The Max tier

Max is one of four options in the composer’s engine menu, alongside Auto, and the other two tiers. It exists for the deepest reasoning we offer.

What it runs

The Max tier runs anthropic/claude-opus-5 by default, made by Anthropic.

Runs as	Input / 1M tokens	Output / 1M tokens
Max tier default	$6.00	$30.00
Max tier default, repeated context	$0.60	—

The second row is the repeated-context rate. When a request re-sends context the model has already seen, those tokens are billed at that lower rate instead of the full input rate — it is applied automatically by the biller, not something you switch on. See How billing works.

You can point this tier at a different model in Settings → How it works → Set an engine per speed tier, and you can override it for a single request from Pick an exact engine.

What lands here

Send work here when the task has many steps that depend on each other, when a mistake early on would quietly ruin everything after it, or when you would rather pay more than check the whole thing twice: multi-step analysis, reconciling sources that disagree, work you intend to act on without re-deriving it yourself.

Short, cheap, high-volume work does not belong here — you will pay more for the same answer. Fast is for that.

Two things this page deliberately does not tell you: how Auto decides, and how a request moves between models. Those are internal and we do not publish them. What we do publish is the above — pick a tier and you know which model runs and what it costs.

What it costs on a real run

Both examples below run as the Max tier default, at the two rates above:

Runs as	Run shape	Cost
Max tier default	4,000 in, 800 out (a short question with a little context)	$0.048
Max tier default	100,000 in, 10,000 out (a long document and a long answer)	$0.90

That is the whole arithmetic: tokens × the two rates. Nothing is rounded up, there is no per-run fee, and the receipt itemises every line. The ceiling on one request is this model’s context window, 1M tokens (about 750,000 words, roughly 1.5k pages) — instructions, attachments and the answer all share it.

What happens when it cannot run

If claude-opus-5 loses its price or its capacity, this tier does not silently run something else:

• If you had re-bound Max to your own choice and that choice lost supply, the tier falls back to its own default and tells you it did — you get a notice naming what you asked for and what actually ran.
• If the default itself is unavailable too, the tier reports itself unresolved rather than borrowing another tier’s model. There is no quiet cross-tier substitution.

This is the only failure behaviour we publish, because it is the only one we can point at in the code that implements it.

What you will and will not notice

You will notice: which tier you are on (the engine menu shows it), a fallback when one happens (it is reported, not hidden), and every charge (itemised on the receipt — see Reading a receipt).

You will not notice, because we do not expose it: how Auto chooses, or anything about where capacity comes from.

What we have not verified

• We publish no measured speed for this tier. Tiers are named for what they are for, not for how fast they run: “Max” is a meaning, not a benchmarked latency, and we have no timings we would stand behind.
• We publish no measured quality comparison between tiers. Nothing here claims Max answers better or worse than another tier on your work.

Next

• Model prices — every model and every price in one table
• The other tiers: Fast and Smart
• Start a run at elsedoes.com/home

Prices last changed 2026-07-29 (source ced6a4f). Every figure here is generated from the same pricing code that bills your runs.