💬 Your Product Feedback Has Been Submitted 🎉

Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users.

Here's what you can expect moving forward ⏩

• Your input will be carefully reviewed and cataloged by members of our product teams. 
  • Due to the high volume of submissions, we may not always be able to provide individual responses.
  • Rest assured, your feedback will help chart our course for product improvements.
• Other users may engage with your post, sharing their own perspectives or experiences. 
• GitHub staff may reach out for further clarification or insight. 
  • We may 'Answer' your discussion if there is a current solution, workaround, or roadmap/changelog post related to the feedback.

Where to look to see what's shipping 👀

• Read the Changelog for real-time updates on the latest GitHub features, enhancements, and calls for feedback.
• Explore our Product Roadmap, which details upcoming major releases and initiatives.

What you can do in the meantime 💻

• Upvote and comment on other user feedback Discussions that resonate with you.
• Add more information at any point! Useful details include: use cases, relevant labels, desired outcomes, and any accompanying screenshots.

As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities.

Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐

And my profile indicates only :

I am also getting it very frequently when assigning multiple issues to coding agent, only coding agent is using the requests. any way to increase the limits like a higher plan. it's really frustrating and negates the purpose of an autonomous agent if i have to come online after every 2 hours and restart the agent. i understand rate-limits are necessary but then at least have a way to schedule auto-retry for coding agents if rate-limited after the cooling period.

Can more transparency be added so we can keep using your api instead of having to look elsewhere? If you added - you need to stay under x requests per minute or wait 10min/1h etc to continue it would be a much better devx

I've run into this and have yet to find the setting that lets me pay for more. Please take my org's $$ and let me continue. I instead end up stalled halfway through the plan. Has anyone tried BYO model to get around this?

They are apparently throttling Pro accounts, making the chat completely unusable. Terrible management and product experience.

Yeah, this is nonsense. I'm here cause I'm currently wasting time waiting for the throttling to reset. I gave it one task: to refactor a class that had grown into a god class. I've hit the rate limit twice on the same task now. Maybe it should look at the request scope and at least say "Sorry Dave, I can't do that" rather than the unfriendly/useless way it's handling this issue. I've got a pro plan and there's a lot of credit left on it, so this is unacceptable. Do better.

I have also run into this issue multiple times before. Usually, this happens after excessive usage of one of the more premium models. A good way to tell this is to look at the right-hand side of the model selection UI:

The number that you see on the right indicates the current amount of rate usage a model consumes, and a more premium model (ex. the Claude 4.5 Opus I am using) will have a higher number, and thus hit the rate limit faster. Do not worry, because they usually reset within 24 hours, so you should gain access soon.

For me nothing is gonna change. I think there isn't any issue (for them), they're strictly applying their rules (https://docs.github.com/en/github-models/use-github-models/prototyping-with-ai-models#rate-limits (Pro+ could corresponds to Copilot Enterprise in the table)), so i downgraded from Pro+ to Pro (There is no reason to pay four times more if I cannot use the product four times as much). We've been talking about this for 4 or 5 days now, don't you think we would have already received help from Microsoft if it were a problem?

It's likely that AI providers for GitHub Copilot have cut off general access, and many users are hitting the limit even without using the available premium requests.

I'm already using the additional ones, but I'd never seen this rate limit before.

After statistical analysis, it was found that the recent rate limit storm began at 2026-04-13T12:31:44Z, after which a large number of people started complaining about rate limit issues. I'm inclined to believe this was a system configuration mistake.

Ok, I am definitely out of patience, 50 hours of wait time after a few requests is just too much. I had copilot subscription sicen it begins as a service but this is pure bullshit - unuseable in the real life in this form, not to mention we are all paying for something that we will literaly would not have a chance to use - there is simpli no scenario with this rate limits in place when one would be able to spend the 1500 requests in a month with f*ing 50 hours wait times between a couple of premium requests.

Goodbye Copilot, I will switch to continue or other VS Code package with my own api key.

btw: what pissess me even more is the fact all of this just hits out of nowhere, with no announcement in advance, no transparency to check what are the current limits for each models and if I am even close to hit some and if so, then for what time ... the only thing one will find is the bunch of pissed of people and one stupid changelog article digged up deep in the blog section, where this whole rate limit bullshit was mentioned with the same lack of transparency and as a "small change" on the side of Opus 4.6 retrie, that was not worth to notify users via email or so - https://github.blog/changelog/2026-04-10-enforcing-new-limits-and-retiring-opus-4-6-fast-from-copilot-pro/ - saas enshittification at ist best!

I bet 90% of users only stick with Copilot because of the subsidies and the existing per-request billing method
(I know I am).
Plus, the rate limits used to be quite flexible and user-friendly. With that being said

Copilot's performance is, at best, six months behind all of its competitors:

• We waited almost 6–7 months just for the "Hooks" feature.
• Sub-Agent Orchestration only started working acceptably after the last couple of updates.
• Now, we are going to have to wait another 5–6 months for the plugin feature.
• There is no default Copilot support (Or even discussion of planning one) for almost %99 of the open source projects (Even Kiro the one that nobodyh has used ever has more support than Copilot) .

Because even rare attempted projects implemantation docs most likely dosent work at all. Constantly pushing breaking changes makes impossible to keep these projects to add support for Copilot.
Even with uptime metrics dropping to 90% lately

The only real edge was its price-to-performance ratio.

Then, to top it all off, they decided to release major updates WEEKLY.

Yes, WEEKLY.

What is the point of an "Insiders" release if you are going to push a new stable version every single week?
Because of this constant swarm of half-baked features (hilariously half of them experimental flagged but most of it enabled by default anyway ) custom workflows are constantly degrading and failing to function properly.

That kind of instability makes trying to build anything reliable completely pointless. Even if I sat down right now and engineered a flawless, 100% deterministic workflow, it would be a total waste of time.

Give it two weeks, tops, and their relentless tinkering will just blow the entire setup apart anyway.

So instead of fighting it and wasting time resolving every tiny tweak needed to keep my workflows fully functional,

I just started to let things sit at 70–80% functionality and brute-force my way through by mashing the retry button under the chat session.

Than this bring us the latest situation. Now, I would argue that even with all of the problems I listed, Copilot still made a lot of sense to buy. But now, it's hilarious to even have to articulate this problem:

I am getting RATE-LIMITED TO THE POINT OF NOT BEING ABLE TO USE IT IN ANY WAY.

A 3-day rate limit. On a premium service that I paid for.

With absolutely no prior warning or observable metrics that show my usage rate.

With the events of the past two months, they have shown absolutely no interest in responding to community and customer complaints. Furthermore, they have been implementing anti-user policies at a pace similar to what we saw at Anthropic.

Conclusion

Therefore, in my opinion, Copilot has lost its only real advantage. Sure, the price is still the most reasonable out there, but that doesn't matter IF YOU CAN'T EVEN USE IT.

I'm a Pro+ subscriber and I've only used approximately 20% of my account quota, yet I've been hit with a rate limit ban — despite not using it consistently throughout the month.

I think this has become extremely frustrating. I'm seriously considering canceling my subscription, especially since there is no clear, visible weekly usage limit that we can track and monitor to understand how to properly manage our usage throughout the month.

At the very least, GitHub should provide a transparent usage dashboard showing the weekly rate limit so subscribers know where they stand before hitting an unexpected wall.

Has anyone used Cursor's Pro plan yet? What would be the alternatives to GitHub Copilot with similar usage patterns by the end of 2025?