Show the usage meter beside the chat box. The red bar would indicate overage

If I understand the change correctly, messages in long chats will “cost” more of the usage now. It would be great if there were an indictor what the last message actually costed.

Sometimes I want to chat about things that are not urgent, so I don’t mind if I run out of the basic bucket and have to wait for it to refill, but other times, like when studying for an exam, I need to have the burst available, and I don’t want to spend the burst when I don’t need to, but I also don’t want to have to check my usage after each message. So it would be nice if we could lock it or something similar.

I know T3 Chat is a closed source Saas, but in recent weeks quiet a lot of features were released. I would be really helpful to get a „whats new“ or changelog overview each time to view what changed. Can be in settings or something and kept high-level for us users in order to not publish any internal secrets.

Using only 1 message in Pro, I can already tell it is insuffient for my needs eating up 3% of my 4 hour bucket in 1 message. But $50 a month for Premier is simply beyond my needs. So I propose a medium tier, maybe $15-$20 a month, that has around half of Premier's gains in usage. (Or better yet, a scalable model that lets you choose exactly what you want and pay more or less for what you want by month or as you go.)

Now that the model picker shows the relative model pricing, it would be a nice feature to be able to sort your favorite models by cost.

I am not aware whether T3 Chat has some feature that prevents search from not reputable sources. Considering increasing amount of AI articles and such (example: Understanding T3 Chat Pricing: A Deep Dive Into Value and Features - Oreate AI Blog) it would be good if T3 Chat had some blacklisted domains (possibly disclosed) with option to request blacklisting or maybe even personal domain blacklist feature. Without relevant context even SOTA models can provide “text prediction slop” rather than useful results and this will future-proof T3 Chat.

The only thing keeping me from never directly paying OpenAI again is the need to use the ‘Study’ / ‘Study and learn’ mode during exam season. It is an amazing tool to help you learn concepcts and it would be amazing if it could be added to t3chat😀

I mean I could easily do this myself (with a simple chrome extension), but it would be nice to have a hotkey to switch between profiles.

I know this isn't probably common for normal people and LaTeX rendering is hard, but just leaving it here as a suggestion.

The recently released 3.5 is much smarter than the Qwen 3 235b, which is also less efficient. Why it hasn't been deprecreated yet is beyond me. Could you pls add Qwen 3.5 thinking/non-thinking?

Rearrange favorite models and the overall model list.

Reasoning is long, and once I've read it, I want to stop looking at it. Right now the collapse button is just at the top of the block, which can be quite a scroll away This is on mobile, if that changes anything

Useful when Claude code is not needed like marketing, sales, social media, content writing, etc.

It has stable performance, please add it

Currently, when new model versions release, users must manually unfavourite outdated models and favourite the new ones. This is repetitive and easy to forget. Proposed Solution: Add a subtle update indicator to the model selector that surfaces when newer versions are available. UI Placement: A button with an update icon positioned next to the filter button. Clicking it reveals a checklist of updatable models with checkboxes to select which ones to update in the list. State Visual New updates available Accent-coloured icon, subtle pulse or badge Viewed but not updated Muted text colour, static icon All models current Hidden entirely This keeps the interface clean while making the update path discoverable without being pushy.

Every now and then (I haven’t measured the exact time, but it seems every 15-30 minutes), the T3 Chat UI shows the above error message. The “Reload App” button doesn’t do anything when clicked. Pressing F5 to refresh the browser shows the Vercel Security Checkpoint for a bit, then the T3 Chat UI works again. This started last week or so, that’s also the first time I’ve seen the Vercel Security Checkpoint UI. The error seems to be related to that as well, given that the technical details are Vercel’s HTML document?! I should note that this only happens when I access T3 Chat from my company’s network. That also causes other problems like LLM answers only appearing after they’ve been fully “typed out”. In the network tab, I can see a lot of “429 too many requests errors” for some requests like “api/server-version” and “api/status”, which could be related.

Vercel appears to block both Firefox and Chrome on Android, and also Firefox on Desktop (Linux), but not Chrome on Desktop. All devices with same IP address… If it was a free service, I would understand having a CAPTCHA. But for a paid service where a user logs in with an account and even has quite restrictive limits, this shouldn’t even exist imo…

A chrome extension that you can have t3 chat in a side panel on any screen, maybe even have it be able to get tab context from like google docs easily