Use ZhiFlo in Hermes
Hermes provides a Custom endpoint flow for the ZhiFlo address, Token, protocol, and model. After you save the provider, hermes chat can use it for a real reply.
Before you start
Section titled “Before you start”- Install Hermes from its official documentation, then confirm that
hermes --versionprints version information. - Create a Token for this device.
- Copy a complete model ID from your account.
On Windows, search for PowerShell from Start. On macOS, open Terminal; on Linux, open a terminal from the application menu. If the command is missing immediately after installation, close the old terminal, open a new one, and check the version again.
Run the model setup flow
Section titled “Run the model setup flow”-
Exit the current Hermes chat if one is open.
-
Run this command in a normal terminal:
Terminal window hermes model -
Select Custom endpoint.
-
Enter this API Base URL:
https://api.zhiflo.com/v1 -
Paste the dedicated ZhiFlo Token at the API Key prompt.
Paste the Token only at this credential prompt. Keep it out of commands, screenshots, and chat messages.
-
Select this compatibility mode:
chat_completions -
Select an account model from the discovered list. If discovery does not return it, enter the complete model ID manually.
-
Review the address, compatibility mode, and model ID in the summary.
-
Save the provider.
Use hermes model to add a provider. The /model command inside a chat only switches among providers that have already been configured.
Start a chat
Section titled “Start a chat”Run:
hermes chatConfirm that the current provider or model points to the ZhiFlo entry, then send:
Do not call tools. Reply with OK only.An OK reply shows that the provider was saved, the model was selected, and a request returned content.
If setup or chat fails
Section titled “If setup or chat fails”- Model discovery is empty: enter the complete model ID from your account manually. Discovery failure alone does not prove the entered model is unavailable.
- ZhiFlo is absent from
/model: exit the chat, rerunhermes model, and complete the final save step. 401response: reopen the setup flow and update the Token, checking for missing characters, expiration, or revocation.404response: usehttps://api.zhiflo.com/v1withchat_completions.
Next: Review usage and quota.