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
| Model | Status | Best 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.
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.
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: