Skip to main content

Base URL & Authentication

All traffic goes through one base URL:
https://api.openference.com/v1

Full endpoint examples

PurposeURL
Chat (OpenAI format)https://api.openference.com/v1/chat/completions
Chat (Anthropic format)https://api.openference.com/v1/messages
Responses APIhttps://api.openference.com/v1/responses
Embeddingshttps://api.openference.com/v1/embeddings
List modelshttps://api.openference.com/v1/models

Authentication

Use HTTP Bearer token authentication.
Authorization: Bearer sk-token-XXXXXXXXXXXXXXXX
  • Keys are created in the dashboard.
  • Prefix is always sk-token- for new keys (legacy sk-user- keys continue to work).
  • Keys can be restricted to a subset of models.

cURL

-H "Authorization: Bearer sk-token-YOUR_KEY"

OpenAI SDK (Python / JS)

client = OpenAI(
    base_url="https://api.openference.com/v1",
    api_key="sk-token-YOUR_KEY"
)
const client = new OpenAI({
  baseURL: "https://api.openference.com/v1",
  apiKey: "sk-token-YOUR_KEY",
});

One key for everything

A single key works simultaneously across:
  • Cursor, Claude Code, Codex CLI, OpenCode
  • Continue, Cline, VS Code extensions
  • Python, Node, any SDK or framework
  • curl, Postman, etc.
You can also create separate keys per environment or tool for usage tracking.

Model restrictions

When creating or editing a key you can limit which models it can access.
  • The GET /v1/models response will only return allowed models for that key.
  • Requests to disallowed models return 403.
  • Leave the restriction empty to allow all active models.

Next