Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

FLUX 3 Video API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name flux-3
Type Text-to-video / image-to-video / video continuation
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

FLUX 3 Video combines text-to-video, 1-10 image keyframe control, and video continuation in one model, with clips up to 20 seconds, 720p/1080p output, and optional synchronized audio.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Sound-on narrative clips

Coordinate visuals, ambience, effects, and dialogue in one generation for ad concepts, storyboards, and social content.

promptgenerate_audio
Keyframe and storyboard control

Use one image for the opening frame, two for opening and closing frames, or 3-10 images for an evenly timed storyboard.

imagesduration
Video continuation

Continue the picture and sound from the end of an MP4 up to 15 seconds long.

start_videoduration
Low-cost prompt previews

Validate composition and motion with a 720p Draft before switching to full quality or 1080p.

draftresolution

Request parameters

model string required

Fixed value flux-3.

example flux-3
input object required

Business parameters. Put FLUX 3 Video-specific configuration here.

prompt string required

Describe the scene, action, camera movement, dialogue, and sound. The prompt is interpreted and expanded before generation.

images string[] optional

Optional PNG, JPEG, or WebP images. One image sets the opening frame, two set opening and closing frames, and 3-10 images form an evenly timed storyboard. Cannot be combined with start_video.

start_video string optional

Optional MP4 to continue from its final frames. Maximum 50 MB and 15 seconds. Cannot be combined with images.

aspect_ratio enum optional

Output aspect ratio. Auto selects a ratio from the prompt and media inputs.

default auto enum: auto21:92:116:94:31:13:49:16
resolution enum optional

Output resolution. Draft generation is available at 720p only.

default 720p enum: 720p1080p
duration integer optional

Generated clip duration in seconds. HiAPI uses an explicit 5-20 second duration for deterministic billing.

default 5
generate_audio boolean optional

Generate synchronized ambient sound, dialogue, and effects. Disable for a silent clip.

default true
draft boolean optional

Generate a faster, lower-cost 720p preview instead of a full-quality clip.

default false
callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; http(s) URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback
when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Cinematic text-to-video

Generate a five-second 16:9 clip at 720p with synchronized audio.

Request body
{
  "model": "flux-3",
  "input": {
    "prompt": "A silver maglev train glides through a solar-panel field at golden hour, low tracking shot, cinematic lighting and stable motion",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "generate_audio": true,
    "draft": false
  }
}
Two-keyframe image-to-video

The first image defines the opening frame and the second defines the closing frame. Do not combine images with start_video.

Request body
{
  "model": "flux-3",
  "input": {
    "prompt": "A smooth cinematic transition from sunrise to a neon-lit night city, stable camera motion",
    "images": [
      "https://example.com/start.webp",
      "https://example.com/end.webp"
    ],
    "resolution": "1080p",
    "duration": 8,
    "generate_audio": true
  }
}
Draft video continuation

Continue from an existing MP4 using the lower-cost 720p Draft tier.

Request body
{
  "model": "flux-3",
  "input": {
    "prompt": "Continue the forward camera move as the train enters a bright mountain tunnel",
    "start_video": "https://example.com/source.mp4",
    "resolution": "720p",
    "duration": 5,
    "generate_audio": true,
    "draft": true
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated video from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

How long can FLUX 3 Video generate?

Set an explicit output duration from 5 to 20 seconds. A start_video input can be up to 15 seconds long.

How do multiple images control the timeline?

One image defines the opening frame, two define the opening and closing frames, and 3-10 form an evenly timed storyboard. images cannot be combined with start_video.

How is Draft different from full quality?

Draft is a faster, lower-cost 720p preview tier and cannot run at 1080p. Full quality supports both 720p and 1080p.

How is FLUX 3 Video priced?

Billing is per generated second. The rate depends on resolution, Draft mode, and whether a source video is continued. View live video API pricing

Next steps