Current limit: 40 RPM
Requested limit: 200 RPM (or higher if possible)
Use case: Personal AI assistant (WorkBuddy agent), which makes
multiple sequential API calls per user request (tool calling, web
search, file reading, etc.). The current 40 RPM limit triggers 429
errors frequently, blocking normal usage.
Account email:2455413087@qq.com
Models used:
- deepseek-ai/deepseek-v4-pro
- deepseek-ai/deepseek-v4-flash
- qwen/qwen3-next-80b-a3b-thinking
Additional notes:
This is for personal development and productivity use. Not for
commercial deployment. Would appreciate any increase to keep the
agent workflow functional.