FLUX 3 Max Image 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/image-to-video
Type	Video generation (image-to-video)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

FLUX 3 Max image-to-video turns a first frame, such as a misty fishing harbor, with an optional last frame, into a 5–20 second clip at 720p or 1080p, 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

Animate a still image

Use an existing image as the first frame and add subject motion, camera moves, and atmosphere in the prompt.

image_urlprompt

First-to-last-frame transitions

Provide both a first and a last frame to generate a transition from the starting shot to the target shot.

image_urlend_image_url

Length and framing control

Choose any length from 5 to 20 seconds and set framing with seven fixed ratios or auto.

durationaspect_ratio

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/image-to-video",
  "input": {
    "prompt": "Morning mist drifts slowly over the quiet fishing harbor as the wooden boats rock gently on the water; sunlight glints across the wet pier planks and the camera slowly pushes forward.",
    "image_url": "https://static.hiapi.ai/gallery/2026/07/8acba0f00bdacec3.jpg",
    "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/image-to-video",
  "input": {
    "prompt": "Morning mist drifts slowly over the quiet fishing harbor as the wooden boats rock gently on the water; sunlight glints across the wet pier planks and the camera slowly pushes forward.",
    "image_url": "https://static.hiapi.ai/gallery/2026/07/8acba0f00bdacec3.jpg",
    "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/image-to-video",
  "input": {
    "prompt": "Morning mist drifts slowly over the quiet fishing harbor as the wooden boats rock gently on the water; sunlight glints across the wet pier planks and the camera slowly pushes forward.",
    "image_url": "https://static.hiapi.ai/gallery/2026/07/8acba0f00bdacec3.jpg",
    "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/image-to-video.

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

input object required

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

prompt string required

Describes the motion, camera movement, and scene changes to create from the first frame.

image_url string required

Public image URL used as the first frame. Supports PNG, JPEG, and WebP.

end_image_url string optional

Optional public image URL used as the last frame. Supports PNG, JPEG, and WebP; when set, the video transitions from the first frame to the last frame.

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

Misty fishing harbor

First-frame image-to-video example: a 5-second 720p clip, with synchronized audio off and low reasoning.

Request body

{
  "model": "flux-3-max/image-to-video",
  "input": {
    "prompt": "Morning mist drifts slowly over the quiet fishing harbor as the wooden boats rock gently on the water; sunlight glints across the wet pier planks and the camera slowly pushes forward.",
    "image_url": "https://static.hiapi.ai/gallery/2026/07/8acba0f00bdacec3.jpg",
    "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

How do first and last frames work?

Pass the first frame in image_url and an optional last frame in end_image_url; the video transitions from the first frame to the last. Without end_image_url, generation starts from the first frame only.

Can I set the duration and aspect ratio?

Yes. duration is an integer from 5 to 20; aspect_ratio accepts auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16.

What are the image requirements?

image_url and end_image_url must be publicly reachable PNG, JPEG, or WebP URLs without hotlink protection or complex redirects.