Introduction

Welcome to the Whirlagi

Access all LLMs through the standard OpenAI API format, and reduce token costs by 1/2

We do all the heavy lifting behind the scenes to serve you personalized inference:

--Support token quota details

--Support setting token-specified call models

--Support using key to query usage quotas

--Support charging by number of models

--Support designated organization access

--Support model mapping, redirect user request models

--Support calling management APIs through system access tokens

--Support token management

A full production-ready LLM flow behind 1 line of code.