Live serving stats
- GLM-5.3 Flash
- 6 queued
- P50 queue wait: 3m 37s
- DeepSeek V4.1 Flash
- 17 queued
- P50 queue wait: 37s
P50 is the median time spent in the queue before processing, over the last 60 minutes.
API history
How to read these charts
Utilization uses the capacity available at each reading. Before API and Chat readings were separated on 29 October, the charts use combined usage. Gaps mean no reading.
GLM-5.3 Flash
OPERATIONAL HISTORY5-minute avg · Last sample 1m ago
API utilization
Average API queue depth
DeepSeek V4.1 Flash
OPERATIONAL HISTORY5-minute avg · Last sample 1m ago
API utilization
Average API queue depth
All-time leadersTokens
01Navya Gupta16,882,193,738
02Udyaaa7,749,052,373
03deesh7,105,791,697
04akshaytheflash5,433,632,039
05Chakshita4,829,673,822
06Ayush Yadav4,012,655,794
07aadeshgupta29-cell3,990,182,908
08Pankaj Gupta3,368,271,545
Stewardship score
01Navya Gupta2,534
02Udyaaa2,080
03aadeshgupta29-cell1,875
04Sai Gautham Reddy Alavala1,853
05Pankaj Gupta1,716
06akshaytheflash1,624
07ArnavK-091,588
08deesh1,588
Tokens served
All time93,596,800,146Input
713,535,266Output
94,310,335,412Total