n8n is the fair-code workflow automation platform that pairs a visual builder with code when you need it, and its AI Agent nodes put LLM steps inside any workflow. Opper ships as a dedicated n8n node: install @opperai/n8n-nodes-opper, add your Opper API credential, and the Opper Chat Model node drives your agents with a live dropdown of 700+ models. One key, a choice of EU or US inference, and per-workflow model swaps without rewiring credentials.
n8noninSettings → Community Nodes → Install @opperai/n8n-nodes-opper, then add the Opper API credential and pick the Opper Chat Model in your AI Agent node. Then pick GPT OSS 20B.
GPT OSS 20B 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 |
|---|---|---|---|---|---|
| AWS Bedrock | EU | No | $0.07 | $0.30 | |
| Geodd | EU/EEA | No | $0.03 | $0.14 | |
| Greenference | EU | No | $0.0090 | $0.04 | |
| Regolo | EU | No | $0.11 | $0.48 | |
| DigitalOcean | US | No | $0.05 | $0.45 | |
| Geodd | US | No | $0.03 | $0.14 | |
| Groq | US | No | $0.07 | $0.30 | |
| Novita | US | No | $0.04 | $0.15 | |
| Fireworks | Multi | No | $0.07 | $0.30 |
GPT-OSS 20B by OpenAI: open-weight Apache 2.0 model, 21B params (3.6B active), near o3-mini, for efficient and on-device reasoning.
Describe a workflow in plain English and Punku builds, tests, and runs the agent for you, with no code involved.
built on Opper
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claudeAnthropic's desktop agent for knowledge work. Run it on any model on Opper, not just Claude.
Anthropic-compatible