AI Summary
5 min read"50 messages every seven days for GPT 5.5 and 50 for Claude Opus 4.8 — and that's it." Federico Vatici's experience with Raycast's Advanced AI tier captures the core tension of the AI aggregator market: these apps promise choice and convenience, but the economics of frontier models make unlimited access through a third party nearly impossible.
In this episode of AppStories, John Voorhees and Federico Vatici survey the rapidly evolving landscape of apps that aggregate multiple large language models (LLMs) into a single interface. They cover the major players — Raycast, Bolt AI, Perplexity, and Notion AI — and assess the tradeoffs between using an aggregator versus sticking with an official client like ChatGPT or Claude.
The aggregator promise and its pitfalls
The central appeal of AI aggregators is straightforward: instead of managing separate subscriptions to OpenAI, Anthropic, Google, and others, you pay one fee and access everything from one app. This is especially attractive for power users who want to compare model outputs or experiment with the latest releases — Perplexity, for example, typically adds new frontier models within hours of their launch.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of AppStories
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (00:31) **Topic Introduction: AI Aggregators** - The hosts introduce the topic of apps that aggregate multiple LLMs from different providers (OpenAI, Anthropic, Google, open-source), contrasting them with using official clients.
- 2 (02:40) **Pros and Cons of Aggregators** - Discussion of the general advantages and disadvantages of using a multi-model aggregator.
- 3 (05:00) **The Key Downside: The Harness vs. The Model** - The most important factor: using a model through an aggregator means using a different "harness" (system prompt, integrations), not the official one.
- 4 (08:24) **Coding Aggregators and Pricing Models** - A brief look at aggregators in the coding space and a deeper dive into the confusing pricing landscape.
- 5 (14:31) **Raycast on iOS and macOS** - Federico's deep dive into Raycast's AI features, which now include system integrations and MCP support on iOS.
- 6 (21:31) **Bolt AI: A Native Mac App** - A look at Bolt AI, a native macOS and iOS app that is a pay-once, BYOK aggregator.
- 7 (23:20) **Perplexity: The Search-Forward Aggregator** - An overview of Perplexity, which started as a search engine replacement and now offers a powerful desktop agent ("personal computer").
+ Full timestamped outline available in the app
Guests on this episode
Show Notes
This week on AppStories, This week, Federico and John talk about the state of AI aggregator apps and their future prospects before checking in on their current AI app setups for the AppStories+ post-show.
Also available on YouTube here.
Subscribe here.
We deliver AppStories+ to subscribers with bonus content, ad-free, and at a high bitrate early every week.
To learn more about an AppStories+ subscription, visit our Plans page, or read the AppStories+ FAQ.
This episode is sponsored by:
- Mercury Weather: Forecasts, beautifully done. Download now for free.
- Claude: For problems worth solving — get started with Claude today.
Links and Show Notes
AI Aggregator Apps
- The Pros and Cons of AI Aggregator Apps
- Apps Mentioned