how much does H3 Max Insert Video cost?

$0.05/sec 480p, $0.06/sec 768p. you pay per run from your inference shell credits. no subscription is required.

how do I run H3 Max Insert Video via api?

call falai/minimax-h3-max-insert-video with the javascript or python sdk, the rest api, or `belt app run falai/minimax-h3-max-insert-video` from a terminal. the api reference on this page lists every input.

who makes H3 Max Insert Video?

H3 Max Insert Video is made by falai and runs on inference shell. every falai app is listed at https://inference.sh/apps/falai.

can my agent use H3 Max Insert Video?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

what are the alternatives to H3 Max Insert Video?

other video apps on inference shell include H3 Max Styles, H3 Max 3D to Video, H3 Max Recast, H3 Max Relight. they run through the same api, so switching is a one-line change.

H3 Max Insert Video

Insert a newly generated scene into an existing video with MiniMax H3 Max via fal. Pick where the scene starts and where the original resumes; guide it with a prompt and references.

video to video video editing

run in browser →run via API

run with your agent

# install belt

$curl -fsSL https://cli.inference.sh | sh

# sign in (or set INFERENCE_API_KEY on a headless machine)

$belt login

# view schema & details

$belt app get falai/minimax-h3-max-insert-video

# run

$belt app run falai/minimax-h3-max-insert-video --input '{"video":"https://example.com/file.png","start_time":1.625,"resume_time":1.625,"prompt":"A red fox darts across the path and vanishes into the bushes."}'

maker: falai
category: video
input → output: video → video
price: $0.05/sec 480p, $0.06/sec 768p
runs via: api, javascript and python sdk, belt cli, mcp
updated: 2026-10-20

api reference

about

insert a newly generated scene into an existing video with minimax h3 max via fal. pick where the scene starts and where the original resumes; guide it with a prompt and references.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash

1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash

1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python

1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567result = client.run({8        "app": "falai/minimax-h3-max-insert-video",9        "input": {10            "video": "https://example.com/file.png",11            "start_time": 1.625,12            "resume_time": 1.625,13            "prompt": "A red fox darts across the path and vanishes into the bushes."14        }15    })1617print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python

1import os2from inferencesh import inference34client = inference(api_key=os.environ["INFERENCE_API_KEY"])567# stream=True yields updates as they arrive8for update in client.run({9        "app": "falai/minimax-h3-max-insert-video",10        "input": {11            "video": "https://example.com/file.png",12            "start_time": 1.625,13            "resume_time": 1.625,14            "prompt": "A red fox darts across the path and vanishes into the bushes."15        }16    }, stream=True):17    if update.get("progress"):18        print(f"progress: {update['progress']}%")19    if update.get("output"):20        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python

1# local file paths are automatically uploaded2result = client.run({3    "app": "falai/minimax-h3-max-insert-video",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python

1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python

1result = client.run({2    "app": "falai/minimax-h3-max-insert-video",3    "input": {4        "video": "https://example.com/file.png",5        "start_time": 1.625,6        "resume_time": 1.625,7        "prompt": "A red fox darts across the path and vanishes into the bushes."8    },9    "webhook": "https://your-server.com/webhook"10}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json

1{2  "event": "task.completed",3  "timestamp": "2024-01-15T10:30:05Z",4  "data": {5    "id": "task_abc123",6    "short_id": "abc123",7    "status": 10,8    "status_text": "completed",9    "output": { ... },10    "created_at": "2024-01-15T10:30:00Z",11    "updated_at": "2024-01-15T10:30:05Z"12  }13}

eventstringtask.completed, task.failed or task.cancelled

timestampstringiso timestamp of the delivery

data.idstringtask id

data.short_idstringshort task id

data.statusnumberterminal status (10=completed, 11=failed, 12=cancelled, 13=rejected)

data.status_textstringthe status as a word: completed, failed or cancelled

data.outputobjecttask output (when completed)

data.errorstringerror message (when failed, omitted otherwise)

data.session_idstringsession id (when the task ran in a session, omitted otherwise)

data.created_atstringiso timestamp

data.updated_atstringiso timestamp

5. schema

input

videostring(file)*

source video to insert a scene into.

start_timenumber*

seconds into the source where the generated scene begins.

min:1.625max:60

resume_timenumber*

seconds into the source where the original footage resumes. must be after start_time, with footage remaining after it.

min:1.625max:60

durationnumber

length of the generated scene in seconds (5-13).

default: 5min:5max:13

promptstring

what happens in the inserted scene.

example: "A red fox darts across the path and vanishes into the bushes."

reference_imagesarray

reference images guiding the inserted scene (max 9).

reference_videosarray

reference videos guiding the inserted scene (max 3).

resolutionstring

output resolution.

default: "768p"

options:"480p""768p"

enable_prompt_expansionboolean

enhance the prompt using the source video.

default: true

color_matchboolean

match the inserted scene's color to the source footage.

default: true

seedinteger

random seed for reproducible generation.

output

durationnumber

total length of the final video in seconds.

expanded_promptstring

the prompt used after expansion.

injected_durationnumber

length of the generated scene in seconds.

seedinteger

seed used for generation.

videostring(file)*

the final video with the inserted scene.

more from falai

H3 Max Styles

falai/minimax-h3-max-styles

$0.08/sec (768P)

H3 Max 3D to Video

falai/minimax-h3-max-3d-to-video

$0.50/request + $0.05/sec (480P), $0.08/sec (768P), $0.16/sec (1080P) + $0.10/generated ref; 5s min

H3 Max Recast

falai/minimax-h3-max-recast

$0.30/sec at 768P, $0.45/sec at 1080P

H3 Max Relight

falai/minimax-h3-max-relight

$0.05/s 480P, $0.08/s 768P, $0.16/s 1080P, $0.32/s 2K; up to 15s/video

new models

ready to run H3 Max Insert Video?

try in browser browse all apps

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.

products

capabilities

get started

learn

build

community

from the blog

H3 Max Insert Video

api reference

about

1. calling the api

install the client

setup your api key

run and get result

stream live updates

2. authentication

3. files

automatic upload

manual upload

4. webhooks

5. schema

input

output

other video apps

more from falai

new models

ready to run H3 Max Insert Video?