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 the Unified 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; HTTPS 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