HiAPI
OverviewModels MarketAPI KeysUsage StatisticsCall LogsBillingReferralPlaygroundStorageChangelogContact UsSettings
Display unit
N
Powered by hiapi
Settings

Welcome

Contact Us

Try the FLUX.3 Video API with text prompts, 1 to 10 keyframes, source-video continuation, synchronized audio, Draft previews, and per-second pricing.

Provider: Black Forest Labs

Category: video generation

Endpoint: /v1/tasks

Status: Available

Cost: See live page pricing

Back to Models

FLUX.3 Video

New
by Black Forest LabsVideo

Try the FLUX.3 Video API with text prompts, 1 to 10 keyframes, source-video continuation, synchronized audio, Draft previews, and per-second pricing.

Pricing

Standard Usage

500 Credits/ s

Input

0 / 5000
5s
5s1-second steps20s

Choose 5-20 seconds in 1-second steps

More parameters

Upload assets

Preview after upload

Upload an MP4 to continue. Maximum 15 seconds and 50MB; cannot be combined with reference images

Generation preferences

Generate synchronized audio for the video

Generate a faster, lower-cost 720p preview

Estimated cost2,500 Credits500 Credits / s × 5s

Output

Ready for generation

Configure your parameters and click "Run" to see the output here.

--GPU-T4

REAL API RESULTS

Three input modes in one video workflow

Switch between text, keyframes, and continuation to inspect the prompt, inputs, and playable result.

Full5s · 720p · 16:9

A tactile cafe shot with synchronized sound

A close tracking shot combines steam, espresso, ceramic detail, and restrained cafe ambience.

Prompt · English

Close-up tracking shot of a barista pulling an espresso shot on a stainless steel machine in a sunlit corner cafe; steam hisses from the portafilter, the coffee stream crackles into the cup, ambient cafe chatter and a ceramic cup clinking softly on a saucer, warm morning light through a window, shallow depth of field, cinematic color grade

Generated result · with audio5s
Draft5s · 720p · 16:9

Preview composition and motion with Draft

The lower-cost 720p tier is useful for checking pacing and camera stability before a final render.

Prompt · English

Wide static shot of a lone kayaker paddling across a still alpine lake at sunrise, paddle dipping into water with soft splashes, birds calling in the distance, mist rising off the water, golden backlight, cinematic wide angle

Generated result · with audio5s

Related video models

Choose an alternative by input mode, duration, and cost.

Fast text to video

Kling 3.0 Turbo

View model

Image to video

Veo 3.1

View model

First and last frame

Seedance 2.5

View model

About FLUX.3 Video

FLUX.3 combines text generation, keyframe storyboards, and video continuation under one model ID. Draft is a preview tier, not a separate workflow. Keyframes and a source video cannot be mixed in one request.

Text generation

Create a complete shot, motion, camera, and sound directly from a prompt.

Keyframe storyboard

Use one image for the opening, two for first and last frames, or up to ten in order.

Video continuation

Continue from an MP4 up to 15 seconds while preserving its visual and audio language.

Specifications and pricing

Billed per output second, with separate Draft and continuation tiers.

Input modes
Prompt / 1 to 10 images / MP4 source video
Output duration
5 to 20 seconds
Resolution
720p / 1080p
Aspect ratio
auto / 21:9 / 2:1 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16
Audio
Synchronized audio enabled by default
Draft
720p only
Model ID
flux-3
API
POST /v1/tasks · Async

Full 720p

500 Credits / sec

Full 1080p

840 Credits / sec

Draft 720p

180 Credits / sec

Continuation 720p

1,180 Credits / sec

Continuation 1080p

1,520 Credits / sec

Continuation Draft

360 Credits / sec

How to use FLUX.3

All three workflows share one model ID, but keyframes and source video must be submitted separately.

01

Choose an input mode

Use a prompt, ordered keyframe images, or one MP4 source video.

02

Set the output tier

Choose 5 to 20 seconds and 720p or 1080p. Draft is limited to 720p.

03

Validate, then integrate

Check the result in Playground, then create async tasks with the same model ID.

API Quickstart

Switch workflows for the matching minimal request. See Docs for every parameter, task retrieval, and errors.

curl -X POST https://api.hiapi.ai/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "flux-3",
  "input": {
    "prompt": "A cinematic close-up of an espresso shot",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}'
The request returns a taskId. Retrieve the video from the task detail endpoint.
Read the full API documentation

Frequently asked questions

Which FLUX.3 workflows are supported?

The same model ID supports text-to-video, 1 to 10 ordered keyframe images, and MP4 source-video continuation. Do not combine images with start_video.

What is the difference between Draft and Full?

Draft is a lower-cost 720p preview tier for checking composition, pacing, and motion. Full supports 720p and 1080p for final output.

How do FLUX.3 keyframes work?

One image defines the opening, two images define the first and last frames, and 3 to 10 ordered images form a storyboard. The prompt controls motion, camera, and sound.

What are the video continuation limits?

start_video accepts an MP4 up to 50MB and 15 seconds. Do not submit images in the same request. Select an output duration from 5 to 20 seconds.

Can FLUX.3 generate audio?

Yes. generate_audio is enabled by default for synchronized ambience, sound effects, or dialogue. Disable it for video-only output.

How is FLUX.3 priced?

Pricing depends on output duration, resolution, Draft mode, and whether source-video continuation is used. The page lists all six per-second tiers.