# Models and providers: configure the actual inference route

> Understand which model handles conversation and which auxiliary models handle supporting tasks before diagnosing quality or cost.

Canonical: https://hermeswatcher.com/tools/models  
Kind: Provider setup · Development & operations  
Last reviewed: Oct 19, 2026  
Basis: Explained from the official Hermes Agent docs and repository (Nous Research). Steps follow the linked official sources.

## What it is for

Hermes distinguishes the main conversation model from auxiliary models used for tasks such as context compression, vision, and routing. That means changing the visible chat model does not necessarily change every model involved in a workflow. Use the model settings to choose a route suited to the task, then verify it in a fresh session. Keep a record of provider, model identifier, and relevant configuration when comparing results.

## What you need

- An authorized provider account or a suitable local endpoint, with current credentials and usage terms.
- A model that supports the tool use and context needs of the intended workflow.

## Setting it up

1. Inspect the current main and auxiliary assignments through the documented model configuration interface. Choose a supported authentication route and retain the existing configuration before changes.
2. Run a bounded sample with representative tools and output requirements. Compare useful results, response failures, and observed usage before selecting a routine default.

## How to check it works

- Confirm the effective model for the session being tested; existing chats may retain their original model.
- Inspect provider usage and auxiliary settings when estimating the total cost of a recurring task.

## Limits

- Model availability, quotas, pricing, and authentication vary by provider and can change.
- A model being selectable does not establish reliable performance on your task. No provider purchase or runtime benchmark is implied by this resource.

## Related workflows

- [Wake up to a useful research briefing](https://hermeswatcher.com/workflows/daily-research-briefing.md)
- [Know whether an automation actually worked](https://hermeswatcher.com/workflows/reliable-recurring-automation.md)

## Sources

- [Official model configuration](https://hermes-agent.nousresearch.com/docs/user-guide/configuring-models)

---

HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt