Gemini 2.5 Pro has its own web search, and auto uses it when you call it on the generateContent endpoint. On every other route and endpoint Opper's engine runs the search.
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
curl "https://api.opper.ai/v3/compat/v1beta/models/vertexai/gemini-2.5-pro:generateContent" \-H "Authorization: Bearer $OPPER_API_KEY" \-H "Content-Type: application/json" \-d '{"contents": [{"role": "user", "parts": [{"text": "What changed in the news today?"}]}],"tools": [{"type": "opper:web_search", "engine": "native"}]}'
Gemini 2.5 Pro runs Google Search grounding on the routes below.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|
| EU | No | $1.25 | $10.00 | $0.13$1.63 write | ||
| EU | No | $1.25 | $10.00 | $0.13$1.63 write |
Gemini 2.5 Pro by Google, an advanced reasoning LLM with 1M context and thinking mode, strong at complex coding, math, STEM, and deep document analysis.
Step-by-step setup for Google Search grounding on each of these models through Opper.
Opper's default search engine for models without their own. Search processing stays in the EU.
"engine": "jina"
The Swedish open-source search API, on Europe's own Staan index and hosted in the EU.
"engine": "searchbase"
Exa's search engine built for AI, on any tool-calling model through one tool entry. US-based.
"engine": "exa"