GitHub Copilot CLI brings Copilot's coding agent to the terminal: it reads your repository, edits files, runs commands, and completes tasks from natural-language prompts. It supports custom model providers through plain environment variables, and with a custom provider configured it runs without a Copilot plan or even a GitHub login. Point it at Opper's OpenAI-compatible gateway and it works with any of 700+ models, with fallbacks and a choice of region on one key.
GitHub Copilot CLIoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Nemotron-Content-Safety-3.5 runs on the routes below. Route only to EU providers when your data has to stay in Europe.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| DeepInfra | US | No | $0.20 | $0.20 |
Nemotron Content Safety 3.5 is NVIDIA's 4B open-weight moderation model that classifies prompts, images and responses as safe or unsafe against a built-in taxonomy or a custom policy.
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claude
OpenAI's open-source coding CLI. Run it on any model on Opper.
opper launch codex
DeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.
OpenAI-compatible