Currently, the $ to $$$ badges are too broad. Models with very different costs often share the same $$ rating, making it hard to choose the most cost-effective one. It would be awesome if we could just hover over the dollar signs to see a tooltip with the exact API cost (e.g., Input: $1.25 / 1M | Output: $2.50 / 1M). This solves the granularity issue without cluttering the current clean UI.

https://github.com/JuliusBrussee/caveman#before--after

Can you please add the date the chat was created next to the chat so that we can more easily filter through chats? Thanks

In the past few days, it seems automatic scrolling has been introduced while the model generates tokens. It never used to be this way, it stayed where it was and you scroll at your own pace, but now it force scrolls down as the model outputs even if you try to scroll back it forces you to scroll to the end. It's outputting at hundreds of tokens a second so I haven't even read the first paragraph and it's scrolling to the end :,(

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

Users with long chat histories struggle to track down older conversations and have requested ways to search or filter by date. While adding timestamps to every chat title would clutter the clean UI, requiring users to type complex search commands (like date:2023) is too advanced and hidden for the average user. The Proposed Solution: Add a small "Filter" icon (like a funnel) directly next to or inside the "Search your threads..." bar. Clicking this icon would open a small, simple dropdown menu allowing users to visually select a timeframe. This dropdown could include quick options like "This Month", "Last 3 Months", or a simple calendar/date-range selector. Once selected, the sidebar only displays chats active during that period. The Benefit: This provides an incredibly intuitive, point-and-click way for average users to filter their chat history. It completely solves their frustration of losing older chats, makes the feature highly visible, and perfectly preserves the minimalist design of the chat list itself.

Users can sometimes lose track of their chats. While the sidebar logically groups chats by recent activity (e.g., "Last 7 Days", "Last 30 Days", "Older"), it doesn't give the precise date. Adding visible dates to the sidebar list would ruin the clean, minimalist design of the interface, but users still need context for when they last worked on a thread. Proposed Solution: Update the existing hover tooltip on sidebar chat titles (which currently just repeats the title). When a user hovers over a chat, it should display the specific date the user last interacted with it. Example Tooltip text: "History Lessons... (Last Active: May 12, 2026)" This keeps the UI clean while giving users exact clarity.

Testing Ernie 5.1 I was really impressed with it's creative writing capabilities. On par or better than Opus 4.6. can we add it to the available models on T3 Chat?

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.

Can't believe nobody asked for this yet. Add a Filter to the list in Settings > Models to filter based on knowledge cutoff.

You have the information for some of the models for Intelligence, Coding, and Math. It would be good to sort/filter by these performance metrics so that users can know which models are better at each without having to go into each model individually or look it up.

It would be really useful to have a way to archive profiles and then restore them later if needed. I am a student and use a profile for each class I am taking (so I have quite a few) and don’t want to delete them completely when I’m done with the class but also don’t want them on the sidebar and in the various menus. Yes, you could delete the profile and move the threads to another profile, but this isn’t really a solution as you are still losing the grouping information (I might want to look back at all the chats for an old class). My current workaround is to just download all of my account’s thread content from settings and use a script to extract specific profiles from that. Another minimal solution would be to make it easy to select all threads from a profile in the settings menu to make local archival of a profile a lot easier.

On PC, I’m used to doing Enter for send, and Shift+Enter for new line. On my tablet, however, the touch keyboard won’t allow me to send Shift+Enter, so I enabled the “Invert Send/New Line Behavior” setting and it solved my issue! However, this setting appears to sync between clients, leading to accidental sends after switching between clients. Bounding this setting to the client instead of syncing it would fix this issue, and should be pretty easy to implement. A middle ground could be a synced default and a local, persistent override. Ideally, we would only have to configure this behavior once per device and not have to keep mental track of which client we used last or go to the settings to change each time we open the website.

There’s currently a temporary chat feature. But what I’d like to have is for the temporary chat feature to be default. There should be an option that inverts the current behavior, where all future chats start off as temporary by default, but then I can hit the toggle button in the top-right to mark it as permanent. Most of the time, my chats are just stupid things that aren’t worth keeping. There’s another feature request to auto-delete chats after a certain time. I think that would also work for my purposes here, assuming it’s also something where the default is for all chats to auto-delete, and it’s not something I have to manually enable on a per-chat basis.

I need T3 to be able to provide a functioning download link for a file in Word format.

For some time now google keeps their new models as “preview“ for very long time and then they silently release GA versions. It would be nice to know what exact model I’m using. That could be displayed after hovering the information icon.

The Problem: Currently, switching to a different model resets all user settings, such as "Thinking Effort" and "Search." Because most models share similar capabilities, these settings should persist. While I understand that certain settings (like thinking effort) can't carry over to non-thinking models, universal settings like Search should not reset. The Impact: Wasted Usage/Quota: I often switch models and ask a question quickly, only to realize the search setting was turned off. This forces me to re-ask the question, burning through my usage limits. Mobile Friction: This is especially frustrating on the mobile view, where the search setting isn't immediately visible and requires extra clicks into a secondary menu to verify. Proposed Solution: Please make user preferences persistent across model changes. If my default preference is "Search x2" and "Medium Thinking," those should stay active whenever I switch to a compatible model.