AI Models

The three tiers (Palos, Luces, Summum) and their AI pools.

The brain selector

Each tier has a pool of AIs and a brain (an orchestrator AI) that, for every user message, picks the best one from the pool depending on the type of task. If the main brain fails (out of credits, downtime), the cascade falls to a secondary brain, then a tertiary, then a built-in heuristic. The chat never breaks.

The tiers, and Pollo Utility

🐔 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 FREE

Max power. For deep reasoning, complete projects, architecture. Free for everyone: what balances it is that it spends more credits per answer.
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

🐔 Pollo Utility BETA

Our own model. It does not pick between third-party AIs: it is ours, with its own personality and rules. It is the only one that opens a Linux console in your browser to build files and hand them to you, and the only one with agents.
Instead of a pool it has three modes, and you pick them: Fast (short), Reasoning (developed, also opens the pages) and Complex (reasons point by point and can launch agents). How each one works →

How to choose

Use caseRecommended 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)
Have it build you a file, a page or a program🐔 Pollo Utility (Complex)
A multi-step calculation, without it making the number up🐔 Pollo Utility

Multimodal models (vision)

Some AIs in the pool understand images. If you attach an image to your message, the brain prioritizes one of these:

Tip: Inside a tier you do not need to pick the AI: the brain does it. What you choose is between the three tiers and Pollo Utility. With a tier the brain decides for you; with Pollo Utility you decide the mode, because each one does different things.