Skip to main content
Use the credit and usage views in Fetch Hive when you want to understand where spend, tokens, and run-level usage appear in the product.

​
Overview

Fetch Hive shows usage in more than one place. Dashboard analytics gives you the workspace-level view, while log tables and run detail sheets show usage for individual prompt, workflow, and agent runs. These surfaces work together. Start with analytics when you want the broad picture, then move into logs and run details when you need a single-run explanation.

​
Where do I see credit usage across the workspace?

Open Dashboard in the main sidebar, then click Analytics. This page gives you the main workspace-level usage views:
  • Total Cost
  • Service Costs
  • Model Costs
  • Token Usage
Use Token Usage when you want the breakdown across input, cached, reasoning, and output tokens. The Claude Prompt Cache setting controls whether Fetch Hive asks Anthropic to cache stable prompt prefixes for a prompt, workflow AI step, deployment, or agent. It does not change the usage fields shown here; cached token reads and writes continue to appear in the existing cached-token usage breakdowns. Use Model Costs and Service Costs when you want to understand where spend is coming from. Open Show all from Model Costs when you need every model row for the selected date range.

​
How do I inspect cost and token usage for an individual run?

Open Prompts, Workflows, or Agents, then click Logs. Prompt logs show Total Tokens, Total Cost, and Duration in the main table. Agent logs also show Total Tokens, Total Cost, and Duration in the main table. Workflow logs show Total Cost and Duration in the main table, along with the tools used in that run. Prompt and agent logs include hover breakdowns for token and cost details directly from the table. Workflow logs include a hover breakdown for run cost. Cost breakdowns use Estimated task credit cost for the Fetch Hive platform portion. This estimate is based on your included plan tasks or purchased top-up tasks; hosted LLM wallet charges are shown separately when they apply. Click a row to open the detail sheet for that run. The summary strip at the top gives you the fastest run-level view of cost and usage.

​
What appears in run details?

Run detail sheets surface different usage details depending on the run type. Prompt run details show summary pills for items like Tokens, Cost, Duration, and Charge Type. Workflow run details focus on Cost, Duration, and Tools in the summary strip. Agent run details go furthest. They show Tokens, Credits, Cost, Duration, and Tool Calls in the summary strip. If you open a traced run and select a span tied to a completion, Fetch Hive can also show usage details for that specific part of the run in the span detail panel.

​
What’s included in these totals?

Fetch Hive separates usage by surface:
  • Workspace analytics aggregates usage for the selected date range
  • Log tables show run-level totals for the rows in that view
  • Run detail sheets expose the same run at a deeper level, with trace and span context when available
The exact fields vary by run type, so it is normal for prompt, workflow, and agent views to show different combinations of tokens, tools, cost, and credits.

​
Notes

  • Task credit cost is an estimate, not a separate plan invoice charge for each run.
  • These views show usage signals in the product UI. Check your plan or billing terms separately for pricing and billing rules.
  • If you want the workspace-level monitoring view first, start with Analytics.
  • If you want the full log and trace workflow, see Log History.