---
title: It cost more than I expected
description: Six things to check, in order, when a run's total is higher than you planned for — starting with the two that explain most of the surprises.
---

Two things explain most of the surprises, and they are worth checking before anything else:
**the run was not on the tier you thought**, and **the spend limit you typed into a chat is
not applied**. Work down the list until one matches.

## 1. Check which tier the run was on

The receipt names it. If it says **Max** and you meant **Fast**, that is your answer —
tiers differ in what they cost per unit of work, so the same job is a different total on
each.

The trap is that the engine picker on the home screen is **your account default, not a
one-off choice**. Change it there for one cheap errand and every new chat afterwards runs
on it, with no reminder. The picker inside an open chat is scoped to that chat, and
**Retry** with a different engine also changes that chat's tier from then on. There is no
"just this message" scope. [Switching models](/docs/switching-models) lays out all four places
and which scope each one has.

## 2. Count the turns, not the runs

The invisible ceiling is **$0.50 per turn**, not per conversation. A conversation of six
turns can spend several times that, because each turn starts the count again. A long
back-and-forth is the most common way to a total that feels out of proportion to any single
answer in it.

## 3. Stop expecting the spend limit field to hold

In a chat, the number you type above the composer **is not applied** — nothing on our side
reads it. The run stops at the fixed per-turn ceiling instead, and slightly above it, because
the check happens after a step has already been paid for. On work you hand off the limit
*is* read, but only between steps and only against money already spent, so it cannot prevent
an overrun and never fires at all on a job that finishes in one push.
[Spending limits](/docs/spending-limits) is the full account, and nothing on this page softens it.

## 4. Look at what the work actually involved

Long work gets expensive faster than the length suggests: every step carries the
conversation so far, so step twenty is reading much more than step two. Large attachments,
many files, and repeated searching all compound the same way.
[Why it cost that much](/docs/why-it-cost-that-much) breaks a real total into its parts and is
the page to read if the first three checks did not explain it.

## 5. Check the receipt line by line

The receipt is the record — it is accurate about what you were charged even where a limit
was not honoured. It shows each priced piece of work rather than a single number, which is
usually enough to see which part of the job was the expensive one.
[Reading a receipt](/docs/reading-a-receipt) explains every field and where receipts appear.

## 6. Compare against the actual prices

If you want to check the arithmetic rather than the behaviour, the per-model prices and the
model each tier runs by default are on [Model prices](/docs/model-prices). Quoting a number here
without the tier beside it would be misleading, so that page is the only place we print
them.

## What to change next time

- **Set the tier deliberately, in the chat rather than on the home screen** — that keeps the
  choice from following you into every future conversation.
- **Hand long work off as a task.** That is the path where the limit you set is genuinely
  read, and where the running total is displayed against it as it goes.
- **Ask for one thing per run.** A run that has to figure out what you wanted spends money
  figuring it out — see [Writing a good request](/docs/writing-a-good-request).
- **Watch the running total, not the limit.** The limit is what you asked for; the total is
  what happened.

Else will never ask you to raise its own spend limit — a request to do so is rejected before
it can reach you. If you see one, it did not come from us.