Pareto Inference
From its catalog listing
Pareto Inference as a Hermes model provider (`--provider pareto`): GLM 5.3 Flash, DeepSeek V4.1 Flash and MiMo V2.6 Flash over OpenAI-compatible Chat Completions, pay per token, with /reasoning mapped to Pareto's reasoning_effort levels and context windows from models.dev.
Good to know before installing
model provider; registers one provider profile at import and nothing else (no tools, hooks, commands or threads). Hermes sends prompts, tool results and a GET /v1/models catalog request to api.paretoinference.com with PARETO_API_KEY, which Hermes reads; the plugin itself opens no connections, reads or writes no files and adds no telemetry.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs (this one needs
PARETO_API_KEY), then asks whether to turn it on.hermes plugins install pareto - Said no? Turn it on later:
hermes plugins enable pareto - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- AI models & providers
- Maintained by
- pareto-inference (Community)
- Needs
PARETO_API_KEYAPI key- Needs Hermes
- 0.22.6 or newer
- Version
- 1.0.0
- In the catalog
- 2026-11-07
Known issues (from its catalog listing)
- Pareto serves streamed requests only. Add api.paretoinference.com to auxiliary.stream_only_base_urls so auxiliary tasks (titles, compression, vision) stream too.
Using the Hermes desktop app? See where plugins live

Full setup & settings ↗Source code ↗
More in ai models & providers
All ai models & providers plugins
New Hermes Agent updates every day on X. Follow @HermesWatcher