Liquid Apollo

Liquid Apollo

Fast, private, and reliable AI

649 ratings
147 reviews
Free

Lowest price: $1.99 2 years ago (-%)


Price history


Details

  • Released
  • Updated
  • July 23, 2024
  • October 3, 2026

Features

Liquid Apollo screenshot #1 for iPhone
Liquid Apollo screenshot #2 for iPhone
Liquid Apollo screenshot #3 for iPhone
Liquid Apollo screenshot #4 for iPhone
Liquid Apollo screenshot #5 for iPhone
iphone
ipad
🖼️Get Icon
Icons↘︎

About

Access a wide range of AI language models, both locally on your device and through cloud APIs. This app allows you to chat with open-source models, connect to your own hosted LLMs, or utilize services like OpenRouter for broad model access.

✓Local LLM support
✓OpenRouter integration
✓Custom backend connections
✓Private AI chat
✓Access to open-source models
✓Connect to hosted LLMs
Show original description

What users say

See all reviews
+1

What's New in Liquid Apollo

2.2.7

October 3, 2026

• Chat: much smoother while a reply streams in • Default model: new chats stay on the model you picked or set in Settings • Models: each chat and each app keeps its own model - opening an older chat no longer changes the default • Quick actions: Start New Chat and Open Last Chat on the Home Screen and in Shortcuts now work reliably • Fixed crashes caused by some long text or code blocks

More

User reviews

Intuitive

The fact that the models here can use tools to search the internet for up to date information and also keep chats private puts it far above all the other apps that just let you chat with the model but have potentially outdated information. Not only that, it’s free as well.

Solid

I really like it. But I really need a "thinking effort" option and custom API image attachment support. Would also like to use the better Siri voices to TTS.

Barebones for connecting to self-hosted AI

There's no option for tool use

Background Phoning Home

Apollo restarts itself in the background (even when exiting the app) and proceeds to phone home all by itself: leap.liquid.ai (also sentry.io).
There is absolutely no reason for this app to be phoning home. And even more so when it is running in the background inadvertently. And it’s impossible to kill in Activity Monitor.

Users Beware.
Show more

Parameters and stop tokens

Parameters and stop tokens do not work when using a custom backend (llama.cpp on my home computer).
I could not find the option to add either of the aforesaid at all when running a local model.

Please fix.

Developer apps

User experience

🐞

Reported Bugs

6 issues

Unable to download Liquid Models

Bug

Deleted locally installed models

Bug

OpenRouter support crashes the app

Bug

Voice list doesn't load all available voices

Bug

Backspace lag leading to unintended text deletion

Bug

Inconsistent behavior when using code blocks

Bug
✨

Requested Features

10 requests

Add support for more open-source models (e.g. Gemma 3)

Feature

Implement image generation and upload functionality

Feature

Allow scheduling of asynchronous tasks

Feature

Integrate with Hugging Face model repository

Feature

Provide built-in prompt library

Feature

Add MCP (Multimodal Conversation Protocol) support

Feature

Enable direct OpenAI API integration

Feature

Improve voice chat functionality

Feature

Add option to delete all chat history

Feature

Implement search and filtering for chat history

Feature

FAQ

What can I do with Apollo - Powered by Liquid?

This app allows you to chat with private, local AI models, connect to open-source AI models, or access your own privately hosted LLMs. It acts as a customizable client for interacting with a wide variety of language models.

How does local model support work?

Local model support, powered by LEAP, enables you to run smaller LLMs privately and securely directly on your device. This means your AI interactions can happen without sending data to external servers.

Can I use popular AI models like ChatGPT?

Yes, you can access models like OpenAI's ChatGPT-4 by using an OpenRouter API key. By signing up at OpenRouter and pasting your key into the app, you can chat with a vast selection of models available through their service.

What are custom backend connections?

Custom backend connections allow you to link the app to LLMs you host yourself on your computer. Tools like LM Studio or Ollama can be used to run LLMs locally, and Apollo can then connect to these for a private, mobile-like experience.

Is this app free to use?

Based on the provided information, the application is free to use and does not have in-app purchases or advertisements. Any costs associated with using AI models would be through third-party services like OpenRouter or your own hosting.