Skip to content

Remote Models

Remote models allow you to connect any OpenAI-compatible inference API to Menatic AI, with API keys stored securely server-side.

  1. Navigate to AI Models
  2. Click Add Model
  3. Select Remote
  4. Fill in the form:
FieldDescription
NameDisplay name (e.g., GPT-4o, Claude 3.5)
API EndpointBase URL of the OpenAI-compatible API
API KeyYour API key (stored encrypted in the database)
Model IDModel identifier sent in API requests (e.g., gpt-4o)
  1. Click Save
Endpoint: https://api.openai.com/v1
Model ID: gpt-4o
Endpoint: https://<resource>.openai.azure.com/openai/deployments/<deployment>
Model ID: gpt-4o

Anthropic’s native API is not OpenAI-compatible, but you can use a proxy like LiteLLM to adapt it.

Any server that implements the OpenAI /v1/chat/completions endpoint works as a remote model.

Remote models appear in the sidebar under the Remote section alongside local Ollama models. They can be selected in the Admin Chat assistant and any other interface that supports model selection.

API keys are stored encrypted in the platform database. They are never exposed in the frontend or logs. Requests to remote providers are made server-side by the backend.