Skip to content

Infinity Download

Every model. One window.

Pick how you want to run AI, then follow the steps. Most take two minutes.

Ask several: three models answering the same question side by side in Infinity — Mix local and cloud models, and ask up to four at once.

On your Mac

Free and private. Nothing leaves your Mac.

Ollama

Free models that run on your Mac. Infinity installs and starts Ollama for you.

LM Studio

Use the models you already have in LM Studio, on your Mac.

Apple Intelligence

Apple’s on-device model, with nothing to download or pay for.

MLX LM

Apple’s fast engine for running open models on Apple silicon.

With a plan you already have

Use your ChatGPT or Claude subscription. No API key.

Your ChatGPT plan

Use a ChatGPT Plus or Pro plan you already pay for, with no API key.

Your Claude plan

Use a Claude Pro or Max plan you already pay for, with no API key.

With your own API key

Pay the provider for what you use. Infinity adds nothing.

OpenAI

GPT models with your own OpenAI API key. Also makes images and handles voice.

Anthropic

Claude models with your own Anthropic API key.

Google Gemini

Gemini models with a key from Google AI Studio.

OpenRouter

Hundreds of models from many companies with one key.

Hugging Face

Open models in the cloud, plus images and transcription. Your token also unlocks gated downloads.

Groq

Very fast answers from open models.

Mistral

Mistral’s models with your own key.

xAI

Grok models with your own xAI key.

Together AI

Open models in the cloud with one key.

Anything else

Any server that speaks the OpenAI API.

Any OpenAI-compatible server

Jan, llama.cpp, vLLM, a server at work, or any service that speaks the OpenAI API.

Not sure where to start?Use Ollama: it’s free, private, and Infinity installs it for you. Add a cloud model later for the hardest questions, and use Ask several to compare them.

Keep going.

Download for Mac

Free · macOS 14+ · Apple silicon or Intel