Introduction

What is Router9?

Router9 is a subscription-based LLM gateway — an OpenRouter alternative with flat monthly pricing. It provides a unified API for all major LLM providers, multimodal skills, persistent storage, and enterprise-grade observability — built specifically for autonomous AI agents.

Key Features

OpenAI-Compatible API — Drop-in replacement that works with any OpenAI SDK, Claude Code, Cursor, LangChain, and more
Multi-Model Access — Route requests to OpenAI, Anthropic, Google, and OpenRouter models through a single endpoint
Flat Monthly Pricing — Predictable costs with no per-token billing. Choose Free ($0), Assistant ($29), or Engineer ($59) per agent
Agent Isolation — Each agent gets its own API key, usage quotas, storage, and audit logs
Multimodal Skills — Built-in speech-to-text, text-to-speech, image understanding, image generation, and web search via MCP
Persistent Storage — S3-compatible file storage with per-agent isolation
Audit Logging — Every request logged with model, tokens, latency, status, and full payloads

Quick Start

# Set your environment variables
export OPENAI_BASE_URL=https://api.router9.com/v1
export OPENAI_API_KEY=sk-r9k-your-key-here

# Make a request
curl $OPENAI_BASE_URL/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

See the Quick Start guide for step-by-step setup instructions.

Documentation Overview

Getting Started

Quick Start — Get up and running in under 5 minutes
Authentication — API key management and security

Agent Plane

Agent Management — Create and manage agent plans
Billing & Plans — Pricing tiers and subscription management
Audit Logs — Track and export request history
Security — Sessions, account security, and best practices

API Reference

Chat Completions — OpenAI-compatible chat API
Models — Available models and routing
Anthropic API — Native Anthropic Messages endpoint
Rate Limiting — Request quotas and 429 handling
Errors — Error codes and response format

Tools

Audio — Speech-to-text and text-to-speech
Vision — Image understanding and generation
Web Search — Real-time web search
Storage — Persistent file storage
Quotas — Tool usage limits by plan

On this page