🎖️ Hermes Token Usage — Today

Generated 2026-08-18T02:00:03 • state.db + cron/jobs.json + config.yaml channel_honcho_hosts
Total tokens
213,565
in + out, excl. cache
API calls
37
2 sessions
Cache reads
3,112,526
94% cache hit rate
Est. cost
$0.05
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

JobRunsInOut CacheCallsAvg durTotal
⏰ influencer-summary-evening
0cf1001ff044 · MiniMax-M3
 1 128,263 33,168 2,915,103 32 12.1m 161,431
⏰ milestr-pipeline
dfaa98141ce1 · MiniMax-M3
 1 50,885 1,249 197,423 5 43.3s 52,134

🔥 Top 15 Sessions titled + parent-linked

Session / JobSourceModel InOutCache CallsDurTotal
⏰ (see cron jobs)
cron_0cf1001ff044_20260818_010500
 cron MiniMax-M3 128,263 33,168 2,915,103 32 12.1m 161,431
⏰ (see cron jobs)
cron_dfaa98141ce1_20260818_000115
 cron MiniMax-M3 50,885 1,249 197,423 5 43.3s 52,134

⚡ Recent Activity last 30 sessions · today

TimeKindSession / Job TokensCallsDur
01:05:01 ⏰ cron
influencer-summary-evening
cron_0cf1001ff044_20260818_010500
 161,431 32 12.1m
00:01:15 ⏰ cron
milestr-pipeline
cron_dfaa98141ce1_20260818_000115
 52,134 5 43.3s
Hermes Token Dashboard • 50 cron jobs · 19 channels · hourly refresh