Live serving stats

GLM-5.3 Flash
1 queued
P50 queue wait: 12s
DeepSeek V4.1 Flash
18 queued
P50 queue wait: 1m 42s

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
100%50%0%19 Nov, 07:4619 Nov, 10:4619 Nov, 13:46
Average API queue depth
84019 Nov, 07:4619 Nov, 10:4619 Nov, 13:46

DeepSeek V4.1 Flash

OPERATIONAL HISTORY5-minute avg · Last sample 1m ago
API utilization
100%50%0%19 Nov, 07:4619 Nov, 10:4619 Nov, 13:46
Average API queue depth
2915019 Nov, 07:4619 Nov, 10:4619 Nov, 13:46
All-time leadersTokens
01Navya Gupta15,820,727,974
02deesh7,062,289,110
03Udyaaa5,929,338,186
04Chakshita4,829,673,822
05aadeshgupta29-cell3,800,608,583
06akshaytheflash3,743,514,695
07Ayush Yadav3,609,008,199
08Pankaj Gupta3,341,829,608
Stewardship score
01Navya Gupta2,455
02Udyaaa1,920
03Sai Gautham Reddy Alavala1,852
04aadeshgupta29-cell1,788
05Pankaj Gupta1,713
06deesh1,580
07akshaytheflash1,580
08Chakshita1,546

Tokens served

All time
83,251,361,598Input
665,702,718Output
83,917,064,316Total