# Live Web Data

> Live web data for LLM apps, explained plainly: how fresh a page must be, which country to read it from, which format to pass and what each page costs.

How fresh is the web your AI reads? Live data, explained plainly. A Teneo Labs project · Built on Live Web Data API.

## Guides

- [Why LLM apps need live web data, and when they do not](https://livewebdata.com/guides/why-llm-apps-need-live-web-data): Why LLMs need live web data: what goes stale after the knowledge cutoff, what real-time should mean in hours, and when to use a contents or search API.
- [Live vs cached web data: where the cache belongs in LLM apps](https://livewebdata.com/guides/live-vs-cached-web-data): Live vs cached web data for LLM apps: how max age works across APIs, when to cache on your side, timeouts, and how to pass fetch times to the model.
- [Country-specific web content for LLMs: same URL, other page](https://livewebdata.com/guides/web-pages-by-country): Why the same URL returns different content by country, what that does to LLM answers, and how to pick a default country and label localized pages.
- [Web data budget for AI apps: fetch cost plus token cost](https://livewebdata.com/guides/web-data-budget-for-ai-apps): Web data budget for AI apps: a worksheet for both bills, the fetch and the input tokens, plus truncation, failed requests, batching and rate limits.
- [Markdown vs HTML for LLMs: which page format to pass](https://livewebdata.com/guides/markdown-text-or-html-for-llms): Markdown vs HTML for LLM context, plus plain text: what each format keeps, how much of the page to pass, tables, metadata and which URL to cite.

## Posts

- [Tell the model how old the page is: fetch timestamps in context](https://livewebdata.com/blog/fetch-timestamps-in-llm-context): A model cannot see when a page was read. Put the fetch time, URL and country next to the content, in one format, and tell the model how to use them.
- [Final URL or canonical URL: which address an LLM should cite](https://livewebdata.com/blog/final-url-vs-canonical-url): A fetched page has up to three addresses. Which one to pass to the model, which one to key stored copies by, and what redirects reveal about country and age.
- [Last-Modified and ETag: what page headers say about freshness](https://livewebdata.com/blog/last-modified-and-etag-freshness-hints): Last-Modified and ETag tell a cache whether a copy changed, not when the content was written. How reliable each one is, and what to store instead.
- [Token cost of web pages: how many tokens one page really is](https://livewebdata.com/blog/token-cost-of-web-pages): In one 44,684-page sample the median page was 3,201 tokens and the 99th percentile 141,410. How to budget the token bill when page sizes skew that far.

## Built on Live Web Data API

> Live web pages as clean Markdown, text or HTML for AI agents. Send up to 10 URLs per request to POST /v1/contents; failed pages cost nothing.

- API base URL: https://livewebdata.com/api
- Auth: `Authorization: Bearer <api_key>` (keys start with 1337_live_)
- OpenAPI: https://livewebdata.com/openapi.json
- MCP server (Streamable HTTP, same bearer key): https://livewebdata.com/mcp

### Docs

- [Overview](https://livewebdata.com/docs.md): Live Web Data API turns any public URL into clean Markdown, text or HTML — fetched live through our fetch network.
- [API reference](https://livewebdata.com/docs/api-reference.md): Two endpoints. HTTP 200 is returned even when individual pages failed — check statuses[] for the per-URL outcome.
- [Examples](https://livewebdata.com/docs/examples.md): Copy-paste examples in cURL, Python and JavaScript. Replace YOUR_API_KEY with a key from the dashboard.
- [Automate requests](https://livewebdata.com/docs/automation.md): Move from clicking Run in the playground to fetching URL lists from your own code — with rate limits, retries and scheduling handled.
- [SDKs](https://livewebdata.com/docs/sdks.md): Thin, typed clients for JavaScript/TypeScript and Python — built-in retries, typed errors, one-line page fetches.
- [MCP for agents](https://livewebdata.com/docs/mcp.md): Use the Live Web Data API as a tool in Claude, Cursor, VS Code and any other MCP client — with one URL and your existing API key.
- [No-code recipes](https://livewebdata.com/docs/no-code.md): Call the API from n8n, Make or Zapier with each tool's generic HTTP step. Native integrations are on the roadmap.

### Optional

- [Full docs in one file](https://livewebdata.com/llms-full.txt)
- [Postman collection](https://livewebdata.com/live-web-data-api.postman_collection.json)
- [Example scripts (.zip)](https://livewebdata.com/live-web-data-api-examples.zip)