Claude Cowork is Anthropic's agent for knowledge work — the same agentic engine as Claude Code, but built for non-technical tasks inside the Claude desktop app, with no terminal required. Give it a goal and it works across your local files, folders, and applications, planning and carrying out the task while you steer, and it's aimed at research, analysis, operations, legal, and finance teams. On Opper it runs on any of 700+ models, not just Claude: point it at Opper's Anthropic-compatible gateway and keep inference in the EU or US on one key.
Claude CoworkoninClaude Desktop only accepts Claude model ids, so this pairing does not run in Cowork yet. Run it in Claude Code instead →
GPT-6 Luna Decisions 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 | Cache read |
|---|---|---|---|---|---|---|
| US | No | $0.10 | $0 | Input price |
OpenAI Decisions model: typed predicate, choice and score answers with probabilities and confidence. Text and inline base64 image input. Use POST /v3/compat/decisions (OpenAI Decisions format; a bare gpt-6-luna resolves here) or POST /v3/compat/v1/systemone with model openai/gpt-6-luna-decisions (System One format, text only).
Step-by-step setup for running Claude Cowork on each of these models through Opper.
An open-source personal agent for everyday tasks. Run it on any model on Opper.
opper launch openclaw
Nous Research's open agent. Run it on any model on Opper.
opper launch hermes
The AI copilot for Obsidian notes. Pick Opper from its provider list and chat with your vault on any of 700+ models.
Opper built in