AI Gateway Overview

Access 100+ AI models through one unified API with intelligent routing, automatic fallbacks, and unified observability

What is Helicone AI Gateway?

Helicone AI Gateway is a unified inference platform that provides access to 100+ AI models from multiple providers through a single OpenAI-compatible API. Simply change your baseURL to start using models from OpenAI, Anthropic, Google, Meta, and dozens of other providers.

Quick Start

Get started in 2 minutes with one line of code

Routing

Intelligent routing across providers

Fallbacks

Automatic failover for reliability

Integrations

Works with your existing tools

Key Features

Unified API

Access models from 20+ providers using the OpenAI API format. No need to learn multiple SDKs or API formats.

// Same API for all providers
const response = await client.chat.completions.create({
  model: "claude-sonnet-4",  // or gpt-4o, gemini-2.0-flash, llama-3.3-70b
  messages: [{ role: "user", content: "Hello!" }]
});

Intelligent Routing

Automatically route requests to the best available provider based on:

• Cost optimization
• Latency requirements
• Provider availability
• Your BYOK (Bring Your Own Key) preferences

Learn more in Routing.

Automatic Fallbacks

Built-in resilience with automatic failover when a provider fails:

// Tries Bedrock first, falls back to Anthropic
model: "claude-3-7-sonnet-20250219/bedrock,claude-3-7-sonnet-20250219/anthropic"

Learn more in Fallbacks.

Cost Tracking

Unified cost tracking across all providers with accurate pricing for 300+ models.

Unified Observability

Single dashboard to monitor requests across all providers with traces, logs, and analytics.

Supported Providers

The AI Gateway supports 20+ inference providers:

OpenAI

GPT-4o, GPT-5, o1, o3, o4

Anthropic

Claude 3.7 Sonnet, Claude 4

Google

Gemini 2.0 Flash, Gemini 3

Meta

Llama 3.3, Llama 4

AWS Bedrock

All Bedrock models

Google Vertex

Vertex AI models

DeepSeek

DeepSeek models

Mistral

Mistral models

xAI

Grok models

Groq

Fast inference

DeepInfra

100+ models

OpenRouter

Multi-provider routing

View the complete list of supported models and providers at helicone.ai/models

How It Works

1. Change Your Base URL

   Update your API client to point to Helicone’s AI Gateway:

   const client = new OpenAI({
     baseURL: "https://ai-gateway.helicone.ai",
     apiKey: process.env.HELICONE_API_KEY,
   });
   
2. Specify Models

   Use model names directly or specify providers:

   // Auto-routing across providers
   model: "gpt-4o-mini"
   
   // Specific provider
   model: "claude-sonnet-4/anthropic"
   
   // With fallback
   model: "gpt-4o/openai,gpt-4o/azure"
   
3. Make Requests

   Use the standard OpenAI API format for all requests:

   const response = await client.chat.completions.create({
     model: "claude-sonnet-4",
     messages: [{ role: "user", content: "Hello!" }]
   });
   

Authentication Options

Pass-Through Billing (PTB)

Use Helicone’s API key and pay through Helicone:

const client = new OpenAI({
  baseURL: "https://ai-gateway.helicone.ai",
  apiKey: process.env.HELICONE_API_KEY,
});

Benefits:

• Single API key for all providers
• Consolidated billing
• No provider account setup needed
• Automatic credit management

Bring Your Own Key (BYOK)

Use your own provider API keys:

const client = new OpenAI({
  baseURL: "https://ai-gateway.helicone.ai",
  apiKey: process.env.HELICONE_API_KEY,
});

Then add your provider keys in the Helicone dashboard.

Benefits:

• Use existing provider credits
• Direct billing from providers
• Priority support with BYOK attempts first

Model Discovery

The AI Gateway provides an OpenAI-compatible /v1/models endpoint to discover available models:

curl https://ai-gateway.helicone.ai/v1/models \
  -H "Authorization: Bearer $HELICONE_API_KEY"

{
  "object": "list",
  "data": [
    {
      "id": "gpt-4o-mini",
      "object": "model",
      "created": 1716537600,
      "owned_by": "openai"
    },
    {
      "id": "claude-sonnet-4",
      "object": "model",
      "created": 1708560000,
      "owned_by": "anthropic"
    }
  ]
}

Next Steps

Get Started

Start using the AI Gateway in 2 minutes

Learn Routing

Understand how requests are routed

Configure Fallbacks

Set up automatic failover

Browse Models

Explore 300+ available models