FLUX 3 Max Text to 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-max/text-to-video
Type	Video generation (text-to-video)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

FLUX 3 Max text-to-video turns a prompt into a 5–20 second clip at 720p or 1080p, such as an aerial sunrise ocean shot, with 7 fixed aspect ratios plus auto, synchronized audio, and low/high reasoning levels.

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

Narrative short clips

Describe the scene, subject motion, and camera movement in the prompt to generate a video with synchronized audio.

promptgenerate_audio

Multi-platform framing

Seven fixed ratios cover landscape, portrait, square, and ultra-wide formats, or let auto choose.

aspect_ratio

Length and resolution

Pick any length from 5 to 20 seconds in 1-second steps, at 720p or 1080p.

durationresolution

Request parameters

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

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "flux-3-max/text-to-video",
  "input": {
    "prompt": "a slow aerial shot of ocean waves at sunrise, photorealistic",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": false,
    "reasoning_level": "low"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "flux-3-max/text-to-video",
  "input": {
    "prompt": "a slow aerial shot of ocean waves at sunrise, photorealistic",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": false,
    "reasoning_level": "low"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "flux-3-max/text-to-video",
  "input": {
    "prompt": "a slow aerial shot of ocean waves at sunrise, photorealistic",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": false,
    "reasoning_level": "low"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value flux-3-max/text-to-video.

example flux-3-max/text-to-video

input object required

Business parameters. Put FLUX 3 Max Text to Video-specific configuration here.

prompt string required

Describes the scene, subject motion, camera movement, and atmosphere of the video to generate.

duration integer optional

Video length in seconds; an integer from 5 to 20 in 1-second steps.

default 5

resolution enum optional

Output video resolution: 720p or 1080p.

default 720p enum: 720p1080p

aspect_ratio enum optional

Output aspect ratio. auto lets the model choose; you can also set 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.

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

generate_audio boolean optional

Whether to generate synchronized audio with the video.

default true example true

reasoning_level enum optional

Reasoning effort before generation: low or high. Defaults to high.

default high enum: lowhigh

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

Sunrise ocean aerial

Text-to-video example: a 5-second 720p aerial shot of ocean waves at sunrise, with synchronized audio off and low reasoning.

Request body

{
  "model": "flux-3-max/text-to-video",
  "input": {
    "prompt": "a slow aerial shot of ocean waves at sunrise, photorealistic",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": false,
    "reasoning_level": "low"
  }
}

Getting the result

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

FAQ

Which durations and resolutions are available?

duration is an integer from 5 to 20 in 1-second steps; resolution accepts 720p or 1080p.

What does aspect_ratio auto mean?

auto lets the model choose the framing. For a fixed ratio, pass 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.

Can I turn off audio?

Yes. generate_audio is on by default; pass false to generate a silent video.

How should I choose reasoning_level?

It accepts low or high; high is the default. Choose the level that fits your generation needs.

How is it billed?

See the live prices on the HiAPI pricing page. View pricing