Inference Logoinference shell

H3 Max Turbo

MiniMax H3 Max Turbo via fal, the faster, cheaper H3 Max variant. Text-to-video and image-to-video with first/last frame, 480P/768P/1080P, 1-15s, prompt expansion, audio pinning.

text to videoimage to videonative audio
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-turbo
# run
$belt app run falai/minimax-h3-max-turbo --input '{"prompt":"A cinematic tracking shot through a misty forest at dawn, golden light filtering through ancient trees."}'
maker
falai
category
video
input → output
text → video, image → video
price
$0.025/s 480P, $0.04/s 768P, $0.08/s 1080P
runs via
api, javascript and python sdk, belt cli, mcp
updated
2026-10-20

api reference

about

minimax h3 max turbo via fal, the faster, cheaper h3 max variant. text-to-video and image-to-video with first/last frame, 480p/768p/1080p, 1-15s, prompt expansion, audio pinning.

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-turbo",9        "input": {10            "prompt": "A cinematic tracking shot through a misty forest at dawn, golden light filtering through ancient trees."11        }12    })1314print(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-turbo",10        "input": {11            "prompt": "A cinematic tracking shot through a misty forest at dawn, golden light filtering through ancient trees."12        }13    }, stream=True):14    if update.get("progress"):15        print(f"progress: {update['progress']}%")16    if update.get("output"):17        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-turbo",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-turbo",3    "input": {4        "prompt": "A cinematic tracking shot through a misty forest at dawn, golden light filtering through ancient trees."5    },6    "webhook": "https://your-server.com/webhook"7}, 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

promptstring*

video prompt. use timeline markers like [0s-3s] for scene pacing.

example: "A cinematic tracking shot through a misty forest at dawn, golden light filtering through ancient trees."
imagestring(file)

first frame image. the output canvas follows this image.

end_imagestring(file)

last frame image. can be given alone for end-only generation; the canvas then follows this image.

target_audiostring(file)

audio clip (2s or longer, max 15 mb) pinned as the soundtrack. trimmed to the video length. use duration of at least 2s.

durationnumber

video duration in seconds (1-15). output can run up to ~0.7s longer.

default: 5min:1max:15
resolutionstring

480p fastest, 768p native quality, 1080p latent refinement from 768p.

default: "768P"
options:"480P""768P""1080P"
aspect_ratiostring

aspect ratio for text-to-video. ignored when an image is given (the canvas follows the image).

default: "16:9"
options:"21:9""16:9""4:3""1:1""3:4""9:16"
prompt_expansion_modestring

prompt rewriting effort: disabled (none), balanced (~1s), or quality (~30s extra).

default: "balanced"
options:"disabled""balanced""quality"
seedinteger

random seed for reproducible generation.

output

expanded_promptstring

the prompt after expansion, as sent to the model.

videostring(file)*

the generated video file.

other video apps

H3 Max Styles

falai/minimax-h3-max-styles

$0.08/sec (768P)

H3 Max Insert Video

falai/minimax-h3-max-insert-video

$0.05/sec 480p, $0.06/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

more from falai

H3 Max Styles

falai/minimax-h3-max-styles

$0.08/sec (768P)

H3 Max Insert Video

falai/minimax-h3-max-insert-video

$0.05/sec 480p, $0.06/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

new models

  1. H3 Max Styles

    falai/minimax-h3-max-styles

    video$0.08/sec (768P)

  2. H3 Max Insert Video

    falai/minimax-h3-max-insert-video

    video$0.05/sec 480p, $0.06/sec 768p

  3. H3 Max 3D to Video

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

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

  4. H3 Max Recast

    falai/minimax-h3-max-recast

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

  5. H3 Max Relight

    falai/minimax-h3-max-relight

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

ready to run H3 Max Turbo?

try in browserbrowse 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.