# Topaz Starlight

> Run Topaz Starlight by topaz online or via API. From $0.0714 per credit, no setup.

**URL:** https://inference.sh/apps/topaz/starlight
**Last updated:** 2026-08-04

---

generative video upscaling — precision, hq, mini, sharp, and fast models

- app: `topaz/starlight`
- maker: [topaz](https://inference.sh/apps/topaz.md)
- category: [video](https://inference.sh/apps/category/video.md)
- tasks: [video upscaling](https://inference.sh/apps/tag/video-upscaling.md)
- price: $0.0714/credit
- runs via: api, javascript and python sdk, belt cli, mcp

## starlight API Guide

### About
generative video upscaling — precision, hq, mini, sharp, and fast models

### 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": "topaz/starlight@25vcw8pt",
        "input": {
            "video": "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": "topaz/starlight@25vcw8pt",
        "input": {
            "video": "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": "topaz/starlight@25vcw8pt",
    "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*: input video file
- **model** (string): starlight model: precise-2.5 (best quality), hq (high quality), mini (lightweight), sharp (detail emphasis), fast-2 (speed optimized)
- **scale** (number): upscale factor (1.0-4.0)
- **upscaling_factor** (number): upscaling factor override (hq model only)
- **low_sharpness** (boolean): use low sharpness mode (hq model only)
- **keep_original** (boolean): keep original detail (hq model only)

#### Output
- **video** (string): upscaled 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 Relight](https://inference.sh/apps/falai/minimax-h3-max-relight.md): $0.05/s 480P, $0.08/s 768P, $0.16/s 1080P, $0.32/s 2K; up to 15s/video

## faq

### how much does Topaz Starlight cost?

$0.0714/credit. you pay per run from your inference shell credits. no subscription is required.

### how do I run Topaz Starlight via api?

call topaz/starlight with the javascript or python sdk, the rest api, or `belt app run topaz/starlight` from a terminal. the api reference on this page lists every input.

### who makes Topaz Starlight?

Topaz Starlight is made by topaz and runs on inference shell. every topaz app is listed at https://inference.sh/apps/topaz.

### can my agent use Topaz Starlight?

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 Topaz Starlight?

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.