Cost and usage

The LLM gateway meters every model call: tokens in and out, tokens read from and written to the cache, the cost in US dollars, and the job, agent, node and model it belongs to. Nodes cannot make a model call around it.

One job

run prints a job's cost when it finishes, and job get shows it at any time, one row per job in its tree:

orchestrator-zero job get job-bb270cf1-b194-4bf1-a0e3-267e061e416a

JOB                                       AGENT   NODES              MODELS                       CALLS  INPUT  CACHED  OUTPUT  COST
job-bb270cf1-b194-4bf1-a0e3-267e061e416a  lead    node-91378eb09343  anthropic/claude-sonnet-5-5  2      465    0       45      $0.0014
└ helper-30aa1892                         helper  node-d77d102ec079  anthropic/claude-haiku-4-5   2      307    0       44      $0.0005

NODES shows where each branch ran and MODELS which models answered, several when a fallback took over. A job with a budget shows it on the last line, and web searches by the provider's server tool are counted there too.

Costs that plugins report

A plugin that calls a paid service of its own reports what each call cost in its tool's result (see Tools). Those costs are part of the branch's COST and of the job's total, count toward its budget, and are listed under the table:

Reported by plugins:
  helper-11acc939 (helper): greetings, 1 greeting, $0.0005, by team
job job-62986020-404d-44c7-84e9-db653ec8c5af completed: 4 calls, 772 input and 89 output tokens, $0.0024 ($0.0005 of it reported by plugins)

They are not model calls: CALLS and the token counts leave them out. usage shows them as rows of their own, and the web UI's job page and Cost page mark them as reported by the plugin.

Across jobs

orchestrator-zero usage                      # the last 24 hours, by job, agent and model
orchestrator-zero usage --since 168h         # the last week
orchestrator-zero usage --job <job-id>       # one job
orchestrator-zero usage --tenant acme --json # for scripts and spreadsheets

A tenant's spending this month, and its monthly budget if it has one, are in tenant list; see A budget per tenant and month.

How prices are worked out

The gateway prices each call with genai-prices at the time of the call, from the usage the provider reports in the response or the stream, and adds $0.01 for each of Anthropic's web searches. Usage rows are kept in the management database and outlive the jobs' history in Temporal.