Vexrail LogoVexrail
Developer Resources

The Vexrail API.

An OpenAI-compatible proxy that works with the SDKs you already use. Change the base URL, add two headers, done.

Transparent Proxy Architecture

Vexrail sits between your app and the LLM provider. Requests flow through unchanged while Vexrail captures analytics and optionally injects contextual recommendations.

Your App Sends a Request

A standard chat completion call with your API keys in the headers. No extra fields or parameters needed.

Vexrail Proxies to the LLM

The request is forwarded to the model provider (OpenAI, Anthropic, etc.). Analytics are captured in parallel.

Response Returned

The LLM response is returned in standard OpenAI format. If monetization is enabled, contextual recommendations are woven into the response naturally.

Your App
Vexrail
LLM
POST /v1/chat/completions
x-publishable-key: pk_live_...
x-secret-key: sk_live_...
200 OK { choices: [...] }

Works With Your Stack

Since Vexrail is OpenAI-compatible, it works with any SDK that supports a custom base URL. We provide integration guides for OpenAI SDK, LangChain, Vercel AI SDK, and OpenRouter.

Need more control?

Call the REST API directly for custom integrations. Standard OpenAI chat completions format with two extra auth headers.