Claude web fetch
Web fetch is Anthropic's server tool that lets Claude fetch and read full web pages and PDFs while it answers. It only fetches URLs that already appear in the conversation, never ones Claude writes itself, respects robots.txt, and can cite the passages it uses. Pages that only render with JavaScript are out of reach. On Opper, Claude gets it on the Messages endpoint, passed through as Anthropic defines it. It runs on Anthropic's own route; Claude served from Bedrock or Vertex doesn't have it.
Add Claude web fetch on Opper
Set up with agents
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Key info
web_fetchIn your code
curl https://api.opper.ai/v3/compat/v1/messages \-H "Authorization: Bearer $OPPER_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "anthropic/claude-haiku-5-5", "max_tokens": 1024,"messages": [{"role": "user", "content": "Summarise https://opper.ai/pricing"}],"tools": [{"type": "web_fetch_20250910", "name": "web_fetch", "max_uses": 3}]}'
Use Claude web fetch with these models
Step-by-step setup for Claude web fetch on each of these models through Opper.
More tools on Opper
Jina Reader
Turn any URL into clean markdown a model can read. Opper's web fetch, running in the EU.
/v3/tools/web/fetchGemini URL context
Gemini reads the URLs in your prompt itself, on generateContent.
urlContextJina search
Opper's default search engine for models without their own. Search processing stays in the EU.
"engine": "jina"