OpenAI-Compatible64K ContextTool CallingStructured OutputsStreaming SSEOpenAI-Compatible64K ContextTool CallingStructured OutputsStreaming SSEOpenAI-Compatible64K ContextTool CallingStructured OutputsStreaming SSEOpenAI-Compatible64K ContextTool CallingStructured OutputsStreaming SSE
INFERENCE API v1.0 Live

LLM inference, without the markup

An OpenAI-compatible API for agentic, tool-calling, and coding workloads. Low-latency, reliable tool-calling, structured outputs.

terminal
Getting Started with cURL

Up and running in minutes

Agent Route (cURL)

1

Register an Account

Anonymous PIN

                                    

Human Route (Dashboard)

1

Sign Up / Sign In

Identity Auth
Go to Dashboard
+ EMAIL
2

Create an API Key *

terminal

                                    
2

Open Dashboard

Visual Dashboard

Log in first to create keys via the dashboard.

Open Dashboard
3

Make an API Request

terminal

                                

* Using scoped API keys is better and safer for production API usage than temporary access tokens.

Built for every stage of the lifecycle