🎖️ Hermes Token Usage — Today

Generated 2026-07-20T01:00:43 • state.db + cron/jobs.json + config.yaml channel_honcho_hosts

Total tokens
86,739
in + out, excl. cache

API calls

2 sessions

Cache reads

878,861

91% cache hit rate

Est. cost
$0.02
placeholder rates

⚠️ Cost estimate uses placeholder rates ($0.10/M input, $1.00/M output). Real GLM-5.1 pricing is $1.40/M input, $4.40/M output. Configure agent/usage_pricing.py for accurate figures — today's real spend is likely 10-15x higher.

📈 Hourly Burn local time

Bars = tokens • Line = API calls

📊 By Source

🤖 By Model

⏰ Top Cron Jobs named from jobs.json

Job	Runs	In	Out	Cache	Calls	Avg dur	Total
⏰ test-agent heartbeat 60m 3c4b5e1c2b99 · MiniMax-M2.7	1	57,542	8,100	878,861	24	4.4m	65,642
⏰ token-logger 072c8aefbcf2 · MiniMax-M2.7	1	21,002	95	0	1	8.1s	21,097

🔥 Top 15 Sessions titled + parent-linked

Session / Job	Source	Model	In	Out	Cache	Calls	Dur	Total
⏰ (see cron jobs) cron_3c4b5e1c2b99_20260720_001641	cron	MiniMax-M2.7	57,542	8,100	878,861	24	4.4m	65,642
⏰ (see cron jobs) cron_072c8aefbcf2_20260720_000041	cron	MiniMax-M2.7	21,002	95	0	1	8.1s	21,097

⚡ Recent Activity last 30 sessions · today

Time	Kind	Session / Job	Tokens	Calls	Dur
00:16:42	⏰ cron	test-agent heartbeat 60m cron_3c4b5e1c2b99_20260720_001641	65,642	24	4.4m
00:00:42	⏰ cron	token-logger cron_072c8aefbcf2_20260720_000041	21,097	1	8.1s

Hermes Token Dashboard • 50 cron jobs · 19 channels · hourly refresh