Liquid Apollo

Liquid Apollo

Fast, private, and reliable AI

681 ratings
152 reviews
Free

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


Price history


Details

Released
July 23, 2024
Updated
November 10, 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
iphoneDuo
ipad
🖼️Get Icon
Icons↘︎

About

Access a wide range of AI language models, from local on-device options to those available through external APIs. This app allows you to connect to open-source and privately hosted LLMs, offering a customizable client for diverse AI interactions.

✓Local AI model support
✓OpenRouter API integration
✓Custom backend LLM connection
✓Private on-device LLM execution
✓Access to diverse open-source models
✓Connect to privately hosted LLMs
Show original description

What users say about Liquid Apollo

See all reviews
+1

What's New in Liquid Apollo

2.3.2

November 10, 2026

- On-device models can now handle much longer conversations with a larger context window - Custom Backends now support image attachments for vision models - Read-aloud now favors Apple’s more natural Premium and Enhanced voices - Settings has a cleaner look - A handful of smaller fixes

More

User reviews

fake news: no LFM3 available

"""
What's New ›
Version 2.3.0
14h ago
Apollo 2.3 brings LFM3, Liquid Al's newest generation of on-device models. LFM3 packs more intelligence into less space, so it runs comfortably and privately right on your device.
"""

Nope. This was the whole reason I reinstalled the app (it was offloaded). I thoroughly tried all sorts of things, including eventually resetting the app via your in-app option to do so (btw, it does not seem to restart the app like it says it does), and then finally fully deleted the app anp and its data. The only difference: it shows less models at the intro model selection screen, but still no LFM3 models.

iPhone 17 Pro Max, iOS 27.[latest available] (27.2, I believe).

Back to the excellent NoemaAI app (and the less advanced Off Grid app, and Pocket Pal app), I suppose (although Noema's MLX support rejected your model, not recognizing the label for the new lfm3 family or model, and no CoreAI models with image/multimodality support were found, IIRC).

Replies are very welcome.
Show more

Only if

This is excellent, I wish you could update it to allow selection of Vision capability and Audio capability for models provide by custom servers.

I run oMLX, it supports vision, video, audio (STT, STS, TTS), all of which are available but cannot be utilised because the app itself isn't aware of it.

My local server models come with 1,048,576 context window, meaning it could easily support a local memory saved on the device to send with any chats but unfortunately the app does not support it.

At the very least being able to use vision for image and video with a local server would be great.

Also, the ability to reduce the size of icons and fonts; it feels too zoomed in.

Thank you for the great application.
Show more

Some issues

Nice app, but it keeps changing the model on openrouter and it can’t render latex outputs for some reason. Maybe it’s the model I’m using but it should work since it works on open routers test workspace.

Cannot remember the last model

Very frustrating that I have to tap 6 times to pick the model I want to use. Every single time.

Doesn’t work for local serving

The AI keeps cutting off context length based on the internal client side context limit and not the server side limits. 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 is Liquid Apollo?

Liquid Apollo is a customizable client for accessing a variety of AI language models. It supports local on-device models, connections to OpenRouter for a wide range of web-based models, and custom backends for privately hosted LLMs.

Does Liquid Apollo have ads?

No, Liquid Apollo does not contain advertisements. It is a free application without any in-app purchases or ads, as indicated by its monetization model.

What devices does Liquid Apollo support?

Liquid Apollo is available on macOS, iPhone, and iPad, allowing users to access AI models across different Apple platforms.

What is the age rating for Liquid Apollo?

Liquid Apollo has an age rating of 12+, making it suitable for users aged 12 and older.

How often is Liquid Apollo updated?

The latest version of Liquid Apollo is 2.3.2, which was last updated on November 10, 2026. This indicates a recent update, suggesting ongoing development and support.

What are the main benefits of using Liquid Apollo?

Users praise Liquid Apollo for its ability to work well with OpenRouter, its excellent support for running local models, and its clean, intuitive user interface. It also supports voice chat and shortcuts.

What are some reported issues with Liquid Apollo?

Some users have reported issues such as frequent crashes, glitches when editing messages, inconsistent message formatting, and slow performance with larger conversations. High battery consumption with certain models has also been noted.

Can I use my own AI models with Liquid Apollo?

Yes, Liquid Apollo supports connecting to your own locally-hosted private LLMs. You can run models on your computer using tools like LM Studio or Ollama and then connect to them via Apollo.