Skip to content
Agentic Control Plane
Topic hub

What AI agents actually cost

Most writing about agent cost is estimation. We run a control plane that meters and prices every call, so these posts are built on our own metered data instead: 210,840 governed tool calls across 94 workspaces, where the orchestration loop was ~89% of total spend and one model drove 80% of the bill from 7.6% of the calls. The pattern that falls out — the loop tax, the leaf work, the one step that should be 90% of the bill and the runaway session that shouldn't — is the difference between cutting an agent bill and just staring at it.

All the headline numbers, with method and provenance, live on the data page. To price your own coding agent, start at ACP for coding agents.

Posts on agent cost

  1. What 210,000 Agent Tool Calls Actually Cost
    We metered 210,840 governed tool calls across 94 workspaces. The tools are nearly free — the bill is the agentic loop, and one model on it drove 80% of the spend.
  2. The Loop Tax: Why AI Agents Are So Expensive
    An agent doesn't make one model call — it makes a chain, re-reading context every turn. That loop is ~89% of the bill. The mechanic, and three levers to cut it.
  3. Claude Code Cost Tracking: Token Counters Tell You What You Spent, Not Where It Went
    A real working day of Claude Code: 276 model calls, 1,697 tool calls, $148.16 at API rates — 100% of it loop tax. Why /cost, ccusage, and proxy totals can't show you that, and what per-action attribution looks like.
  4. One step is 90% of our agent's model bill — on purpose
    We metered every tool call our agent builder makes. A single step accounts for 90% of the model spend. That's not a leak — it's the result of routing each step to the model it actually needs, which you can only do when cost is attributed per call.
  5. We Benchmarked 14 Models on Real Agent Runs
    Isolated tool-call skill barely predicts whether a model can run an agent. We tested 14 models two ways — and cheap models aren't worse, they're erratic on the loop.
  6. Cost Per Customer in CrewAI Agents
    CrewAI cost tooling stops at the LLM call. How to attribute agent spend per customer, per agent, and split the loop tax from the real work.
  7. Session X-Ray: Debugging a Single Agent Run, Call by Call
    The Agent X-ray shows you an agent across all its runs. The Session X-ray opens one run — every call in order, the loop tax inside it, and the single step that cost you. Here's how to read one.
  8. Control and Optimize Your Agents, Down to Each Tool Call
    You ship an agent and see one answer. Inside, it made 200 tool calls across a dozen model turns, and it cost something different every run. Here's how to see that, control it, and make it cheaper — one tool call at a time.
  9. Stop your AI agent from burning through your API budget — in three steps
    Cursor agents have looped overnight and burned $135 of credits in a week. Codex sub-agents have run $350 over plan. A leaked GCP key produced an $18,000 bill. The fix isn't smarter prompting — it's a control plane with rate limits and budget caps.

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