Max Mode in chat
Toggle MASS-RAG on for a single conversation.
Max Mode is configured in two places. The bot-level toggle in Source settings decides whether the bot can use Max Mode. The chat-level toggle in the conversation input decides whether this conversation uses it right now.
Prerequisites#
- Your plan must be Pro or Ultra. Free users see "Max Mode requires Pro or Ultra plan."
- The bot must have Max Mode enabled in its Source settings. Otherwise the chat toggle shows "Max Mode is not enabled for this bot."
Toggling Max Mode#
In the chat input bar there is a small Max Mode toggle. Switch it on; the next message you send will use the MASS-RAG pipeline.
The toggle is per-conversation. You can keep one conversation in Max Mode and another in Standard for the same bot.
What you'll notice#
- Latency is 2–3× higher. Responses start arriving later, then stream as usual.
- Quality on complex queries is notably better — especially questions spanning multiple sections or asking for inference.
- Credits drain faster — ~5–7× per message vs standard. Watch your daily quota.
When to leave it off#
For short factual questions ("what's the deadline for X?", "what's our return policy?"), Standard RAG is faster, cheaper, and just as accurate. Save Max Mode for the harder questions.
→ Background: Max Mode (MASS-RAG)