# Which model should I write with? > How Inkwell's three model tiers map to real writing work, what each pass draws against your plan, and why the picker names the exact model serving you. The Inkwell Team · Jul 21, 2026 AI, Product, Models Jump to a section on the website - [The ladder, in writing terms](https://www.inkwell.software/blog/which-model-should-i-write-with#section-the-ladder-in-writing-terms) - [The cost intuition](https://www.inkwell.software/blog/which-model-should-i-write-with#section-the-cost-intuition) - [What Free and Pro unlock](https://www.inkwell.software/blog/which-model-should-i-write-with#section-what-free-and-pro-unlock) - [The picker names names](https://www.inkwell.software/blog/which-model-should-i-write-with#section-the-picker-names-names) Open the model menu in most AI tools and you get a list of codenames: version numbers and suffixes that mean a great deal to the companies shipping them and very little to anyone mid-scene. Inkwell's picker asks a more useful question: how much model does this pass need? Every account gets a three-tier ladder — fast, balanced, frontier — and each tier resolves to a specific, named model on whichever provider serves you. _\[Visual: model-tiers — view the full article at inkwell.software]_ ## The ladder, in writing terms The fast tier powers everything that has to feel instant. Suggestions while you type always run here, whatever you have picked, because latency matters more than depth when you are mid-sentence. It is also the right choice for quick mechanical passes where you want speed and volume over subtlety: a formatting sweep, a first look at a scene you just drafted. The balanced tier is the everyday workhorse. A dialogue pass on a scene, a punch-up on an act, the skill runs that make up most of a working session. On Pro, this is the default; if you never open the picker, this is what serves you. The frontier tier is the most capable model on the ladder, and the one to reach for when a pass has to hold the most in its head at once. Structural revision, a full-draft pass where the note on page 9 has to connect to the payoff on page 94, the kind of long-horizon work where you would rather wait a few extra seconds and get the deeper read. None of this is about one tier being smart and another being dumb. It is about matching capability to stakes, the same way you would not send a table-read draft to a proofreader or a typo sweep to your most expensive script consultant. > **A rule of thumb** > > Draft on fast, work on balanced, and save frontier for the passes where depth is the whole point. A typo sweep does not need the frontier tier. A page-one rewrite of your midpoint does not want the fast one. ## The cost intuition Plans with hosted passes carry a monthly allowance. Fast keeps quick passes economical; balanced and frontier spend more of that allowance for a deeper read. Use the comparison in the picker to see the current step up before you choose a tier. Treat that hint as a comparison, rather than a fixed price for a pass. The amount of text you send, the length of the reply, and any cached input or long-prompt pricing affect the draw. Check your usage after the pass to see what it used. The practical version: frontier spends your allowance faster than fast. Most writers step up deliberately for the work that needs a deeper read. ## What Free and Pro unlock The fast tier is on every plan, including Free. Balanced and frontier unlock on Pro. Defaults follow the same shape: a Pro account that never touches the picker runs balanced, and a Free account runs fast. The clamp also works when you drop a plan. If you picked frontier on Pro and your subscription lapses, your passes fall back to your plan's default rather than erroring out or quietly serving a tier your plan no longer includes. And in the picker, tiers above your plan are grayed out rather than hidden, so you can always see what an upgrade buys before you make it. ## The picker names names One more deliberate choice: the picker shows the exact model each tier currently resolves to. Not "fast-v2," not a marketing gloss — the concrete model name, per provider, as the picker at the top of this post shows. Your pick covers every AI surface except typing suggestions: skill passes, inline edits, and chat all resolve the same selection identically, so the model shown selected is exactly the model that runs. Model lineups change; providers retire models and ship new ones. When that happens, the name in the picker changes with it, because the picker reads the same model registry the product routes through rather than hand-kept copy. You should never have to wonder which model rewrote your scene. It says so, right where you chose it. --- Canonical page: