Live serving stats

GLM-5.3 Flash
4 queued
P50 queue wait: 19s
DeepSeek V4.1 Flash
21 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 HISTORY1-hour avg · Last sample 0m ago
API utilization
100%50%0%19 Nov, 07:5019 Nov, 10:5019 Nov, 13:50
Average API queue depth
42019 Nov, 07:5019 Nov, 10:5019 Nov, 13:50

DeepSeek V4.1 Flash

OPERATIONAL HISTORY1-hour avg · Last sample 0m ago
API utilization
100%50%0%19 Nov, 07:5019 Nov, 10:5019 Nov, 13:50
Average API queue depth
2613019 Nov, 07:5019 Nov, 10:5019 Nov, 13:50
All-time leadersTokens
01Navya Gupta15,820,976,362
02deesh7,062,636,402
03Udyaaa5,929,948,029
04Chakshita4,829,673,822
05aadeshgupta29-cell3,800,667,681
06akshaytheflash3,744,568,991
07Ayush Yadav3,609,008,199
08Pankaj Gupta3,341,829,608
Stewardship score
01Navya Gupta2,455
02Udyaaa1,920
03Sai Gautham Reddy Alavala1,852
04aadeshgupta29-cell1,787
05Pankaj Gupta1,713
06deesh1,580
07akshaytheflash1,580
08Chakshita1,546

Tokens served

All time
83,254,921,484Input
665,718,264Output
83,920,639,748Total