🎖️ Hermes Token Usage — Today

Generated 2026-10-26T00:10:13 • state.db + cron/jobs.json + config.yaml channel_honcho_hosts

Total tokens
162,053
in + out, excl. cache

API calls

4 sessions

Cache reads

1,194,966

88% cache hit rate

Est. cost
$0.03
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

🔥 Top 15 Sessions titled + parent-linked

Session / Job	Source	Model	In	Out	Cache	Calls	Dur	Total
💬 Create Milestr AI agent assessment 20261026_000556_a6add375	slack	MiniMax-M3.1-Flash	105,594	9,919	1,133,089	17	0s	115,513
❓ subagent 20261026_000822_c4597a ↳ child of 20261026_000556_a6add375	subagent	MiniMax-M2.7-highspeed	31,722	1,361	48,565	4	0s	33,083
❓ subagent 20261026_000822_fa8086 ↳ child of 20261026_000556_a6add375	subagent	MiniMax-M2.7-highspeed	12,899	190	256	1	0s	13,089
❓ subagent 20261026_000822_904c1d ↳ child of 20261026_000556_a6add375	subagent	MiniMax-M2.7-highspeed	79	289	13,056	1	0s	368

⚡ Recent Activity last 30 sessions · today

Time	Kind	Session / Job	Tokens	Calls	Dur
00:08:22	❓ subagent	❓ subagent 20261026_000822_904c1d ↳ 20261026_000556_a6add375	368	1	0s
00:08:22	❓ subagent	❓ subagent 20261026_000822_c4597a ↳ 20261026_000556_a6add375	33,083	4	0s
00:08:22	❓ subagent	❓ subagent 20261026_000822_fa8086 ↳ 20261026_000556_a6add375	13,089	1	0s
00:05:56	💬 slack	Create Milestr AI agent assessment 20261026_000556_a6add375	115,513	17	0s

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