API endpoint
Tokener.ai model API base URL and supported OpenAI-compatible paths.
Supported model API surfaces (relative to the base URL below):
| Status | Method | Path | Use for |
|---|---|---|---|
| Supported | GET | /models | List model ids available to your key |
| Supported | POST | /chat/completions | Chat and reasoning models (primary) |
| Supported | POST | /embeddings | Embedding models |
| Supported | POST | /messages | Anthropic Messages API shape |
| Compatible | POST | /responses | OpenAI Responses API (optional; prefer /chat/completions) |
Streaming works on chat-style paths (stream: true). Which models exist, their pricing, and availability are live on the Models catalog — not duplicated here.
Base URL
https://api.tokener.ai/v1
All model traffic uses this OpenAI-compatible base URL. The website and console never proxy LLM calls. Set it as base_url / baseURL and send your Tokener.ai API key as the Bearer token (or x-api-key for /messages).
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.TOKENER_API_KEY,
baseURL: "https://api.tokener.ai/v1",
});Create a key in API keys before calling these paths.
Every response — success or error — carries x-request-id and request-id
headers; include them when contacting support. There is no browser CORS
support: call these paths from your backend, not directly from a browser.
See Errors for error response shapes and the full
error code table.