What Models and providers 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.
Set 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.
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 and failure points
- 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.
Primary sources
Spotted something wrong or out of date? Tell us on X at @HermesWatcher (opens in a new tab) and we will fix it.