Skip to content
Agentic Control Plane
Topic hub

What AI agents actually cost

Most writing about agent cost is guesswork. ACP meters and prices every tool call it checks, so these posts use measured numbers. The data is 285,814 tool calls across 96 of our own workspaces (our dogfood, not customer data; July 2026 snapshot). The agent loop was 97% of the spend. One model drove 77% of the bill from 30% of the model calls.

Most of those calls never touch a model, so the bill is the loop around the model, not the tools. The posts below cover the loop tax, the one step that should be most of the bill, and the runaway session that should not exist.

The headline numbers, with method and source, are on the data page. To price your own coding agent, start at ACP for coding agents.

Posts on agent cost

  1. How Much Does an AI Agent Cost? What 285,000 Tool Calls Showed
    We metered 285,814 tool calls across 96 of our own workspaces, as of July 2026. The tools are nearly free. The bill is the agent loop, and one frontier model drove 77% of the spend on 30% of the model calls.
  2. The Loop Tax: Why AI Agents Are So Expensive
    An agent doesn't make one model call. It makes a chain, re-reading its whole context every turn. In our June 2026 data that loop was about 89% of the bill. How it works, and three ways to cut it.
  3. Claude Code Cost Tracking: Token Counters Show What You Spent, Not Where It Went
    One real Claude Code day: 276 model calls, 1,697 tool calls, $148.16 at API rates, all of it loop cost. Why /cost, ccusage and proxy totals can't show that, and what per-turn attribution looks like.
  4. We Benchmarked 13 Models on Real Agent Runs
    Single tool-call scores barely predict whether a model can run an agent. We tested 13 models both ways in June 2026. Cheap models weren't worse, they were erratic.
  5. Stop your AI agent from burning through your API budget
    Cursor agents loop when context is summarized. Codex sub-agents have run $350 over plan in a week. A forgotten key produced an $18,000 bill. Here is how to set a spend cap and per-tier rate limits on your coding agents.

Related: Claude Code · tool-call economics · all posts