Models & operators
ZeroSignal isn't tied to one AI provider. Models are served by independent operators on an open network — the catalog you see in the model picker is read live from an on-chain registry, and anyone can run an operator and list models on it. For how operators are paid and kept honest, see The operator network.
The model picker
Open the picker from the composer to browse what's available:
- Filter by Text, Image, or your Favorites; search by model name.
- Star models you use often to pin them under Favorites.
- Each model shows capability badges — Vision (reads images), Generation / Edit (makes and modifies images), Image tools, Reasoning, and Tools — plus model tags such as Code, Medical, X-ray, or Uncensored (with an 18+ warning where relevant), drawn from the model's HuggingFace card.
- Each model shows its live rate in dollars per million tokens (input · output), with all fees included — see Pricing.
The Tools, Image tools, and Generation / Edit badges mark models that can use built-in tools like web search and image generation, which run on the operator's node.

Opening a model's details shows its context window, maximum output length, supported reasoning effort levels, and a description.

Multiple operators per model
The same model is often served by more than one operator, each setting its own price. The picker shows the operators behind a model so you can choose a specific one — or just take the default. The app continuously probes operators for reachability and compatibility, so offline or incompatible operators are flagged before you ever send to them.
How operators are named
An operator that has linked an NFD (an Algorand name) is shown by that name — with its avatar, if the NFD has one — instead of a bare wallet address. The name is a link: open it to read the operator's public NFD profile on NFDomains. Operators without an NFD show a shortened form of their payout address, which isn't a link.
The same name and avatar identify an operator everywhere it appears: in a model's details, on the ⓘ beside an answer, and in your starred operators under routing settings.
Auto mode
Don't want to choose? Auto reads your message on your device and routes it to a topical lane — general chat, code, reasoning, or image — then picks an available model and operator for that lane, favoring the cheapest qualifying option (subject to your routing preferences). It doesn't grade prompts by difficulty or send "hard" questions to a "stronger" model — there's no distinct reasoning tier in the catalog today.
The routing runs entirely on your device, so your prompt isn't shared with any routing service.
No censorship
The catalog is open: operators decide what models they serve and under what policies, and you decide what you use. Capability tags in the picker tell you what to expect from each model.