Premium requests are exhausted too quickly — 22.4% used in one day on Copilot Pro (VS Code, Agent & Ask)

[CrazyNutLz]

Select Topic Area

Product Feedback

Copilot Feature Area

VS Code

Body

Hi everyone, I’m seeing what feels like a very small daily quota for "Premium requests" and I’m hoping someone from the community or GitHub staff can help explain.

I use GitHub Copilot heavily inside VS Code during my normal work hours. My primary modes are the Agent and Ask modes (Copilot Chat / Agent workflows). To save Copilot Premium requests, I exclusively used GPT-5.2-Codex and Claude Haiku 4.5. If I can use ChatGPT on the web (the ChatGPT web UI) I do that instead so it doesn’t consume Copilot Premium requests.

The problem

Despite all these measures, my Copilot account used 22.4% of the Premium requests quota in a single normal work day. This is on a Pro subscription. That feels far too low for a pro developer who uses Copilot heavily — I quickly run out of useful quota.

Questions

How are "Premium requests" counted exactly? (chat turns? tokens? background checks/telemetry?)

Are Agent/Ask modes more expensive than standard interactions? Could some features be burning quota faster than I expect?

Is this expected behavior for Copilot Pro, or is there a known bug/issue that causes unusually high consumption?

Are there recommended settings, usage patterns, or toggles to reduce Premium request usage while keeping useful functionality?

Any pointers to official docs about how Copilot counts premium usage would be great. If GitHub staff are monitoring this forum, I’d appreciate clarification — 22.4% per day makes the Pro subscription unusable for heavy daily use.

Thanks in advance for any help or explanations.

[github-actions[bot]]

💬 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. ⭐

[cmkushnir]

Looking at the multiplier list: https://docs.github.com/en/copilot/concepts/billing/copilot-requests#model-multipliers it seems your usage amount is correct. But yeah, 300 pr for a month is a bit low, even the 1500 for the next level up can be used quickly. Think the suggested usage is to use the 0x models, e.g. GPT-5 mini, for most stuff and save the pr for the big or final requests where you don't have a lot of follow-up instructions or tuning to provide.