# LLMConnect • AI Chat — user reviews

> 31 indexed App Store user reviews of LLMConnect by Sebastian Diaz Delgado, rated 3.50/5 from 4 ratings.

- Source: https://appshunter.io/ios/app/llmconnect-ai-chat/id6737247302/reviews
- App overview in markdown: https://appshunter.io/ios/app/llmconnect-ai-chat/id6737247302.md
- Rating breakdown: 5★ 2 · 4★ 0 · 3★ 0 · 2★ 2 · 1★ 0

## Newest reviews (11 of 31)

### 2/5 — Grundidee top, Umsetzung noch buggy

*2025-11-14*

Leider sind bspw. die Bot Konfiguration buggy und verliert immer die Einstellungen. Die Konfiguration der Prompts lässt sich nicht nutzen

### 2/5 — Many bugs but it includes a basic RAG system

*2025-09-24, version 2.2.04*

many bugs, missing basic function like full thread export to .txt log. Bg with threads always scowling back to first message and others. Would like more control on llm parameters.

### 2/5 — Needs work.

*2025-03-12*

Brilliant idea. Hope you’ll make a great product out of it. Good luck!

### 1/5 — Not free even use your own api

*2025-02-20, version 2.1.0*

Not free even use your own api

### 2/5 — Quality decreased and Price Increased

*2025-02-04*

I initially rated this 5 stars.  LLMConnect was amazing when it was initially released, but between the price increase and the decreased functionality, I’m no longer going to support this project.  The price increase didn’t affect me, but it was a major reason I initially rated it 5 stars.

### 1/5 — Didn’t work all of a sudden

*2025-02-04, version 2.1.0*

App suddenly stopped working. Restore purchase didn’t work. What a scam

### 1/5 — scam in the purest sense

*2025-01-31*

allows you to set up an entire backend structure for your hosted LLM, before then asking you to hand over $5-$10/month to use it. got me good, i’ll give ya that!

### 1/5 — Expensive and not fully functional

*2025-01-22, version 2.1.0*

The subscription is quite expensive and the save button doesn’t work when creating a bot.

### 2/5 — Expensive

*2025-01-08, version 2.0.04*

Gotta pay 8 bucks a month, good luck with that

### 1/5 — Currently broken, but it has enormous potential.

*2024-12-31*

The app is plagued by numerous technical issues and riddled with bugs. While these issues might be tolerable if the app were free, considering its paid nature, they render the app completely unusable. Moreover, the messages are being sent in reverse order to LLMs, so you can expect mixed results from state-of-the-art models.

### 1/5 — Seriously?

*2024-12-29, version 2.0.04*

I have to pay this much money to use MY OWN api keys from providers I already paid for?

## Most critical reviews (10 lowest-rated)

### 1/5 — Don't bother

*2026-05-25*

If you want a harness for your local inference build this is not the app for you. $50/yr price tag to be able to use your custom endpoint. I understand the dev needs to make money somehow but it completely defeats the purpose of blowing money on GPUs for free local inference.

### 1/5 — Looks polished but unusable

*2026-03-01*

It as if the owner of this app has never used it themselves. The font is too small, you’re unable to read the LLM response at the still generating. Meaning, if your response is four pages long, wouldn’t it be nice to be able to read the top while it’s still generating? You can’t do that here it just keeps blocking you… Many other defects that are surprising for something that requires a payment when there are apps like Cu that far exceed these capabilities for free.

### 1/5 — Many bugs.

*2025-10-24, version 2.3.4*

many bugs, missing basic function like full thread export to .txt log. Bg with threads always scowling back to first message and others. Would like more control on llm parameters. Typingmind is much better.

### 1/5 — No shortcut support

*2025-10-07*

Subscription without any shortcut support is sad

**Developer response:** Thank you for your feedback. We’d love to know what kind of Shortcuts support you’d like; for example, what actions you’d want to automate or trigger. 

Please email us at contact@llmconnect.co to share your ideas so we can start developing the integration.

### 1/5 — Still broken post update.

*2025-07-30*

I suspect the update was to reset the reviews. It still does not work and I would not recommend this product.

### 1/5 — keine Funktion

*2025-07-07*

Abo unbedingt erforderlich, ohne geht gar nichts. Okay, also Abo abgeschlossen…und die App lädt nicht einmal die Auswahl an KI Modellen. Völlig unbrauchbar.

**Developer response:** Hallo! Vielen Dank für dein Feedback. Es macht uns Sorgen, was du beschreibst, denn wir haben die App getestet und bei uns funktioniert alles einwandfrei. Könntest du uns bitte an contact@llmconnect.co schreiben und uns mehr über das Problem mitteilen?

Nur um sicherzugehen: Hast du bereits deinen API-Schlüssel eingegeben und die Modelle in den App-Einstellungen geladen? Die richtige Reihenfolge wäre:
	1.	API-Schlüssel eingeben
	2.	Verfügbare Modelle laden (der Button mit dem kreisförmigen Pfeil auf derselben Seite wie das API-Feld)
	3.	Ein Standardmodell auswählen

Bitte beachte, dass nur aktivierte Anbieter in der Auswahl sichtbar sind.

Falls das trotzdem nicht funktioniert, schreib uns bitte eine E-Mail – wir helfen dir gerne weiter. Es tut uns leid, dass du Probleme mit der App hast, aber wir sind hier, um sie so schnell wie möglich zu lösen.

