Hermes Agent

Configure Hermes Agent for your enterprise and verify the request in your console logs.

Configuration

Use your enterprise HTTPS gateway URL, an API key scoped to this tool and a model ID that supports the protocol. The address below comes from this gateway’s public configuration. Find an eligible model

  1. Run hermes model in the Hermes Agent environment and select Custom Endpoint.
  2. Enter the gateway URL ending in /v1 and your project key. Choose Chat Completions and set an allowed model ID.
API protocolAddress to enter
Chat CompletionsBase URLhttps://tokenpyxis.com/v1

Verification

Start Hermes Agent, send a short text request and check the enterprise logs. If your workflow uses tool calls, test one round in an isolated project.

Check the model, timestamp and token usage in the enterprise console logs. If the tool shows a request ID, look it up directly. See reconciliation steps

Troubleshooting

Run hermes doctor to inspect the configuration. Once the main model works, check separately configured helpers such as summarization and vision.

Business inquiries
Scan with WeChat to add the business team on WeCom