topazNot yet certifiedReleased 10/06/2026

Wonder 3.5

Wonder 3.5 is Topaz Labs’ image enhancement model for generative upscaling and detail recovery. It repairs and enhances an existing JPEG, PNG, or TIFF image, with controls for enhancement strength, output dimensions, and grain. An input image is required, making it suited to restoring low-quality photos and refining images for larger displays or print.

View API reference ↓
Input / output priceFrom$0 / $0per 1M
24h uptime100.00%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.images.generate({
  model: "topaz/wonder-3.5",
  prompt: "A lighthouse at dusk, oil painting",
  size: "1024x1024",
});

// Base64 only: images are returned, never stored.
const png = Buffer.from(res.data[0].b64_json, "base64");

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
topaz00——$0$0Read —Write ——NoNoGlobalListed

Uptime

24 hours

Request success rate per provider.

topaz100.00%

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.images.generate({
  model: "topaz/wonder-3.5",
  prompt: "A lighthouse at dusk, oil painting",
  size: "1024x1024",
});

// Base64 only: images are returned, never stored.
const png = Buffer.from(res.data[0].b64_json, "base64");

Wonder 3.5 answers POST /v1/images/generations, not chat completions. It is billed per output token: the balance held for a request is the most tokens the size and quality asked for were measured to take.