Gemini 3.5 Flash-Lite uses Gemini code execution through Opper on the generateContent endpoint, passed through as Google defines it.
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-3.5-flash-lite:generateContent" \-H "Authorization: Bearer $OPPER_API_KEY" \-H "Content-Type: application/json" \-d '{"contents": [{"role": "user", "parts": [{"text": "Sum the first 50 primes and show your working."}]}],"tools": [{"codeExecution": {}}]}'
Gemini 3.5 Flash-Lite runs Gemini code execution 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 | $0.30 | $2.50 | $0.03 | Not offered on this route | Not offered on this route | ||
| EU | No | $0.33 | $2.75 | $0.03$0.41 write | Not offered on this route | |||
| US | No | $0.30 | $2.50 | $0.03$0.38 write | ||||
| Multi | No | $0.30 | $2.50 | $0.03 | Not offered on this route | Not offered on this route | ||
| Multi | No | $0.30 | $2.50 | $0.03$0.38 write |
Gemini 3.5 Flash Lite is Google's low-latency workhorse for high-volume automation, pairing 1M context with audio, video, and PDF understanding.
Step-by-step setup for Gemini code execution on each of these models through Opper.
GPT models write and run Python in a sandbox, on the Responses endpoint.
code_interpreterClaude runs code in Anthropic's sandbox, on Anthropic's own route.
code_executionClaude drives a desktop through screenshots, clicks and typing in your agent loop.
computer_toolset