Claude Code is Anthropic's agentic coding tool for the terminal. It reads your whole repository, plans and applies changes across files, runs commands and tests, and iterates on failures from natural-language prompts — all without leaving the shell, on macOS, Linux, and Windows. On Opper it runs on any of 700+ models, not just Claude: pin one with a single --model flag, switch mid-task without losing context, and choose EU or US hosting on one key.
Claude CodeoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Grok 4.20 Reasoning 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 |
|---|---|---|---|---|---|
| xAI | EU | Enterprise | No | $2.00 | $6.00 |
| xAI | US | Enterprise | No | $2.00 | $6.00 |
| Google Cloud | Multi | Enterprise | No | $2.00 | $6.00 |
Grok 4.20 Reasoning by xAI generates visible chain-of-thought across a 2M context window with real-time data and tool use.
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
An open-source, model-agnostic coding agent for the terminal, wired to Opper's catalogue.
opper launch opencode