How much do AI coding agents actually cost to run?

The model API bill is the cost you see; the one that surprises you is context. An agent re-reads and re-derives your codebase every session, so most of the spend is tokens paid to re-learn what it already knew. Control it by giving agents a durable source of truth instead of re-reading the repo, and by making cost observable per task — so you tune a number, not a guess.

0106where the spend actually goes

Where the spend actually goes

Not the clever output — the context. Every agent, every session, re-reading the same files to rebuild understanding it had yesterday. At fleet scale that repetition is the bulk of the bill, and it's invisible until you measure per-task cost.

0206the fix is a context layer, not a cheaper model

The fix is a context layer, not a cheaper model

Serve agents the current, canonical answer about your codebase on demand (this is what trovex does — roughly 60% fewer tokens per lookup in our own use) instead of having them re-derive it. Cheaper models help at the margin; cutting re-derivation moves the number.

0306make cost a dial, not a surprise

Make cost a dial, not a surprise

Observability per task (what each run cost and produced) turns spend into something you tune. Without it, you only learn the bill at the end of the month and can't attribute it.

0406common questions

Straight answers.

Is a bigger model cheaper overall?: Not usually. The driver is how much context the agent re-reads, not the per-token price. A cheaper model that still re-derives the repo every session can cost more in total.
What's the ~60% number?: In our own use, serving agents the canonical doc via trovex instead of re-reading the repo cut roughly 60% of the tokens per lookup. It's the one hard number we stand behind; everything else stays qualitative.
How do we even see agent cost?: Instrument per-task: cost and outcome per run. That observability is the difference between tuning spend and guessing at a monthly bill.