AI Models
The three tiers (Palos, Luces, Summum) and their AI pools.
The three tiers
🐔 Palos FREE
Fast and direct. For short questions, quick translations, casual chat.
gpt-oss-20b
gemini-3.5-flash-lite
gpt-oss-20b (Cloudflare)
nemotron-3.5-lightning
ling-3.0-flash
💡 Luces FREE
Balanced. The most-used tier: code, study, medium-depth analysis.
gpt-oss-20b
qwen3.6-27b
mistral-small
gemini-2.5-flash
gemini-3.5-flash
gemini-3.7-flash
llama-3.3-70b (Cloudflare)
gpt-oss-20b (Cloudflare)
nemotron-3.5-lightning
ling-3.0-flash
laguna-s-2.1
dots-3-note
gemma-4-26b
⭐ Summum PREMIUM RECOMMENDED
Max power. For deep reasoning, complete projects, architecture.
gpt-oss-120b
qwen3.6-27b
gemini-2.5-flash
gemini-3.5-flash
gemini-3.7-flash
gpt-oss-120b (Cloudflare)
llama-3.3-70b (Cloudflare)
qwen3-30b (Cloudflare)
nemotron-3-super-120b
laguna-s-2.1
dots-3-note
How to choose
| Use case | Recommended tier |
|---|---|
| Casual conversation, jokes, brief translations | 🐔 Palos |
| Quick code, refactors, simple debugging | 💡 Luces |
| Mid-depth analysis, summaries, study help | 💡 Luces |
| Deep reasoning, math, philosophy | ⭐ Summum |
| Complete projects, software architecture | ⭐ Summum |
| Long-context analysis (huge PDFs) | ⭐ Summum (Gemini Flash, 1M+ tokens) |
| Document/screenshot analysis (vision) | 💡 Luces or ⭐ Summum (Qwen 3.6 or Gemini) |
Multimodal models (vision)
Some AIs in the pool understand images. If you attach an image to your message, the brain prioritizes one of these:
- Qwen 3.6 27B — vision + text, 131K context, with tool calling.
- Gemini 2.5 Flash — vision + text, 1M+ tokens of context.
- Gemini 3.7 Flash — vision + text, 1M+ context, Google's most capable.
Tip: You don't usually need to choose the AI manually. The brain does it. The decision you make is the tier (Palos, Luces, Summum), and the brain picks within that tier.
