Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Help Center
🔍

Web search

Learn more about this feature

Web search every model can use.Real-time info, cited sources, every model: no per-provider tax.

Found this helpful? Share it:

The assistant can search the web during a conversation to find current, up-to-date information, and it shows you the sources so you can check everything 🔍

Web search Free and upworks on every signed-in account, the free tier included. It is on by default, so you can just start asking.

How it works

When Search is on, the assistant looks up real-time information while it answers: recent events, live data, pricing, documentation, or anything that changes over time. It reads several sources, pulls the information together, and gives you a clear answer alongside the pages it drew from.

Read a specific page

Beyond searching, the assistant can fetch a page you name and read it directly. Paste a URL and ask about it, for example "Summarize this release note" with the link, and it pulls the page in rather than guessing from search results.

Sources

Answers that use the web come with source cards linking to the original pages. Open a card to read more or verify a claim for yourself.

Want the sources spelled out inline? Just ask. Try "What's the latest on X? Include your sources."

When the assistant searches

The assistant decides on its own when the web would improve an answer. It typically searches for:

  • Current events and recent news

  • Live data like stock prices, weather, or sports scores

  • Product information, pricing, or documentation

  • Facts it is not confident about

You can also nudge it directly: "Search the web for..." makes sure it looks things up.

Turn it on or off

Web search is the Search row in the composer tools dropdown (the sliders icon next to the message box). It is on by default. Turn it off for conversations where you want answers from training data and your attached context alone. See Chat settings and toggles.

Turning search off can make answers faster for questions that do not need current information.

Related articles

⚙️

Chat settings and toggles

Customize each conversation from the composer: tool toggles, autonomy, compaction, and a spend limit.

🧠

Choosing models

Browse 200+ AI models, read their cost bands, set the speed dial, and pick the right model for each conversation.

Up next

Running code in chat

Let AI write and run code on a cloud computer, then hand you back the output and any files it produced.

Was this helpful?