Video

FLUX 3 Video

FLUX 3 Video by Black Forest Labs supports text-to-video, image-to-video with 1–10 ordered keyframes, video continuation, and draft enhancement. Generate synchronized audio with 5–20 second HD or FHD output, configurable safety tolerance, and results stored on the APIMart CDN.

Native Audio5–20 SecondsOrdered KeyframesHD and FHD

Get API Key API Docs

Service Highlights

99.9% SLA
Official Discounts
Pay-as-you-go
Fast & Low Latency

Input

Model

Generation Mode

Create a video from a prompt

Prompt*

Duration5s

Choose an integer from 5 to 20 seconds.

Resolution

Aspect Ratio

Generate Audio

Generate synchronized native audio with the video.

Draft Mode

Generate a lower-cost, low-quality HD draft first, then convert it to the final video with a second request.

Safety Tolerance2

Output

Stored on the APIMart CDN

Pricing Details

Transparent pricing with no hidden fees. Pay only for what you use.

* Actual costs are subject to final output.

FLUX 3 Video API for 20-Second Video with Native Audio

Generate from a prompt, animate 1–10 ordered keyframes, continue a source video, or enhance a completed draft. Choose 5–20 seconds, HD or FHD output, and synchronized native audio.

50K+

Active Users

99.9%

Uptime

Faster

70%

Cost Savings

FLUX 3 Video API Capabilities

Confirmed generation modes, output controls, and delivery features

Native Video and Audio Generation

Generate synchronized native audio together with the video, or set audio to false when a silent result is required.

5–20 Second Duration

Choose an integer duration from 5 to 20 seconds for text-to-video, image-to-video, or video continuation requests.

Text-to-Video

Create a video from a required text prompt with explicit duration, resolution, aspect ratio, audio, and safety controls.

Ordered Image Keyframes

Provide 1–10 images in playback order. One image is the start frame; with multiple images, the first and last define the endpoints.

Video Continuation

Continue one source MP4 video from a public URL or base64 input using the video-to-video workflow.

Draft Enhancement

Generate a lower-cost HD draft, then use its completed task ID to render a final HD or FHD video.

HD and FHD Output

Use HD for standard output and drafts, or choose FHD for a higher-resolution final video.

Safety Control and CDN Delivery

Set safety_tolerance from 0 to 4. Completed results are transferred to the APIMart CDN for long-term access.

What You Can Create with FLUX 3 Video

Practical workflows built from the four confirmed generation modes

Prompt-Based Short Video

Turn a written scene and action description into a 5–20 second video with optional synchronized audio.

Animate a Starting Image

Use one image as the starting keyframe and describe the required motion in the prompt.

Ordered Keyframe Sequence

Submit ordered keyframes to define the start, end, and evenly distributed intermediate moments of a clip.

Continue an Existing Clip

Provide one source video and a prompt describing what should happen next in the continuation.

Review with an HD Draft

Generate an HD draft first to review the motion before submitting its task ID for final rendering.

Synchronized-Audio Clips

Generate video and native synchronized audio in one request, or disable audio for a silent deliverable.

How FLUX 3 Video Works

Submit and retrieve a FLUX 3 Video task in three steps

Choose a Workflow

Select text-to-video, ordered image keyframes, video continuation, or enhancement of a completed draft task.

→

Configure the Request

Add the required prompt or source input, then choose 5–20 seconds, HD or FHD, aspect ratio, audio, and safety tolerance.

→

Submit and Retrieve

Submit the asynchronous task, poll its status, and retrieve the completed video from the APIMart CDN.

FLUX 3 Video API FAQ

Common questions about FLUX 3 Video capabilities and workflows

What is FLUX 3 Video?

FLUX 3 Video is Black Forest Labs' video model for text-to-video, ordered image keyframes, video continuation, and draft enhancement with optional synchronized native audio.

What can FLUX 3 Video generate?

It supports text-to-video, image-to-video with ordered keyframes, video continuation, and enhancement of a completed draft task.

Does FLUX 3 Video generate audio?

Yes. Synchronized native audio is enabled by default. Set audio to false when you need a silent video; disabling audio does not change the price.

How long can a FLUX 3 Video clip be?

Requests accept an integer duration from 5 to 20 seconds. Output resolution can be HD or FHD, while draft mode is limited to HD.

Which generation modes does FLUX 3 Video support?

Use t2v for a prompt, i2v for ordered images, v2v for a source video, and draft_enhance with a completed draft task ID.

How do ordered keyframes work?

You can submit 1–10 images in order. One image is the start frame; with two or more, the first and last are the endpoints and intermediate images are distributed between them.

How does the draft workflow work?

Create an HD draft with draft set to true. After it completes, submit its task ID with draft_from_task_id to render a final HD or FHD video.

What safety and delivery controls are available?

Set safety_tolerance from 0 to 4. When a task completes, the result URL is transferred to the APIMart CDN for long-term access.

Related Models

Explore more models in the same category.

View All Models →