Integration guide

Add OpenLux to Cherry Studio

Cherry Studio supports custom OpenAI-compatible providers. Add OpenLux as one provider and the desktop app can compare GPT-6 Astra, Claude Opus 5, Gemini 3.8 Flash and Qwen3 Max in the same window.

Create an API key Read the docs

Abstract orange glass sculpture illustrating the Cherry Studio integration with OpenLux — Cherry Studio + OpenLux — one key, one endpoint, one bill.

Set it up in four steps

Create an OpenLux key

Create the key in the OpenLux console. It is scoped to your account and works across every model in the catalogue.

Add a new provider

In Settings → Model Providers choose Add Provider, set the provider type to OpenAI-compatible and enter https://openlux.lol/v1 as the API host.

Add the models you use

Type model names exactly as they appear in the OpenLux catalogue — gpt-6-astra, claude-opus-5, qwen3-max — so they show up in the chat model picker.

Switch per conversation

Each conversation can use a different model, which makes comparing two answers on the same prompt a two-click operation on one account.

Configuration

Copy these blocks, replace the placeholder key and you are done.

Settings → Model Providers → Add Provider

Provider Name: OpenLux
Provider Type: OpenAI  (API host override)
API Host:      https://openlux.lol/v1
API Key:       sk-openlux-...
Models:        gpt-6-astra, claude-opus-5, gemini-3.8-flash, qwen3-max

Models that fit Cherry Studio

GPT-6 Astra

OpenAI · $0.3677 / 1M tokens

Claude Opus 5

Anthropic · $0.4412 / 1M tokens

Gemini 3.8 Flash

Google · $0.0551 / 1M tokens

Qwen3 Max

Qwen · $0.0784 / 1M tokens

The full list is in the model catalogue and the use-case collections.

Cherry Studio + OpenLux questions

Does Cherry Studio allow custom providers?

Yes. Any OpenAI-compatible endpoint can be added as a provider with its own API host, key and model list — OpenLux needs no special support.

Can I keep my existing OpenAI setup as well?

Yes. Providers are independent entries, so the official OpenAI provider and OpenLux can coexist and be switched per conversation.

Which models make sense in a desktop client?

Flagships for hard questions (GPT-6 Astra, Claude Opus 5) and cheap tiers for everyday chat (Gemini 3.8 Flash, DeepSeek V4). All are metered per token rather than per seat.

Where do I see what I spent?

In the OpenLux console, broken down by model and day. Cherry Studio itself needs no billing configuration.

Connect Cherry Studio to OpenLux today

One key covers every model in this guide and the rest of the catalogue, metered in USD with free trial credit to start.

Create an API key See pricing