Claude Web Search: How Claude Browses the Web

Claude web search lets Claude pull live results from the internet and ground its answer in them, with inline citations you can click to verify. It runs on the Brave Search index, works on every plan including Free, and fires automatically when a question needs current information — or on demand the moment you ask it to search.

Search behaviour, the settings toggle and plan availability verified 9 August 2026 against Anthropic's enable-and-use-web-search guide.

We research and fact-check with Claude every day, and web search changed how much of that work stays in one window instead of bouncing to a browser. Below: exactly when Claude reaches for the live web versus its training data, how to trigger a search, what it is genuinely good at, how it compares to Connectors and file uploads, and when to trust the answer versus double-check it. We verified this flow hands-on, so where a step is fiddly we have flagged it from experience instead of guesswork.

When does Claude search the live internet?

Claude searches only when a question signals recency, ambiguity, or a fact that moves — prices, release dates, current events. Stable knowledge comes straight from training, so an evergreen-sounding prompt may never trigger a lookup unless you ask for one.

Every Claude model ships with a training cutoff — a date after which it simply hasn't read anything. For stable facts (how bubble sort works, the capital of Peru), Claude answers straight from training, which is instant and costs you nothing extra. Claude web search exists for the other case: questions where the answer moved after the cutoff, or where being wrong is expensive.

So the honest answer to does Claude have web search is yes — but it doesn't search on every message. Claude evaluates whether your query signals recency or ambiguity, and only then sends a query to the web. That design keeps fast questions fast. It also means an evergreen-sounding prompt ("best practices for X") may never trigger a search even when you wanted fresh sources.

The practical takeaway: if a query needs Claude real time information and the phrasing sounds timeless, say so explicitly. Adding "search the web" or "use current sources" removes the guesswork.

How to turn on Claude web search

Click the slider icon in the chat input, find Web search in the dropdown, and switch it on — or enable it once in profile settings so it persists across chats. Team and Enterprise workspaces need an admin to enable it first.

On claude.ai, Claude AI web search is a toggle, not a separate mode. Click the slider icon in the chat input, find Web search in the dropdown, and switch it on; you can also enable it once in your profile settings so it persists across chats. Anthropic's own enable-and-use-web-search guide walks through the same steps and notes that Team and Enterprise workspaces need an admin to turn the feature on first.

Once the toggle is on, you still control each search two ways:

• Let Claude decide. Ask normally and Claude searches when it judges the query needs it.
• Force it. Include a phrase like "search the web," "use web search," or "cite current sources." Claude then runs a search even for a topic it thinks it already knows — the fix for the common "why isn't Claude searching?" complaint.

If searches never run even with the toggle on, the usual culprit is that Claude decided the query was answerable from training. Explicit instructions override that judgment every time.

How the search pipeline actually works

Claude writes formatted queries, sends them to Brave Search, and gets back titles, URLs and text snippets rather than whole pages. It reasons over those snippets to write a cited answer. Web fetch is the separate tool that reads one full page.

Claude does not crawl the open web page by page. When a search is warranted, it writes one or more formatted queries and sends them to its search provider, Brave Search, which maintains an independent index of tens of billions of pages. Brave returns a structured payload — titles, URLs, and text snippets — and Claude synthesizes those into a written answer with inline citations. Anthropic launched this capability for claude.ai in March 2025 and described the mechanics in its announcement; the model reasons over the returned snippets rather than loading each site itself.

That distinction matters for accuracy. Search-grounded answers lean on the snippets Brave surfaces, so they're only as current and complete as those snippets. When you need the full text of one specific page, that's a different tool: web fetch. Paste a URL and, with web search enabled, Claude retrieves that page's full content and reads it end to end — the right move when you want Claude to search the internet for a topic and then dig into a single result in depth.

What live search is genuinely good for

Current facts, cited synthesis across several sources, verification through clickable links, and fresh or niche details too recent for training data. It is weaker on paywalled pages and deep multi-page investigation, where fetching specific URLs works better.

In daily use, Claude web search earns its keep on a specific shape of task:

• Current facts. Prices, release dates, version numbers, "did this ship yet" — anything that changes after a training cutoff.
• Cited research synthesis. Ask a question that spans several sources and Claude pulls them together into one answer with links, which beats reading ten tabs yourself.
• Verification. Because every grounded claim carries a citation, you can click straight through to the source instead of trusting the model blind.
• Fresh, niche, or local details. New library releases, a just-published policy, a small company's current offering — things too recent or too specific to sit in training data.

Where it's weaker: deep multi-page investigation (fetch the key URLs instead), paywalled or login-gated content Brave can't index, and anything where the snippet lacks the nuance of the full article. For an overview of where search sits among Claude's other capabilities, our Claude AI features guide maps the whole surface.

Web search vs Connectors vs uploads

Reach for search when the information is public and current, Connectors when the answer lives in a tool you own such as Drive or GitHub, and file uploads when you already hold the exact document. All three stack in one conversation.

The question we get most is which tool to reach for. All three feed Claude information it didn't have, but they pull from different places.

The rule we use: reach for web search for public, current information; reach for Connectors when the answer lives in a tool you own — covered in our Claude Connectors guide; and upload a file when you already have the exact document, staying inside the file upload limits. They stack, too: search the web for context, then upload your own data to combine both in one answer.

Claude web search availability across plans

Every tier gets it, Free included, but each search and fetch draws down your daily message allowance. Free users feel that hardest — one long article fetch eats a noticeable slice — so leave the toggle off until a query genuinely needs it.

Web search is one of the few agentic-adjacent features Anthropic ships to everyone. It rolled out to all Claude users worldwide, Free tier included — but usage isn't unlimited, because each search and each fetch consumes part of your daily message allowance. The same capability is exposed to developers as a server tool in the Claude web search API docs.

For Free users especially, the cost math is real: fetching a long article can eat a meaningful slice of your daily capacity, so Anthropic's own advice is to keep search off until a query actually needs it. If you're weighing which tier fits your usage, the plan-by-plan breakdown lives in our Claude AI features overview.

When to trust the answer — and when to double-check

Grounded answers beat memory-only ones, but Claude reasons over snippets that can be stale, thin or quoted out of context. Trust the synthesis for casual questions; click through to the primary source for any number you plan to publish or act on.

Grounded-with-citations is far more trustworthy than a model answering from memory, but it isn't infallible. Claude reasons over snippets, and a snippet can be outdated, quoted out of context, or drawn from a weak source. Our own habit is simple: trust the synthesis, verify anything you'll act on.

The citations are the whole point — they exist so you can check the work, so use them. When accuracy matters, click through to the original. On how Claude's cited-search approach compares with rivals built entirely around live retrieval, see Is Claude better than ChatGPT?; a dedicated search-first tool like Perplexity leans harder into citation-first answers, while Claude balances search against everything else it does.

Claude web search has been stable since its 2025 rollout, and the toggle-and-cite behavior described here matches the current claude.ai apps.

For example, ask Claude for a stock price or a score from 5 minutes ago: it runs 1 live search, pulls the top 3 results, and answers with 2 linked citations you can verify in under 10 seconds.

Claude pricing at a glance

Free costs nothing, Pro is $20 a month, Max starts at $100 a month, and API access is billed per token. Search is included at every tier — what changes is how much daily allowance you have to spend on it.

For the full breakdown of every plan, see our how much Claude costs guide.