Venarm for developers · Preview

One API.
Every route.

Build against a familiar interface while Venarm handles providers, credentials, fallbacks, limits, and observability behind the scenes.

Open ChatExplore the surface
request.js
const response = await fetch("/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${VINEM_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "venarm-auto",
    messages,
    stream: true
  })
});

// Provider routing and fallback are automatic.
Developer preview · The public endpoints shown below are planned and are not live yet. The current chat API remains private to Venarm.

Platform

Infrastructure without the busywork

Venarm is being designed as a dependable model gateway with one policy layer and clear operational visibility.

Intelligent routing

Choose a logical model while Venarm selects an eligible provider and follows the configured fallback chain.

Credential isolation

Provider secrets remain encrypted on the server and never enter browser code, logs, or client responses.

Built-in observability

Trace attempts, latency, failures, fallback behavior, and token reporting from the Admin command center.

Compatibility

A surface your tools already understand

OpenAI- and Anthropic-style interfaces are planned so existing SDKs and agent workflows need minimal changes.

POST/v1/chat/completionsChat and streaming in an OpenAI-compatible shape
POST/v1/messagesAnthropic-compatible messages for agent tooling
GET/v1/modelsModels available to the authenticated account and plan