# Models and prices

Drafts are written by a **language model** — a program that understands text
and can write it. draften calls it over the internet at a provider (Anthropic
by default; OpenAI or a model on your own server work too), and every use is
paid for. Here is roughly what it costs and how you keep it under control.

## Three tasks, three models

The assistant does not use the same model for everything. A cheaper one does
the simple work; the strong one only writes:

| Task | What it does | Default model |
|---|---|---|
| Triage | decides which new mail is the assistant's | Claude Haiku 4.5 (cheap) |
| Drafting | writes the draft, reading the knowledge sources | Claude Sonnet 5 (strong) |
| Learning | evaluates your edits and proposes lessons | Claude Haiku 4.5 (cheap) |

Which model and key the assistant uses is in Settings → **Models and keys**.
You usually need not change them.

## What it costs

Prices are in US dollars, as the model provider charges them; draften does
not convert them. Roughly, as measured on real mail:

| What | Per item | Typical month |
|---|---|---|
| triage of new mail | about 0.005 USD per check | under 1 USD |
| a draft (Sonnet 5) | 0.05–0.20 USD | 10–20 USD at 3–5 drafts a day |
| a draft (Opus 5) | 0.12–0.27 USD | 20–25 USD |

Long threads and drafts for which the assistant reads a lot in the sources
cost more. The new-assistant wizard is a one-off cost — before every paid
step it shows an estimate, usually a few dollars.

## Where you see the spend

- **Overview**, the **What the models cost** card — what writing, triage and
  learning cost over the chosen period, today's spend and the daily cap.
- **Mail** and **Drafts** — the cost of every message and draft.
- **Settings → Activity** — mail checks and requests with their outcome.

## Daily cap

In Settings → [Behaviour and limits](/en/behaviour-and-limits) you set a **daily
cost cap**. Once the assistant reaches it, it writes no more drafts that day,
evaluates nothing and starts no paid wizard step or trial; work under way
finishes. In the morning (by the organisation's time zone) the count starts
over. Mail arriving meanwhile gets the **limit** status.

The cap is a good safeguard in case an unexpected flood of mail arrives.

## Who pays

The model provider is paid through an **API key** — the organisation's, the
mailbox's, or the draften operator's default key. Who manages the keys is
described in the administrators' page [Model API keys](/en/admin/api-keys).