Skip to main content
PrimaLabs serves open models over a serverless, OpenAI-compatible API. Point any OpenAI SDK at our base URL, pass an API key, and call a model — no infrastructure to run, no reserved capacity, billed per token.

Base URL

Every endpoint in these docs is relative to this base URL. Clients differ in whether they want the /v1 suffix. Use the row that matches yours; a wrong base URL shows up as 404 on paths like /v1/v1/models or /v1/chat/completions/chat/completions. Never set the base URL to a full endpoint such as .../v1/chat/completions.

Authentication

Send your API key as a bearer token on every request:
Create a key in the dashboard. You can hold several — one per app or environment — and they all draw on the same balance. See Authentication.

OpenAI-compatible

The API mirrors the OpenAI wire format, so existing OpenAI clients work with only a base URL and key change:

Endpoints

Next steps

Quickstart

Make your first request in under a minute.

Models

The catalog, pricing, and context windows.

Rate limits

The three limits in front of every request.

Service status

Live uptime per model, incidents, and email updates.