Gemini URL context

by GoogleWeb fetch

URL context is Google's Gemini tool for reading the pages you link in a prompt. Gemini takes up to 20 URLs per request and 34MB per URL, reads web pages, PDFs and images, checks Google's index cache before fetching live, and pairs with Google Search grounding to find pages first. Paywalled pages, YouTube and Google Workspace files are out of reach. On Opper it works on the Gemini generateContent endpoint, passed through as Google defines it.

UseGemini URL contextwithin

Add Gemini URL context 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.

Get your API key

Key info

Tool

urlContext

Endpoint

generateContent

In your code

1curl "https://api.opper.ai/v3/compat/v1beta/models/gemini/gemini-4-argon:generateContent" \
2  -H "Authorization: Bearer $OPPER_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{"contents": [{"role": "user", "parts": [{"text": "Summarise https://opper.ai/pricing"}]}],
5       "tools": [{"urlContext": {}}]}'

Use Gemini URL context with these models

Step-by-step setup for Gemini URL context on each of these models through Opper.

Gemini 4 Argon Gemini 3.8 Flash Gemini 3.7 Flash Gemini 3.6 Flash Gemini 3.5 Flash-Lite Gemini 3.5 Flash Gemini 3.1 Pro Preview Gemini 2.5 Pro See all 700+ models

More tools on Opper

Jina Reader

Turn any URL into clean markdown a model can read. Opper's web fetch, running in the EU.

Read/v3/tools/web/fetch

Claude web fetch

Claude fetches and reads pages itself on the Messages endpoint, on Anthropic's own route.

Readweb_fetch

Jina search

Opper's default search engine for models without their own. Search processing stays in the EU.

Search"engine": "jina"