Proteus

Proteus is Topaz Labs’ video enhancement model for detail-preserving upscaling, denoising, and restoration. It enhances an existing video with automatic adjustments or fine control over detail recovery, compression artifacts, noise, blur, and grain. An input video and output resolution are required, supporting workflows that improve footage quality while preserving its source characteristics. Your use is subject to Topaz Labs's Terms & Privacy Policies.

View API reference

Price: $0.08, Per video
Lowest available configuration

Get API key Read the docs

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'topaz/proteus',
  prompt: '',
  inputReferences: [
    { data: 'https://example.com/input.mp4', mediaType: 'video/mp4' },
  ],
  resolution: '1920x1080',
});

Read docs

Overview Providers API Similar

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Checking availability for your team

Provider

Input	Output	Capabilities	ZDR	No Training	Free AI Gateway Credit	Release Date

Topaz Labs

Legal:Terms•Privacy

$0.08/video+17 more

10/06/2026

Getting started

Enhance an existing video with experimental_generateVideo from AI SDK 6 or later. Set AI_GATEWAY_API_KEY; AI Gateway routes the request to Topaz and waits for the result.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the video API setup.

index.ts

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'topaz/proteus',
  prompt: '',
  inputReferences: [
    { data: 'https://example.com/input.mp4', mediaType: 'video/mp4' },
  ],
  resolution: '1920x1080',
});

Enhance a video

Supply your input video and the output dimensions.

index.ts

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'topaz/proteus',
  prompt: '',
  inputReferences: [
    { data: 'https://example.com/input.mp4', mediaType: 'video/mp4' },
  ],
  resolution: '1920x1080',
});

Parameter	Type	Required	Description
`prompt`	`string`	Yes	Use an empty string; the SDK requires a prompt but Topaz does not use text.
`inputReferences`	`Array<{ data: string \| Uint8Array \| URL; mediaType: string }>`	Yes	Exactly one input video. For MP4, use mediaType: "video/mp4".
`resolution`	`string`	No	Output dimensions as width x height, e.g. 1920x1080. Required unless output.width/output.height or complete source metadata supplies them.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
video	—	URL, File bytes	1	—	Supply one existing video through inputReferences.

Enhances the whole input video. Text prompts, duration, aspectRatio, and seed do not control the output.

Provider options

Pass enhancement controls under providerOptions.topaz.

index.ts

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'topaz/proteus',
  prompt: '',
  inputReferences: [
    { data: 'https://example.com/input.mp4', mediaType: 'video/mp4' },
  ],
  resolution: '1920x1080',
  providerOptions: { topaz: { auto: 'Manual', compression: 0.2 } },
});

Pass these fields under providerOptions.topaz.

Parameter	Type	Required	Description
`source`	`{ width: number; height: number; duration: number; frameRate: number; frameCount?: number }`	No	Actual input width and height in pixels, duration in seconds, and frame rate. If supplied, all four fields are required. Set frameCount explicitly for variable-frame-rate input.
`output`	`{ width?: number; height?: number }`	No	Output dimensions; these take precedence over resolution.
`auto`	`'Auto' \| 'Manual' \| 'Relative'`	No	Parameter estimation mode.
`compression`	`number`	No	Compression artifact removal from -1 to 1.

Copy link to headingMore models by Topaz Labs

Model

Context	Latency	Throughput	Input	Output	Cache	Search	Capabilities	Providers	ZDR	No Training	Free AI Gateway Credit	Release Date

topaz/starlight-precise-2.6

—

$0.09/sec+1 more

—

10/06/2026

topaz/wonder-3.5

—

$0.08/img+7 more

—

10/06/2026