What is the CoffeeScribe Model?

How the curated default model works, why Free and Pro are locked to it, and what changes when you upgrade to Creator

The short version

The CoffeeScribe Model is the curated AI model that powers generation on Coffeescribe. Free and Pro are locked to it; Creator unlocks a model picker — but the CoffeeScribe Model still shows up at the top of that picker, pre-selected and recommended.

Think of it as our pick of the best balance of quality and cost, refreshed as the AI landscape changes.

Why a single curated default?

We tried letting every paid user pick from a dozen models. What we learned: model choice is a power-user decision that creates support load without adding much value for most readers. Picking a default model — and standing behind it — makes the experience predictable and the cost stable.

So Free and Pro share one curated default. You don't need to read benchmarks, compare context windows, or decide whether to enable web search. The model is chosen for you, and we maintain it.

This is the lock side of Coffeescribe's lock-vs-unlock framing. Creator is the unlock side — see below.

Will the underlying model change?

Yes. New AI models ship every few weeks, and the right balance of quality and cost shifts with them. We update the CoffeeScribe Model from time to time as better options become available — or as a current pick gets retired by its provider.

The brand label — "CoffeeScribe Model" — stays the same so you don't need to track which specific model is behind it. We treat that name as the product, not the engineering detail.

What about the Pro tier?

Pro is locked to the CoffeeScribe Model — same model that Free uses, same predictable behaviour. Pro's Pro-ness comes from elsewhere:

  • Generous monthly allowance vs. Free's one-off welcome credit
  • Carry-over — unused tokens roll forward up to one extra month
  • Audiobook generation
  • Private scribes
  • Verify Validity, AI-powered dictionary, AI Chat in Notebooks
  • Unlimited PDF exports

If you bought Pro hoping to pick your own model, that's now a Creator feature — and Creator's monthly allowance is bigger too. See Plans & Pricing for the upgrade path.

What unlocks at Creator?

Creator gets the model picker. The structure is deliberate:

  1. CoffeeScribe Model (recommended) — pinned at the top of the picker, pre-selected as the default. If you don't change anything, you generate with the same curated model Pro uses.
  2. Recommended models — a curated set of around a dozen alternatives we've personally verified for writing quality and citation behaviour. Each one shows Writing / Research / Cost dot ratings (1–5).
  3. All other models (advanced — at your own risk) — a collapsed disclosure that opens up the full OpenRouter catalogue (350+ models). Smaller models — for example, those in the 8B-parameter range — may produce noticeably lower-quality output, and some models may fail to generate at all. We don't review or guarantee them; the disclosure carries an explicit at-your-own-risk warning.

The picker is alternatives, not a switch. The CoffeeScribe Model stays the safe default; the other tiers are there for users who know what they're doing and want something specific.

What if I run out of tokens?

It depends on your tier:

  • Free — When your welcome credit hits zero, generation stops and you're prompted to upgrade. Existing scribes, highlights, and notes stay accessible.
  • Pro — If you hit zero before your monthly renewal, Coffeescribe gives you extra tokens to finish your work. This happens once per billing cycle. After the grant is used, further generation is paused until you upgrade to Creator (the increase covers the rest of the cycle) or your renewal arrives.
  • Creator — Coffeescribe also gives you a one-time goodwill grant per billing cycle to finish your current work the first time you empty out. Once that's spent, buy a token top-up any time — top-ups are added to your balance immediately, never expire, and can push your balance above the monthly carry-over cap because they're purchased separately.

What does the token meter show?

The meter in your navbar uses a simple four-state visual on every tier — Plenty / Getting low / Very low / Empty. We don't show raw token counts in the navbar or library because the unit is opaque (1 token ≈ 0.75 of a word) and watching the digit creates anxiety without informing decisions. The meter tells you what you actually need to know: are you fine, or are you running out?

The exact token quantity for a top-up purchase is shown once at the moment of purchase (Creator only — top-ups are not available to Free or Pro), so you know what you're paying for. After that, the meter goes back to vague.

See also