Skip to main content
Use this page if you want the fastest mental model for how AI Stats works before you move into the quickstart, SDKs, or API reference. AI Stats gives you one API for models, providers, routing, pricing, and async AI workflows. That means you can:
  • call multiple providers through one consistent API
  • keep request and response handling simpler
  • track usage, latency, and price in one place
  • change models or routing strategy without rebuilding your app
You can get started on :free models with zero deposited credits. Paid models require available wallet balance.

Why teams use AI Stats

AI integrations get harder as soon as you need more than one provider, more than one model, or more than one deployment environment. AI Stats gives you a stable integration layer so you can ship features first and adjust providers, routing, or pricing strategy later.

Core features

Unified Endpoints

Standardized chat, image, and moderation endpoints that work consistently across all providers.

Smart Routing

Requests are dynamically routed to the optimal provider for speed, cost, or reliability.

Built-in Usage Tracking

Every request is logged with latency, token counts, and cost metrics for transparent reporting.

BYOK (Bring Your Own Key)

Optionally connect your own provider API keys to manage billing and rate limits yourself while still benefiting from the Gateway’s unified interface.

Getting started

  1. Sign up for an AI Stats account.
  2. Generate an API key in your dashboard.
  3. Make your first request to the /v1/responses endpoint.

Quickstart

Jump into our quickstart to make your first successful API call in under a minute.

Next steps

Authentication

Learn how to authenticate securely using your personal or team API key.

API Reference

Browse the complete API documentation with endpoints, parameters, and response schemas.

Best Practices

Guidance on how to get the most out of the AI Stats Gateway.

Examples

Copy ready-to-run snippets for Next.js, Node.js streaming, Python, and curl.

Need more detail? Continue with Integrating with the Gateway for an end-to-end walkthrough, then explore Integrations or Rate limits as you scale.
Last modified on May 19, 2026