Skip to content

API Keys

API keys route your requests through Gonka Broker’s proxy layer, which forwards them to the Gonka decentralized network and returns responses in OpenAI-compatible format.

Your app → Gonka Broker Proxy → Gonka GPU Network → Response
  1. Your application sends a request using the OpenAI API format
  2. Gonka Broker receives it and forwards it to the decentralized GPU network
  3. The inference runs on available GPUs
  4. The response is returned to your app in standard OpenAI format

From your application’s perspective, this is identical to calling the OpenAI API.

API keys support the OpenAI Chat Completions API, including:

  • Chat completions (/v1/chat/completions)
  • Streaming responses (stream: true)
  • System, user, and assistant messages
  • Temperature, top_p, max_tokens, and other standard parameters
  • Tool calling (tools, tool_choice)

See API Compatibility for the full list of supported endpoints and parameters.

All requests go to:

https://proxy.gonkabroker.com/v1

Set this as the base_url (Python) or baseURL (JavaScript) in your OpenAI client configuration.

Use caseWorks?
Replacing OpenAI in existing codeYes
Using LangChain, LlamaIndex, or similar frameworksYes
Using Cursor, Continue, or other AI-powered dev toolsYes
Any tool that supports OpenAI-compatible APIYes
  • Your key secret starts with gk-prx- and should be treated like any API credential
  • Gonka Broker does not log or store your prompts and completions
  • If a key is compromised, rotate it immediately — this invalidates the old secret and issues a new one