Parameters
Supported file types
Use cases
- Extract readable text from a web page
- Download and parse remote documents
- Inspect API response bodies
DeepSeek Fetch backend (opt-in)
By defaultweb_fetch retrieves pages directly. Set tools.web_fetch.provider
to "deepseek" to fetch through DeepSeek’s official Fetch API
instead, which returns the page as Markdown — handy for pages the direct
backend cannot render (e.g. JavaScript-heavy sites).
deepseek_api_key model credential (or the
DEEPSEEK_API_KEY environment variable). Calls are billed per
successful request ($0.75 per 1,000), so the backend stays opt-in; "direct"
(the default) is free. The SSRF guard still applies: private, loopback, and
cloud-metadata URLs are rejected before any request is issued. Document
URLs (PDF, Word, etc.) are always downloaded and parsed locally.
Olostep backend (opt-in)
Settools.web_fetch.provider to "olostep" to fetch through
Olostep’s Scrape API instead.
Olostep renders the page in a browser and returns it as Markdown, so it also
works on JavaScript-heavy sites.
tools.web_search.olostep_api_key (or the OLOSTEP_API_KEY environment
variable); create one in the Olostep dashboard.
Each scrape uses Olostep credits, so the backend stays opt-in. The SSRF guard
still applies, and document URLs (PDF, Word, etc.) are still downloaded and
parsed locally.
The default
direct backend only retrieves static HTML. For pages that require JavaScript rendering (such as SPAs), switch to the DeepSeek or Olostep backend above, or use the browser tool.