---
title: Humanlike Chat
colorFrom: indigo
colorTo: pink
sdk: static
app_file: index.html
pinned: false
fullWidth: true
short_description: Chat with the hosted Humanlike model.
models:
  - LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-GGUF
  - LessThanThreeAI/Gemma-4-31B-Humanlike-Chat
  - LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-FP8
  - LessThanThreeAI/Gemma-4-31B-Humanlike-Chat-GPTQ-Int4
---

# Humanlike Chat

Static chat client for the hosted OpenAI-compatible endpoint at `https://api.lessthanthreeai.com/v1`.

- Model: `gemma-4-31b-humanlike-chat`
- No API key required
- Optional system prompt for a persona, setting, or relationship, kept in the browser between reloads
- Thinking: off (default), low, medium, or high
- One conversation per page load; refreshing starts a new session
- Requests send only `model`, `messages`, `stream`, `max_tokens`, and `chat_template_kwargs`, so the endpoint defaults match the deployment gate

The service runs on scale-to-zero capacity. The first message after an idle period can take a few minutes while a worker starts, and the request stays connected while that happens. Later messages are fast until the worker shuts down after five idle minutes.