Costs & Budgets
Warning: AI agents make real API calls that cost real money. Every time an agent works — every heartbeat, every task, every comment it reads and writes — it sends and receives text through a provider…
Costs
> Warning: AI agents make real API calls that cost real money. Every time an agent works — every heartbeat, every task, every comment it reads and writes — it sends and receives text through a provider like Anthropic or OpenAI, which charges you per token (roughly per word). This isn't a Paperclip fee; it's a cost you pay directly to the AI provider. Read this guide before your agents start running in earnest.
Paperclip's budget system exists to make sure you're never surprised. You set limits, and the platform enforces them automatically — an agent won't spend a cent beyond what you allow.
The Costs page in the sidebar is where all of this lives. It has five tabs — Overview, Budgets, Providers, Billers, and Finance — plus a shared date-range selector and four headline metrics at the top. This guide walks through each tab, then folds in the core concepts around how costs work, how budgets protect you, and how to tune spend over time.
---
How Costs Work
Every time an agent runs a heartbeat, it generates an API call. That call sends the agent's context (its identity, its tasks, the instructions it's working from) to the AI provider, and receives a response (the agent's reasoning and next actions). The provider charges based on the number of tokens — input tokens (what's sent) and output tokens (what comes back).
Paperclip records every one of these calls: which agent made it, which model it used, how many tokens were used, and the exact dollar cost. These records are aggregated per agent per calendar month (resetting on the 1st of each UTC month).
> Note: A token is roughly equivalent to one word, though technically it's a fragment of text slightly smaller than that. A busy agent doing coding or writing work might process 100,000–500,000 tokens per month. At typical Anthropic pricing, that's roughly $3–$15 per month for a moderately active worker agent — but this varies significantly based on the model used and how much context each task requires.
Beyond per-request inference costs, there are also account-level charges — monthly subscription fees, credit top-ups, invoice adjustments, refunds — that don't map to a single API call. Paperclip tracks those separately in the finance ledger so you can reconcile your actual provider invoices against what Paperclip thinks you spent.