimensions depend on the aspect ratio.	`"720p"`	720p1080p1440p2160p
`safety_tolerance`	integer	The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive.	`2`	min: 0, max: 4

promptrequiredstring

The text prompt describing the video you want to generate.

aspect_ratiostring

Aspect ratio of the generated video. `auto` lets the model choose.

Default: "auto"

auto21:92:116:94:31:13:49:16

durationenum

Duration of the generated video in seconds. `auto` lets the model choose.

Default: "auto"

auto567891011121314151617181920

generate_audioboolean

Whether to generate audio for the video.

Default: true

resolutionstring

Resolution of the generated video. `1080p`, `1440p` (2K) and `2160p` (4K) are finished by the video upsampler; exact dimensions depend on the aspect ratio.

Default: "720p"

720p1080p1440p2160p

safety_toleranceinteger

The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive.

Default: 2min: 0, max: 4

Updated: 11/7/2026