Hermes is an open agent from Nous Research, the team behind the Hermes family of open-weight models. It runs as a terminal agent for general assistant and tool-use workflows, designed in the open and built to be steerable and unopinionated rather than locked down. On Opper it runs on a single key across 700+ models with full observability and a choice of region.
HermesoninPaste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Jev 1.13 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 |
|---|---|---|---|---|---|---|
| Multi | —Not established | No | $0.04 | $0 | Input price |
TypeSafe System One model for typed yes/no decisions (noul), classification (choice), and rubric scoring (score), preserving probabilities and confidence. Text or structured text input only. Context limits: 64k total request tokens and 32k tokens for state plus the longest question. Use POST /v3/compat/v1/systemone.
Step-by-step setup for running Hermes on each of these models through Opper.
Anthropic's desktop agent for knowledge work. Run it on any model on Opper, not just Claude.
Anthropic-compatible
An open-source personal agent for everyday tasks. Run it on any model on Opper.
opper launch openclaw
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