6,610tokens a browser toolset adds before the agent reads its task

Your token budget cannot see four of the charges on the bill

A ceiling written into the prompt is advice. The orchestrator is the only layer that sees tool overhead, per-search fees and runtime charges, and can stop.

Cost9 minSep 25cited

4 / 7steps a machine can verify

Which agent steps need a frontier model? Route by verification

Frontier token prices rose 72% in a year while mid-tier prices fell. The saving is in routing per step, and one question decides which steps to downgrade.

Cost8 minSep 21own measurement

70%pass rate reshapes cost per task

What does one agent task cost? The arithmetic, worked through.

Nobody prices an agent per call. Here is the full calculation, with published token rates, the multipliers people forget, and a worked example.

Cost9 minSep 14own measurement

15.5Ktokens per case

Multi-agent designs cost 4x to 8x more tokens. When does that pay off?

Published papers put a single agent at 1.9K tokens against 15.5K for the best multi-agent method. The overhead is real. So is the accuracy gain.

Cost8 minSep 12cited

1token invalidates the prefix

One changed token at the front invalidates the whole prompt cache.

Caching is the cheapest lever on an agent bill, and agents keep breaking it. What invalidates a prefix, and how to order context so it survives.

Cost8 minSep 12cited

50×spread in break-even estimates

Self-hosting break-even estimates disagree by 50x. Here is why.

Published numbers are not wrong, they answer different questions. Utilisation is the hidden variable, and nobody puts it in the model.

Cost8 minSep 12cited

−35.8%token price, year over year

Budget tokens fell 36% this year. Frontier pricing doubled.

Headlines say inference is getting cheaper. Trackers say the market split in two, and agents run on the half that got more expensive since January.

Cost7 minSep 12cited