AI Gateway

AI Gateway is a standalone routing layer for production LLM traffic. Send requests through one OpenAI-compatible endpoint to access 300+ models across providers, with built-in fallbacks, retries, load balancing, and usage tracking.

Quick Start

Complete the first request in a few minutes.

Create an account

Connect a provider

Open BYOK, choose OpenAI, select Connect, and add your provider API key.

Create an API key

Open API Keys, select Create API key, and copy the key.

Run a request

Set the key in your terminal and send a request to the Responses endpoint.

export ORQ_API_KEY="your-api-key"

curl -X POST https://api.orq.ai/v3/router/responses \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4",
    "input": "Hello, world!"
  }'

Inspect the request

Open Traces to review the response, latency, token usage, and cost.

Next steps

Fallbacks & Retries

Keep requests flowing when a provider fails.

Supported Models

Browse the model catalog and provider capabilities.

⌘I

Overview

Routing

Security & Privacy

Model Capabilities

Analytics & Monitoring

Integrations

Quick Start

Next steps

Fallbacks & Retries

Supported Models

​Quick Start

​Next steps

Fallbacks & Retries

Supported Models

Quick Start

Next steps