Key settings
Prerequisites
- The current version of the tool is installed
- A BetterToken API key: register and get one
- A Model ID from the model plaza
Additional requirements
- The selected Model ID comes from the supported provider
- macOS, Linux, or Windows WSL2
Install
Install Hermes Agent
- macOS / Linux / WSL2
- Windows
Feature quick reference
Manual setup
Use the interactive Hermes Agent model setup as the primary path. Command and environment-variable options remain available as alternatives.Setup
- Interactive setup
- CLI config
- Environment variables
1
Run the model selector
2
Choose the OpenAI or OpenAI Compatible provider
Select OpenAI or OpenAI Compatible from the provider list.
3
Fill in the BetterToken config
Enter:
- Base URL:
https://bettertoken.ai/v1 - API Key: your BetterToken API Key
- Model: a model ID from a supported provider copied from the model plaza
4
Restart Hermes Agent
After updating the config, quit the current Hermes Agent session and start it again.
5
Start Hermes Agent
Migrate from OpenClaw
If you already use OpenClaw, first check whether your current Hermes Agent version provides the migration command. Run a dry run before changing anything.https://bettertoken.ai/v1, your BetterToken API Key, and a model ID from a supported provider.
Verify the connection
Send a short test prompt. If the tool returns a response without an authentication or Model ID error, the connection works. Fully restart the tool after changing its configuration.Switch models
Open the model selector or change theModel field in the configuration. Use the exact Model ID from the model plaza, then restart the current session.
Common errors
Troubleshooting
- If requests fail or return no response, confirm that Base URL is exactly
https://bettertoken.ai/v1. Do not append/chat/completionsin this field. - If Hermes reports that the model does not exist, confirm that Model is a model ID from a supported provider from the model plaza.
- If authentication fails, check for copied spaces and confirm that the selected Model ID comes from the supported provider.
- If Hermes still uses the old model after a change, quit the current Hermes Agent session and run
hermesagain. - BetterToken usually does not require an extra
User-Agentor custom headers. Only add headers when your custom gateway, tenant routing, observability, or caching layer explicitly requires them.
Do not commit real API Keys to your repository. For team-shared setup, prefer environment variables or local config.
Related FAQ
- MCP vs API Key and Base URL
- What are model_provider, base_url, and wire_api?
- How to configure an OpenAI-compatible API in Cline
- OpenClaw BetterToken setup guide
Advanced setup
Supported providers
Statuses apply to the BetterToken setup documented on this page.
What the setup methods mean
What the setup methods mean
- Manual setup: enter the API Key, Base URL, and Model.
- Not supported: no verified direct setup is currently available.
Technical details
Protocol, endpoint, and internal provider fields
Protocol, endpoint, and internal provider fields
This setup uses
https://bettertoken.ai/v1. The tool appends the OpenAI-compatible endpoint path. Do not add /chat/completions or /responses unless a specific field explicitly requires it.