GitHub Copilot is GitHub's AI pair programmer, built into VS Code and the JetBrains IDEs. Its bring-your-own-key support includes a Custom Endpoint provider that speaks both the OpenAI and Anthropic API formats, so chat and agent mode run on the model you choose while inline code completions stay on GitHub's own models. Point it at Opper's compatible gateway and you get 700+ models on one key with a choice of EU or US hosting, and in VS Code it works even without a Copilot plan.
GitHub CopilotoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Gemini 3.1 Flash-Lite runs on the routes below. Route only to EU providers when your data has to stay in Europe. 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 | $0.28 | $1.65 | $0.03 | Not offered on this route | |||
| US | No | $0.25 | $1.50 | Input price | ||||
| Multi | No | $0.25 | $1.50 | $0.03 |
Gemini 3.1 Flash Lite by Google, a cost-effective, low-latency multimodal LLM with 1M context, thinking mode, and tool use for efficient task automation.
Step-by-step setup for running GitHub Copilot on each of these models through Opper.
Point Cursor's OpenAI base URL at Opper to run it on any of 700+ models.
OpenAI-compatible
Cline's OpenAI-Compatible provider points straight at Opper's gateway.
OpenAI-compatible
Add Opper as an OpenAI provider in config.yaml and Continue's chat, edit and autocomplete run on any model.
OpenAI-compatible