I am a GitHub Copilot Pro user and I want to share feedback about Copilot Pro AI Credits usage has become unpredictable and too costly after token-based billing #198389
Replies: 2 comments
-
|
💬 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 ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
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. ⭐ |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
🏷️ Discussion Type
Product Feedback
💬 Feature/Topic Area
Copilot Agent Mode
Body
I am a GitHub Copilot Pro user and I want to share feedback about the new AI Credits usage model.
My Copilot usage suddenly reached around 73% very early in the monthly cycle. This is surprising because my normal development workflow has not changed significantly. The new token-based usage model feels much less predictable compared to the earlier request-based model.
For regular developers, it is very difficult to understand how much usage will be consumed before running Copilot Chat, Agent mode, premium models, or large-context prompts. A single broad coding task can consume credits very quickly, especially when repository context, agent loops, and generated code are involved.
I have now configured a $0 budget with “Stop usage” enabled, but that only prevents extra billing. It does not solve the main problem: Copilot Pro can become unusable very early in the month without enough warning or control.
My requests:
The current model feels significantly more expensive and unpredictable for normal software development work.
Beta Was this translation helpful? Give feedback.
All reactions