Guides
Choose Your Model
DumGum offers two model tiers: Smart and Pro. The difference is output quality, cost, and features.
Smart vs Pro
| Smart | Pro | |
|---|---|---|
| Quality | Solid, reliable output | Highest quality output |
| Best for | High-volume standard conversations | Premium or complex conversation flows |
| Features | SoulEngine, Core Guardian, Vision Link, Smart Share, Fictional Disclosure, Platform Information, User Suggestions | Everything in Smart, plus Long-term Memory |
| Cost | €0.025 per reply | €0.035 per reply |
New projects use chat-2-smart by default.
Both tiers give the Persona the same short-term memory: the 30 most recent messages of the conversation. What differs is what survives beyond that window: Pro adds Long-term Memory. See Conversation Memory for what actually occupies those 30 slots.
Current and Legacy Models
The current generation is chat-2.2-smart and chat-2.2-pro. They cost the same as the chat-2 models and support the same features, with the sharing and first-reply behaviour described in Control Sharing and Sexual Intensity and the question control described in Model Versions. Prefer chat-latest-smart or chat-latest-pro if you would rather follow the newest version automatically: today they resolve to 2.2.
chat-2.1-* and chat-2-* remain available and behave exactly as they did when they shipped. That is deliberate: a pinned version never moves underneath you. The flip side is that a setting introduced after your version is ignored there — replyParameters.questionFrequencyRate is read by 2.2 and later only, so if you send it to an earlier model nothing happens. All three generations support Vision and Smart Share features.
The dating-smart-1 and dating-pro-1 models are the legacy generation, still supported, but new projects should use the chat-2.2-* models.
If you are already running on 2.1 or 2.0, moving to 2.2 is worth it only if you use the question control: that is the single thing that changed between them. Staying where you are costs you nothing — a pinned version is supported for as long as you want it, at the same price per reply.