Public LLM AnalyticsMetadata only
Live usage and context telemetry
A public aggregate view of tracked LLM activity, including total request volume, large-context pressure, provider mix, and trend movement over time.
Window: Mar 11, 2026 - Apr 10, 2026•Updated Apr 10, 9:17 PM
Back to homeRequests
12
Estimated cost
$1.23
Over 15k rate
92%
Requests
12
Total tracked requests in the current reporting window.
Tokens
5M
Combined input and output token volume across all requests.
Large Context
92%
11 requests crossed the 15k input-token threshold.
Avg Latency
187.4s
Average response latency across requests with timing metadata.
Recent request activity
Last 14 days of total request volume with a 7-day week-over-week comparison.
This week
12
Previous week
0
Week-over-week
+100%
Mar 28Apr 10
Mar28
Mar29
Mar30
Mar31
Apr1
Apr2
Apr3
Apr4
Apr5
Apr6
Apr7
Apr8
Apr9
Apr10
Context health
Large-context activity and cost indicators for the same reporting window.
Over 15k requests
11
Average context usage
45%
Estimated total cost
$1.23
Top models
Most active models in the reporting window.
openai/gpt-5.4
145K tokens
9
claude-sonnet-4-6
5M tokens
2
gpt-5.4
16 tokens
1
Top providers
Provider volume and token distribution.
openai
145K tokens
10
anthropic
5M tokens
2
Top features
Where LLM requests are being used the most.
minimal-get-submit
5M tokens
2
current-coding-session
19K tokens
1