Built-in tools
Some models on the network can do more than write text. Depending on the model and the operator serving it, a model can search the web, read a page, and generate or edit images in the middle of a reply. These are built-in tools — and they run on the operator's node you routed to, not in your browser.
What the tools can do
| Tool | What it does |
|---|---|
| Web search | Looks up a query on the web and feeds the results back to the model, which cites them in its answer. |
| Web read | Fetches a specific page and converts it to clean text the model can quote from. |
| Image generation | Creates an image from a text description, inline in the reply. |
| Image editing | Modifies an image — yours or one it just made — from your instructions. |
The model decides when to reach for a tool while it's answering; you don't call them directly. A single reply can use several in a row.
Where they run
When a model searches or reads the web, the operator's node makes that request — the outbound connection comes from the operator, not your device. This is the same trust boundary as inference itself: the operator you chose already reads your prompt to answer it (see Privacy & security). What the operator never learns is who you are — your request still arrives through a relay with no identity attached.
Seeing tools at work
When a model uses a tool mid-reply, each call shows up as a compact labeled line saying
what it's doing — Searching for "algorand consensus", Reading algorand.co — with the
sites a search found listed underneath as clickable chips. A run of calls collapses into
a one-line summary you can expand. Sources also appear as numbered citations at the end
of the message, once the model starts writing its answer.
See Chatting → Tool activity.
Images appear inline in the reply. Click one to open it full-screen, download or copy it, or hand it back to the model for edits — see Chatting → Generating and editing images. The Images setting caps how many images one request may produce (Settings), and each image has a per-image cost (Pricing).
Not every model has them
Tools are a per-model, per-operator capability, so the model picker tells you what's available before you send:
- Tools — the model can use web search and web read.
- Image tools — the model can generate or edit images inside a text reply.
- Generation / Edit — the model is a dedicated image model.
See Models & operators for the badges, and The operator network for how operators advertise what they serve. Auto mode routes image requests to a model that can handle them.
Web image search isn't offered on the network today. Web search, web read, and image generation and editing are the built-in tools currently available.