PerchAI
How it works

Models

The models available on each Perch plan, and how Roost chooses between them.

Perch runs on a range of models rather than a single one. Roost picks between them for you on every task, and on Pro you can pin a specific model by hand. This page lists what each plan includes.

This list evolves

The model lineup changes as we add and retire models. The names below are current examples, not a fixed contract. What stays constant is the structure: Starter runs a curated pool, Pro unlocks every model, and BYO runs your own.

Starter

A curated pool of capable hosted models, selected by Roost. There are no manual pins on Starter, and it includes up to $20 of hosted usage each month.

Example models: DeepSeek V4, GLM 5, and Kimi K2.5.

Pro

Every model in the registry, selectable by hand or left to Roost. Pro adds the premium models and includes up to $150 of premium-model usage each month, plus unlimited everyday use under fair use.

Example premium models: GLM 5.2, DeepSeek V4 Pro, Kimi K2.7 Code, Kimi 2.6, MiniMax M2.5, and Nemotron Ultra.

BYO

Run Perch on your own cloud key or a local OpenAI-compatible endpoint. There are no Perch usage limits on your own inference, and hosted Perch models stay off until you add a key.

At a glance

StarterProBYO
Model selectionCurated pool, automaticEvery model, automatic or pinnedYour own model
Premium modelsNoYesYour choice
Manual model pinNoYesn/a
Included usageUp to $20 / monthUp to $150 / month + unlimited everyday useYour own inference
Vision for text-only modelsYesYesYes

For prices and plans, see Pricing. For how the routing works, see Perch Roost.

Models | Perch AI