FLUX.3 Video

Black Forest Labs FLUX.3 video generation with text, image, first/last-frame, exact keyframe, and video-extension modes with native audio.


Model id	`flux-3-fal`
Media	video
Submit to	`POST /v1/videos`
Price	varies by tier and settings; `GET /v1/models/flux-3-fal/estimate` quotes it
Typical time	about 360.0 s

Text → Video

Generate a complete shot from text with native audio. Select it with "mode": "text_to_video", or leave mode out and the inputs decide. Required: prompt, duration_seconds
Optional: aspect_ratio, generate_audio Resolution tiers: 720p, 1080p (send as tier).

{
  "model": "flux-3-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "mode": "text_to_video",
  "aspect_ratio": "auto",
  "duration_seconds": 5,
  "tier": "720p"
}

Field	Allowed	Default
`aspect_ratio`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"auto"`
`duration_seconds`	5.0 – 20.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`

Image → Video

Animate a single opening image into coherent motion. Select it with "mode": "image_to_video", or leave mode out and the inputs decide. Required: prompt, first_frame, duration_seconds
Optional: aspect_ratio, generate_audio Resolution tiers: 720p, 1080p (send as tier).

{
  "model": "flux-3-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "mode": "image_to_video",
  "aspect_ratio": "auto",
  "duration_seconds": 5,
  "first_frame": "asset_…",
  "tier": "720p"
}

Field	Allowed	Default
`aspect_ratio`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"auto"`
`duration_seconds`	5.0 – 20.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`
`first_frame`	asset id (up to 1)

First/Last Frame → Video

Generate a transition pinned to both an opening and closing image. Select it with "mode": "first_last_frame_to_video", or leave mode out and the inputs decide. Required: prompt, first_frame, last_frame, duration_seconds
Optional: aspect_ratio, generate_audio Resolution tiers: 720p, 1080p (send as tier).

{
  "model": "flux-3-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "mode": "first_last_frame_to_video",
  "aspect_ratio": "auto",
  "duration_seconds": 5,
  "first_frame": "asset_…",
  "last_frame": "asset_…",
  "tier": "720p"
}

Field	Allowed	Default
`aspect_ratio`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"auto"`
`duration_seconds`	5.0 – 20.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`
`first_frame`	asset id (up to 1)
`last_frame`	asset id (up to 1)

Keyframes → Video

Pin up to 10 images to exact positions on a 24 fps timeline. Select it with "mode": "keyframes_to_video", or leave mode out and the inputs decide. Required: prompt, keyframes, duration_seconds
Optional: aspect_ratio, generate_audio Resolution tiers: 720p, 1080p (send as tier).

{
  "model": "flux-3-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "mode": "keyframes_to_video",
  "aspect_ratio": "auto",
  "duration_seconds": 5,
  "keyframes": [
    {
      "image": "asset_…",
      "frame_index": 0
    },
    {
      "image": "asset_…",
      "frame_index": 48
    }
  ],
  "tier": "720p"
}

Field	Allowed	Default
`aspect_ratio`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"auto"`
`duration_seconds`	5.0 – 20.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`
`keyframes`	asset ids (up to 10)

Extend Video

Continue an existing video from its final frames. Select it with "mode": "extend_video", or leave mode out and the inputs decide. Required: prompt, source_video, duration_seconds
Optional: aspect_ratio, generate_audio Resolution tiers: 720p, 1080p (send as tier).

{
  "model": "flux-3-fal",
  "prompt": "A slow aerial shot over a misty pine forest at dawn",
  "mode": "extend_video",
  "aspect_ratio": "auto",
  "duration_seconds": 5,
  "source_video": "asset_…",
  "tier": "720p"
}

Field	Allowed	Default
`aspect_ratio`	`auto`, `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	`"auto"`
`duration_seconds`	5.0 – 20.0 seconds	`5`
`generate_audio`	`true`, `false`	`true`
`source_video`	asset id (up to 1)

Reference inputs take asset ids from POST /v1/uploads or an earlier output’s asset_id. Prices and allowed values come from the live catalog; GET /v1/models/flux-3-fal is always current.

Start here

Using the API

Choosing a model

Image models

Video models

Audio models

Agents and MCP

Text → Video

Image → Video

First/Last Frame → Video

Keyframes → Video

Extend Video

​Text → Video

​Image → Video

​First/Last Frame → Video

​Keyframes → Video

​Extend Video

Text → Video

Image → Video

First/Last Frame → Video

Keyframes → Video

Extend Video