Gemini 3.8 Flash searches the web through Exa with one tool entry, "engine": "exa". Pinning it replaces Gemini 3.8 Flash's own search, which auto would otherwise use on its maker's endpoint.
Exa searchwithinPaste 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/chat/completions \-H "Authorization: Bearer $OPPER_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "gemini/gemini-3.8-flash","messages": [{"role": "user", "content": "What changed in the news today?"}],"tools": [{"type": "opper:web_search", "engine": "exa"}]}'
Gemini 3.8 Flash runs Exa search 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 | Not offered on this route | Not offered on this route | ||
| 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 | Not offered on this route | Not offered on this route | ||
| Multi | No | $0.75 | $3.75 | $0.07$0.83 write |
Gemini 3.8 Flash is Google's workhorse multimodal model for software engineering and agentic tasks, pairing 1M context with image, audio, video, and PDF input.
Step-by-step setup for Exa search 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"
Linkup's search for AI apps, running in the US, EU, Canada and APAC, on any tool-calling model.
"engine": "linkup"