cost-report

cost-report — LLM Cost Breakdown

Generate a human-readable (or machine-readable) cost report from Hermes' own usage ledgers.

Procedure

1. Surface the numbers Hermes already keeps. There is no hermes logs export usage stream (that subcommand never existed) — use the built-in insights and logs views:

   hermes insights --days ${WINDOW}     # token + cost breakdown from session history
   hermes logs --since ${WINDOW} --component agent   # raw log lines for detail
   

2. Aggregate per-provider / per-skill splits. hermes insights rolls usage up globally. For the per-provider / per-skill / per-gateway tables below, pull from your tracing layer (self-hosted Langfuse via the observability/langfuse plugin — Part 20) or from a JSONL usage log you collect with the Part-20 log-tail pipeline. With such a JSONL file, DuckDB inspects it quickly:

   duckdb -c "
     CREATE TABLE logs AS SELECT * FROM read_json_auto('/tmp/hermes-logs.jsonl');
   
     -- By provider
     SELECT provider,
            SUM(cost_usd) AS cost,
            SUM(tokens_in) AS tok_in,
            SUM(tokens_out) AS tok_out,
            COUNT(*) AS calls
     FROM logs
     GROUP BY 1
     ORDER BY 2 DESC;
   "
   

3. Produce four tables:

   A. By provider

   Provider     Cost($)  Tokens-in   Tokens-out   Calls
   anthropic    18.44    2.1M        380K         412
   openai       6.20     1.2M        220K         187
   gemini       0.45     890K        140K         523
   

   B. By gateway

   Gateway     Cost($)  % of total
   telegram    14.22    56%
   cli         8.10     32%
   discord     2.77     11%
   cron        0.50     2%
   

   C. By active skill

   Skill                 Cost($)  Calls  Avg-cost
   claude-code           9.40     22     $0.43
   lightrag-query        4.11     189    $0.02
   pr-review             3.20     8      $0.40
   weekly-dep-audit      1.25     1      $1.25