One API. Every Model.
Optimal Cost.

NeoRouter intelligently routes your AI requests to the best model for each task. Thompson Sampling learns which models excel at what — saving you money while delivering top-quality results.

Start Free ($1 Credit) View API Docs
--
Requests Routed
--
Money Saved
7
AI Models
6
Providers
# Drop-in replacement for OpenAI — just change base_url from openai import OpenAI client = OpenAI( base_url="https://your-neorouter-url/v1", api_key="ocr_your_key_here" ) response = client.chat.completions.create( model="auto", # NeoRouter picks the best model messages=[{"role": "user", "content": "Hello!"}] )
🧠

Intelligent Routing

Classifies every message by task type and difficulty, then picks the optimal model. No manual model selection needed.

💰

Up to 99% Cost Savings

Uses cheap models for simple tasks, expensive ones only when needed. Thompson Sampling continuously optimizes the cost-quality trade-off.

📈

Gets Smarter Over Time

Multi-armed bandit algorithm tracks model performance per task category. The more you use it, the better it routes.

🔌

OpenAI-Compatible API

Drop-in replacement. Change base_url and api_key in any OpenAI SDK. Works with Python, Node.js, curl, and Claude Code.

🛡

Multi-Provider Failover

6 providers, 7 models. If one provider goes down, traffic auto-routes to alternatives. Built-in health monitoring.

🔍

Full Transparency

See exactly which model handled each request, why it was chosen, and what it cost. Real-time dashboard included.

How It Works

1

Classify

A fast model classifies your message by task type and difficulty in ~200ms

2

Compete

Models compete via Thompson Sampling based on their track record for this task

3

Route

The winning model gets the request and streams the response back to you

4

Learn

Outcome is scored, model trust updated. The system gets smarter with every request

Supported Models

Claude Opus 4.6

Anthropic
Complex coding, creative writing

Gemini 2.5 Pro

Google
Reasoning, web tasks

Gemini 2.5 Flash

Google
Simple tasks, chat, classification

O4 Mini

OpenAI
Terminal, automation

MiniMax M2.5

MiniMax
Chat, general tasks

GLM-4 Plus

Zhipu
Coding (medium)

Kimi K2.5

Moonshot
General purpose

Simple Pricing

Pay only for what you use. No subscriptions, no minimums.

Pay As You Go

Provider cost + 15% platform fee. Start with $1 free credit.

Ready to optimize your AI costs?

Get started in 30 seconds. No credit card required.

Create Free Account