Viele Grüße
– LLM Connect Team

### 1/5 — Does not work without payment

*2025-04-19, version 2.1.02*

Beautiful app, but does not work without subscribing, you can't even test it.

Deleted!

### 1/5 — Worst Mandatory In-App Purchase App Ever

*2025-03-30*

TL;DR: I DONT RECOMMEND

Like why? I can’t even send one single message to an ai to test the app, it immediately goes to prompting me to pay a outrageous monthly fee. This app is the definition of worst app possible.

### 1/5 — Stoped working

*2025-03-27*

Does not work on my phone any more.

### 1/5 — Does not work.

*2025-03-02*

Brilliant idea. 
BUT the app does not work.

**Developer response:** Hi Mark! We would love to get more feedback from you on which part of the app is not working. We’ve checked all the features, and everything seems to be working fine. Could you let us know which part of the app is not working for you or reach out to us through our website so we can discuss it further?

## Most praised reviews (10 highest-rated)

### 5/5 — Excellent

*2026-05-01, version 3.1.0*

Once optimised, provides a vastly superior LLM interaction experience. 

This coming from an individual with very little knowledge on the subject, still, very impressed. 

Good work gentlemen.

### 5/5 — Great app & developer

*2025-10-02*

App just keeps getting better. Works great with multiple providers, models, etc. Can connect to my locally hosted LLM, or run open source models on the device. 

Dev is open to feedback and quick for fixes (took only one day on two different occasions after bug reports).

### 5/5 — I want app like this

*2025-08-28*

Smart organization, feature with adding my keys! But it’s not free :(

### 5/5 — Thank you!

*2024-12-06*

Brilliant solution to get people out of hands of all those corporations that always hungry for money. Thank you for that! There are lots of features to add I hope you’re working on it. (On macOS I use BoltAI. In case you run out of inspiration - check it out).

### 5/5 — Fantastic features and one time pricing

*2024-11-08*

I’ve been using this app for a couple of weeks now and I find it invaluable.  I already had API keys which I use via Windows 11 apps, but couldn’t use them with my phone.  I hate subscription models and was so happy to come across this!

### 4/5 — Good App - couple bugs

*2026-01-04*

I have not found too many IOS/Ipad apps that support APIs such as Grok while also having the features you’d find on Linux/windows such as branching, memories etc.  Very customizable if you take the time to get used to it.  I do have two bugs that I hope get fixed - both regarding the main SYSTEM PROMPT.   There is thankfully a way to customize it as well as a restore button but (Bug #1) if you do a select all and erase all of the text of the prompt, the default prompt will re-appear as if you had pressed the restore button.   My work around is to do a select all but then unselect the first few characters and paste in or type the prompt I want to use and then erase the first characters.  This isn’t too annoying were it not for bug #2 if you fully close the app or reboot your phone, it does not remember or store the customized system prompt and always defaults back to original.   My work around is to just save the system prompt in the prompts library (which is a cool feature just type “/name” and the name of the prompt to save yourself some typing.  I then copy and paste the system prompt from the library before I begin new chats.   I’ve only played with the Bot feature a little and need to RTFM/play with before I can comment on.

**Developer response:** Hi! I’m glad you’re enjoying the app! Regarding the bugs, thanks for reporting them. I’ll look into it and fix it ASAP.

### 4/5 — Needs work.

*2025-03-06*

Brilliant idea. Hope you’ll make a great product out of it. Good luck!

### 3/5 — Very buggy

*2025-11-14*

Trying to use a custom provider. It connects and fetches models but always gives me

Error: The operation couldn’t be completed. (CustomProvider error 2.)

Lots of weirdness to the UI layout and navigation and gestures. This could be a solid four app if it worked right.

### 3/5 — Full featured and will be awesome someday!

*2025-10-23*

Plagued with ridiculous bugs… Stuff that’s easy to fix.  Like the menu button cannot be pressed.  Yes, it can be but like it takes 10 presses.  common Xcode problem.  Also, RAG is not implemented correctly apparently.   Would love to give them my money but too broken.

**Developer response:** Hi there!

We’re aware there’s an issue with iOS 26 affecting some buttons, but unfortunately that’s something out of our hands until Apple releases a fix. As soon as it’s possible for us to implement a workaround, we’ll do it ASAP.

Regarding RAG, could you tell us a bit more? What do you feel is not implemented correctly so we can improve it? You can reach us directly at contact@llmconnect.co, we’d love to hear more details!

### 2/5 — Unstable and unusable, clearly vibe coded without testing

*2026-07-17*

Ever since I started using this app months ago, there have been nothing but bugs with basic functionality. It seems vibe coded and untested. Frankly, this is not something that should be acceptable as a paid, public release on the App Store.

For example, every time the app is opened, or a new chat is started, it immediately reloads the most recent chat, so it is impossible to start a new chat without it loading the old one. 

Another example: Grok never worked despite having explicit support in the app because LLMConnect was trying to include parameters that don’t exist in its requests. These both seem like things that would come up very easily if the app was tested properly, even by an individual. 

Again this kind of thing should be kept in beta until it’s actually functional as an MVP. It seems like the developer blatantly ignored best practices just to collect a subscription fee.

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-08-12.*