OptimaGPT

OPENAI-COMPATIBLE API

Connect your applications to private AI.

Use familiar OpenAI API patterns to connect supported applications to models running on infrastructure you control.

Node hardware monitoring with CPU, memory, GPU and model executors
Node details - hardware monitoring and model executors. View full size

Familiar API patterns. Models you choose.

Bring private AI into support tools, automation and internal applications.

Connect existing applications

Use compatible clients and integrations with your OptimaGPT Gateway.

Choose your models

Host models on Optima Nodes and select the ones your applications need.

Manage access centrally

Manage API keys through the Gateway and decide which assistants applications can use.

Connect to your Gateway.

Use the product documentation for the API base URL, authentication and supported requests.

Open the documentation ↗
  1. 1

    Set up the Gateway and a Node

    Connect a Node and make the model you want to use available.

  2. 2

    Configure API access

    Create a key and grant access to the assistant where needed.

  3. 3

    Connect and test your application

    Configure your compatible client with the Gateway URL and API key, then test a request.

Bring private AI into existing workflows.

WhosOn

Connect private AI to live chat and customer service workflows.

Explore WhosOn →

Business connectors

Give configured assistants access to selected tools and business data.

Explore Connectors →