Universal AI Proxy

Single API endpoint for multiple AI providers. OpenAI compatible.

UnifiedAI

Universal Proxy

Your App
OR

OpenRouter

200+ models

GLM

GLM (Z.ai)

Z1 & GLM-4 series

+

More Soon

Coming providers

Quick Start
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:9000/v1",
    api_key="sk-test"
)

response = client.chat.completions.create(
    model="openrouter-deepseek/deepseek-chat",
    messages=[{"role": "user", "content": "Hello"}]
)
import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'http://localhost:9000/v1',
  apiKey: 'sk-test'
})

const response = await client.chat.completions.create({
  model: 'openrouter-deepseek/deepseek-chat',
  messages: [{role: 'user', content: 'Hello'}]
})
curl -X POST http://localhost:9000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-test" \
  -d '{
    "model": "openrouter-deepseek/deepseek-chat",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
200+ AI Models
5+ Providers
2 API Formats
100% Free

Multi-Provider Access

OpenRouter and GLM currently supported, more providers coming soon

OpenAI Compatible

Drop-in replacement for OpenAI SDK and compatible tools

Real-Time Streaming

Server-Sent Events (SSE) support for responsive experiences

Cost Optimization

Intelligent routing to the most cost-effective providers

Supported Providers

OpenRouter

Access to 200+ models from various providers through OpenRouter's API

GLM (Z.ai)

ChatGLM models including GLM-4.6, GLM-4.5, and Z1 series

API Formats

OpenAI v1 Format

Standard /v1/chat/completions endpoint. Compatible with OpenAI SDK and tools like Cursor, Continue.dev

Ollama Format

Ollama-compatible endpoints: /api/chat, /api/generate, /api/tags

OR
GLM
OAI
AWS
GCP
HF
XAI
+

One API for All Providers

Access multiple AI providers through a single unified interface. Switch between OpenRouter, GLM, and more without changing your code.

Browse providers →
/v1/chat/completions
/api/chat
/api/generate

Standard API Formats

Compatible with OpenAI and Ollama formats. Works with existing tools like Cursor, Continue.dev, LangChain, and any OpenAI SDK.

View formats →

Real-Time Streaming

Full support for Server-Sent Events (SSE) streaming. Get tokens as they're generated for responsive user experiences.

Learn more →
Direct
UnifiedAI
Save up to 60%

Cost Optimization

Route requests to the most cost-effective provider for each task. Access free models when possible, premium models when needed.

Compare costs →