# H3 Max Relight

> Run H3 Max Relight by falai online or via API. From $0.05 per second, no setup.

**URL:** https://inference.sh/apps/falai/minimax-h3-max-relight
**Last updated:** 2026-10-20

---

Relight an existing video from a lighting sphere reference image with MiniMax H3 Max via fal. Keeps subjects, motion, camera and audio; output 480P to 2K.

- app: `falai/minimax-h3-max-relight`
- maker: [falai](https://inference.sh/apps/falai.md)
- category: [video](https://inference.sh/apps/category/video.md)
- input → output: video → video
- tasks: [video to video](https://inference.sh/apps/tag/video-to-video.md), [relighting](https://inference.sh/apps/tag/relighting.md)
- price: $0.05/s 480P, $0.08/s 768P, $0.16/s 1080P, $0.32/s 2K; up to 15s/video
- runs via: api, javascript and python sdk, belt cli, mcp

## minimax-h3-max-relight API Guide

### About
relight an existing video from a lighting sphere reference image with minimax h3 max via fal. keeps subjects, motion, camera and audio; output 480p to 2k.

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Setup Your API Key
Set `INFERENCE_API_KEY` as an environment variable. Get your key from settings → api keys.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

#### Run and Get Result

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


result = client.run({
        "app": "falai/minimax-h3-max-relight@6k8jzxkv",
        "input": {
            "video": "https://example.com/file.png",
            "reference_image": "https://example.com/file.png"
        }
    })

print(result["output"])
```

#### Stream Live Updates

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])


## stream=True yields updates as they arrive
for update in client.run({
        "app": "falai/minimax-h3-max-relight@6k8jzxkv",
        "input": {
            "video": "https://example.com/file.png",
            "reference_image": "https://example.com/file.png"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

### 2. Authentication
The API uses API keys for authentication. See the authentication docs for detailed setup instructions.

### 3. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "falai/minimax-h3-max-relight@6k8jzxkv",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

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

### 4. Schema

#### Input
- **video** (string) *required*: Source video up to 15 seconds (mp4, mov, webm, m4v, gif). Trimmed to a 17n+5 frame count at 24 fps.
- **reference_image** (string) *required*: Lighting reference: a sphere render showing the target light positions, colors and intensity.
- **resolution** (string): 480P and 768P native; 1080P and 2K refined from 768P.
- **aspect_ratio** (string): Output aspect ratio. adaptive follows the source.
- **seed** (integer): Random seed for reproducible generation.

#### Output
- **seed** (integer): Seed used for generation.
- **video** (string): The relighted video.

## other video apps

- [H3 Max Styles](https://inference.sh/apps/falai/minimax-h3-max-styles.md): $0.08/sec (768P)
- [H3 Max Insert Video](https://inference.sh/apps/falai/minimax-h3-max-insert-video.md): $0.05/sec 480p, $0.06/sec 768p
- [H3 Max 3D to Video](https://inference.sh/apps/falai/minimax-h3-max-3d-to-video.md): $0.50/request + $0.05/sec (480P), $0.08/sec (768P), $0.16/sec (1080P) + $0.10/generated ref; 5s min
- [H3 Max Recast](https://inference.sh/apps/falai/minimax-h3-max-recast.md): $0.30/sec at 768P, $0.45/sec at 1080P
- [H3 Max Lip Sync](https://inference.sh/apps/falai/minimax-h3-max-lip-sync.md): 480P $0.05/s, 768P $0.08/s, 1080P $0.16/s, 2K $0.32/s; +20% if >15s

## faq

### how much does H3 Max Relight cost?

$0.05/s 480P, $0.08/s 768P, $0.16/s 1080P, $0.32/s 2K; up to 15s/video. you pay per run from your inference shell credits. no subscription is required.

### how do I run H3 Max Relight via api?

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

### who makes H3 Max Relight?

H3 Max Relight 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 Relight?

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 Relight?

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