Gemini 3.6 Flash has its own web search on 3 of its 5 routes, 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/gemini/gemini-3.6-flash: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 3.6 Flash runs Google Search grounding on the routes below. Some routes also sell flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | ||
|---|---|---|---|---|---|---|---|---|
| EU | No | $0.82 | $4.13 | $0.08$0.91 write | Not offered on this route | |||
| US | No | $0.75 | $3.75 | $0.07$0.79 write | ||||
| Multi | No | $0.75 | $3.75 | $0.07$0.83 write |
Gemini 3.6 Flash, Google's token-efficient multimodal Flash model, cuts output tokens by 17% while improving coding and agentic planning.
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"