Dashboard

By group

The group breakdown groups every LLM call by its group tag and shows you exactly which parts of your app are driving your bill.

What you'll see

• Total cost — cumulative spend for this group
• % of bill — what share of your total LLM spend this group represents. Highlighted in red when over 50%.
• Calls — total number of tracked calls for this group
• Avg tokens — average total tokens per call. High numbers here usually mean large context windows or long prompts.
• Avg cost / call — average spend per individual call. Compare this across groups to find efficiency gaps.
• Avg latency — average response time in milliseconds

What to look for

A large gap in avg cost / call between groups is a signal worth investigating. If search costs 10x more per call than chat, the likely cause is context window size — how many tokens you're passing in with each request.

Setting group tags

Group tags come from the group parameter in your SDK call:

await trackedCall({group: 'search',  // this is the tag...})

Use any string that makes sense for your product — a feature name, a team, a workflow, or a client. The group breakdown is only as useful as the tags you define. The same tag you pass here is what you set spend targets against in the Spend targets page.

Next: By user →