Skip to main content
Hermes Agent can run on any OpenAI-compatible model backend, so point its custom provider at Deepshi.

​
Configure

The quickest way is the interactive picker: 
hermes model
# choose the custom / self-hosted endpoint option
# API base URL:  https://api.deepshi.ai/v1
# API key:       your Deepshi API key
# Model name:    a Deepshi model id, e.g. deepshi-3.0
Or set it directly in ~/.hermes/config.yaml: 
model:
  default: deepshi-3.0
  provider: custom
  base_url: https://api.deepshi.ai/v1
  api_key: YOUR_DEEPSHI_API_KEY
To keep the key out of the file, use a named provider with key_env: 
custom_providers:
  - name: deepshi
    base_url: https://api.deepshi.ai/v1
    key_env: DEEPSHI_API_KEY
    api_mode: chat_completions

model:
  provider: custom:deepshi:deepshi-3.0   # format: custom:<provider>:<model-id>
Hermes Agent is agentic, so pick a model with the tools capability. See Text models.