Web Foundation

Find the source. Then read what it actually says.

Search discovers relevant pages. Fetch and OCR bring the selected page, document or scan into your workflow as readable text.

01 / Discover

Where should I look?

A focused query. Relevant sources.

02 / Read

What does it say?

The selected source. Its useful text.

Already have the source? Go straight to Fetch or OCR.

Fetch / OCR

The link is a starting point. The text is what you can use.

Read an accessible URL or a supported file. OCR extracts writing inside scans and images; the source still deserves review.

Fictional store · Returns
Home / Help / Returns

Changed your mind?

Request a return within thirty days of delivery. Include your order number.

Readable excerpt

The policy, without the page furniture.

Request a return within thirty days of delivery. Include your order number.
Fictional equipment guide

Care & maintenance

Inspect the filter every month. Replace it when damaged.

Readable excerpt

Bring the useful instruction forward.

Inspect the filter every month. Replace it when damaged.
Illustrated scan · Fictional delivery note

Warehouse receipt

One carton requires inspection.

RECEIVED
Illustrative OCR excerpt

Readable does not mean infallible.

One carton requires inspection.

Verify names, dates and numbers against the scan. Layout and image quality affect extraction.

Fictional source previews and prepared excerpts. No live upload, fetch or OCR. Extraction provides text, not a generated answer or an indexed knowledge base.

Choose your entry point

Your backend or your agent can lead.

The capabilities connect, but their input contracts are not interchangeable.

Direct APIs

Search from your backend. Fetch accepts URLs or inline base64 data URIs in contents, up to 10 MB per item, with per-item results and errors.

API reference

Web Utilities MCP

Give an MCP client web_search and fetch_url. Fetch accepts one to five public URLs; use the API for inline files.

MCP integration

Gateway tools

Enable WebSearch and OpenUrl during inference. Multi-step research with AdvancedWebUsage is a separate capability with different billing.

Built-in tools

Start with a source you want to use.

Search when you need to find it. Fetch directly when you already have it. Treat retrieved content as untrusted material, not instructions for your agent.

Different steps. Different billing.

Search is billed per search. Extraction uses processingUnits with plan-based daily allowances. Optional schema-guided JSON uses separately billed jsonProcessingUnits, outside that allowance. Model analysis costs extra. Fetch API requires a positive balance.

Fetch reads text; Media Descriptions interprets media. Neither bypasses restricted access or guarantees perfect output.

Current billing and limits