What version of Kimi Code CLI is running?
kimi 2.6
Which open platform/subscription were you using?
moonshot.ai
Which model were you using?
kimi2.6
What platform is your computer?
windows 10
What issue are you seeing?
Subject: Critical Bug: Incorrect TPD Calculation and Severe Latency on Tier 0
I am a new user who registered today and topped up $5 to test the Kimi k2.6 model. I am extremely disappointed as I am encountering a critical bug that prevents me from evaluating the model.
Despite only using approximately 150,000 tokens across my sessions, I am receiving a "Request reached organization TPD rate limit" error claiming I have hit 1,505,241 tokens. It appears the system is incorrectly calculating the context refresh or directory scanning as consumed tokens, effectively locking me out of my daily quota after only a few minor requests.
Additionally, the latency is unacceptable, with the model taking 5 to 7 minutes to respond to a single query. This makes the tool completely unusable. Please investigate this discrepancy in token counting and the severe performance issues for new Tier 0 accounts.
What steps can reproduce the bug?
LLM provider error: Error code: 429 - {'error': {'message': 'Your account org-20c6704033e44fc495ca875175c492a9 / proj-5c2d04a3e8d540e4a4de9884ec74a073 request reached organization TPD rate limit, current: 1505241,
limit: 1500000', 'type': 'rate_limit_reached_error'}}
If this persists, run kimi export and send the exported data to support for assistance. Please do not share the exportedfile publicly.
What is the expected behavior?
No response
Additional information
No response
What version of Kimi Code CLI is running?
kimi 2.6
Which open platform/subscription were you using?
moonshot.ai
Which model were you using?
kimi2.6
What platform is your computer?
windows 10
What issue are you seeing?
Subject: Critical Bug: Incorrect TPD Calculation and Severe Latency on Tier 0
I am a new user who registered today and topped up $5 to test the Kimi k2.6 model. I am extremely disappointed as I am encountering a critical bug that prevents me from evaluating the model.
Despite only using approximately 150,000 tokens across my sessions, I am receiving a "Request reached organization TPD rate limit" error claiming I have hit 1,505,241 tokens. It appears the system is incorrectly calculating the context refresh or directory scanning as consumed tokens, effectively locking me out of my daily quota after only a few minor requests.
Additionally, the latency is unacceptable, with the model taking 5 to 7 minutes to respond to a single query. This makes the tool completely unusable. Please investigate this discrepancy in token counting and the severe performance issues for new Tier 0 accounts.
What steps can reproduce the bug?
LLM provider error: Error code: 429 - {'error': {'message': 'Your account org-20c6704033e44fc495ca875175c492a9 / proj-5c2d04a3e8d540e4a4de9884ec74a073 request reached organization TPD rate limit, current: 1505241,
limit: 1500000', 'type': 'rate_limit_reached_error'}}
If this persists, run kimi export and send the exported data to support for assistance. Please do not share the exportedfile publicly.
What is the expected behavior?
No response
Additional information
No response