Mistral Small 3, latency-optimized 24B instruction-tuned model with 32k context and over 81% MMLU accuracy.
Available on
Privacy
- ZDR
- Training
- No
- Region
- US
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.
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Mistral Small 3 24B Instruct runs on the routes below. Route only to EU providers when your data has to stay in Europe. Its route also sells flex processing: the same model at another price, picked per request with service_tier. How service tiers work.
| Provider | Region | Zero data retention | Training | Input | Output | Cache read | |
|---|---|---|---|---|---|---|---|
| US | No | $0.05 | $0.08 | Input price |
Mistral Small 3, latency-optimized 24B instruction-tuned model with 32k context and over 81% MMLU accuracy.
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-compatibleAn open-source personal agent for everyday tasks. Run it on any model on Opper.
opper launch openclawThe AI copilot for Obsidian notes. Pick Opper from its provider list and chat with your vault on any of 700+ models.
Opper built in