The short answer
Web search is a toggle in the composer. Switch it on and the model you selected answers from current sources instead of only from its training data. It costs no credits, and it works with every model in the catalogue.
That last part is the useful bit. Most models have no retrieval of their own, so a question about this month is normally answered from a training set that ended months ago. The toggle puts a search layer in front of whichever model you picked, which means you can ask Claude, or a Llama model, or a small fast model, a question about today and get a sourced answer.
When it changes the answer
Three categories where the difference between search on and search off is not subtle.
Anything with a date in it. Prices, model releases, product launches, company news, version numbers. Without search, a model answers confidently from whatever was true when it was trained, and gives you no signal that the information is stale. This is the single most common way AI answers go quietly wrong.
Anything obscure or specific. A small company, a niche tool, a local regulation, a particular error message. Training data covers these thinly or not at all, and thin coverage is exactly the condition under which models invent plausible detail.
Anything you intend to act on. Not because search makes the model smarter, but because it produces sources you can open. A claim with a link you can check is a different object from a claim without one, even when both turn out to be correct.
When to leave it off
Search is not free of cost to answer quality, which is why it is a toggle rather than a default.
For reasoning, writing and analysis of something you supplied, search adds nothing and can actively distract. If you have uploaded a document and want the model to reason about that document, pulling in web results introduces material that is not yours and was not asked about. Same for creative writing, code review of your own code, and working through a problem step by step.
The rough rule: switch it on when the answer depends on facts about the world, switch it off when the answer depends on thinking about something already in the conversation.
Reading the sources properly
A sourced answer is more checkable, not automatically more correct. Two failure modes survive retrieval and are worth watching for.
The first is a source that exists but does not support the claim. The model retrieved a page, and the page is real, but the specific number or statement attributed to it is not in it. Opening one or two cited links on any answer you plan to rely on catches this quickly.
The second is a source that is itself wrong or out of date. Search does not evaluate credibility, so a stale blog post ranks like an authoritative one. For prices and specifications especially, a vendor page beats a roundup article, and both beat a forum comment.
If a claim matters, the fastest verification is to ask a second model the same question with search on, in the same conversation. Where two independent retrievals agree on a specific number and a source, confidence is reasonable. Where they diverge, that is your finding.
- The toggle is in the composer, next to attach
- Web search costs no credits
- It works with every model, including ones with no native retrieval
- Switch it on for anything with a date, anything obscure, anything you will act on
- Switch it off for reasoning about a document you uploaded
- Open at least one cited link on any answer that matters
- Cross-check important claims by asking a second model with search on
Frequently asked questions
Can Claude search the web in Whizi?
Yes. The web search toggle applies to whichever model you selected, so Claude Sonnet 5 or Claude Opus 5 will answer from current sources when it is switched on. This is one of the practical advantages of a multi-model workspace: you are not limited to whichever models happen to ship with their own retrieval.
Does web search use extra credits?
No. A message costs the same whether search is on or off, because the credit rate is set by the model alone. The only thing that changes the cost of a message is which model answers it.
Why did the model give me outdated information?
Almost always because search was off, so the answer came from training data with a cutoff months in the past. Models rarely flag this themselves, which is why a confident wrong date or price is such a common failure. Turn the toggle on and ask again; if the answer changes, the first one was stale.
Should I leave web search on all the time?
No. It helps on questions about the world and hurts on questions about material already in the conversation, where retrieved pages pull the model away from the document you actually uploaded. Treat it as a per-question decision rather than a setting, which is why it lives in the composer rather than in preferences.