Loading...
#
Model name
Time to first token
Avg duration
Success rate
Cache hit rate
Loading...
Based on real calls in the last 24 hours, updated every 5 minutes. Time to first token marked * is a speed-probe value (the model had no streaming calls in the last 24 hours).
#
Model
Calls
Input
Output
Cache hits
Loading...
#
Tool name
Calls
Number of users
Input
Output
Trend
#
Provider
Models
Input
Output
Fastest latency
Loading...
#
Provider
Calls
Input
Output
Trend
Loading...
#
Referrer
Referral points earnings
Loading...