ChatHaiku / Support Open chat Status
Getting started

Choosing a model

ChatHaiku currently offers two models. Epos 3 is the current flagship. Epos 2.1, the model it replaces, is still available if you prefer how it answers.

The models

ModelStatusBest for
Epos 3 Current flagship The default choice. Everyday questions, writing and fixing code, planning, and logic. Trained to look things up on the web and in documents.
Epos 2.1 Previous flagship · 1.5B · 32K tokens The model Epos 3 replaces. Choose it if you preferred how it answered.

Which should I use?

Use Epos 3 unless you have a reason not to. It is better than Epos 2.1 across the board, and it is the model to start with.

Switching models

On desktop, the model picker sits at the top centre of the screen. Click it and choose. On mobile the same picker is reached from the header menu.

Model picker
Model
Epos 3Rootcomputer's production model family ▾
Epos 3Current flagship
Epos 2.11.5B · Previous flagship
The Epos models collapse into one row. Click the chevron to see the variants; the row itself always reads as whichever one is selected.

The Epos models are grouped, because they are variants of one family rather than unrelated products. Clicking the row selects the current variant; the chevron expands the list. Whichever variant you pick is remembered, so the collapsed row keeps reading as the model you actually chose.

Switching models keeps your current conversation. The new model reads the history that is already there and continues from it. This works, but the reply may shift in tone or quality mid-conversation, and if you switch to a model with a shorter window, the older turns can fall out of range.

What the models can do

Both models can look things up, and both support Extended effort. Document retrieval runs on its own when a question matches the knowledge base. Web search runs only when you arm the button beside the composer. Messages are limited to 2,048 words each. See Retrieval and web search.

Linking to a model

The active model is reflected in the address bar, so a URL can open the chat with a particular model already selected:

  • /chat?model=epos3 — Epos 3
  • /chat?model=epos2 — Epos 2.1

Longer forms such as ?model=epos_2 also work. An unrecognised name is ignored rather than treated as an error, and you get your last-used model instead.

Context windows

A model's context window is how much of the conversation it can hold at once, measured in tokens — roughly three-quarters of a word each. Epos models hold about 32,000 tokens.

As a conversation approaches the limit, ChatHaiku warns you before the model starts silently forgetting the beginning. When you see that warning, start a new chat — or branch from an earlier message to keep the part that matters.

Long conversations degrade quietly

When history exceeds the window, the oldest turns are dropped. The model does not announce this; it simply stops referring to things you told it earlier. If a model seems to have forgotten something, conversation length is the first thing to check.

When a model is offline

Models run on Rootcomputer's own hardware and go offline for training, maintenance, and the occasional power cut. When the active model is unreachable you will see a message naming it:

Unavailable notice
Epos 3 is not available right now — please try again later.
The other model is often still up. Switch in the picker, or check the status page.