For users
← All topics

Models and prices

Which model sorts, writes and learns, what one draft costs and how to save without losing quality.

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:

TaskWhat it doesDefault model
Triagedecides which new mail is the assistant'sClaude Haiku 5.5 (cheap)
Draftingwrites the draft, reading the knowledge sourcesClaude Sonnet 5.5 (strong)
Learningevaluates your edits and proposes lessonsClaude Haiku 5.5 (cheap)

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

Assistants that wrote with Claude Sonnet 5 were switched to Sonnet 5.5 at the same price with the draften update, and triage and learning from Claude Haiku 4.5 to Haiku 5.5 at a tenth of the price; assistants on older OpenAI GPT-5 models were switched to GPT-6 models. You see the new model in the assistant's Settings and on every new draft; the switch does not appear in the change history.

Model effort

Effort is how thoroughly the model thinks before it answers: a higher one tends to be more careful, but takes longer and costs more. It is set for each task separately — in Settings → Models and keys, the Key and model per task card, the Model effort field under the model in the Triage, Drafting and Learning boxes.

The first choice, the model's default, lets the model work at its default level (the brackets show which one that is). The effort returns to it after a change of model too. Each model takes different levels:

ModelLevelsDefault
Claude Sonnet 5.5, Sonnet 5, Opus 5, Fable 5.1low to maximumhigh
Claude Opus 5.5low to maximummedium
Claude Haiku 5.5low to maximummedium
Claude Haiku 4.5the model takes no effort setting—
GPT-6 Luna, GPT-6 Sol, the GPT-5.6 seriesnone, low to maximummedium
GPT-6 Astralow to maximummedium
a model on your own serveranyset by the server

Before, the assistant had one effort for all tasks. It was carried over to Drafting; Triage and Learning run at the model's default level.

What it costs

Prices are in US dollars, as the model provider charges them; draften does not convert them. Roughly (a draft is 40–120 thousand input tokens, half of them from the cache, and 1–2 thousand output tokens):

WhatPer itemTypical month
triage of new mail (Haiku 5.5)a fraction of a cent per checkunder 1 USD
a draft (Sonnet 5.5 or Sonnet 5)0.05–0.15 USD5–20 USD at 3–5 drafts a day
a draft (Opus 5.5)0.10–0.29 USD10–40 USD
a draft (Opus 5)0.14–0.38 USD15–60 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

Daily cap

In Settings → 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.

Plain text version