Single API endpoint for multiple AI providers. OpenAI compatible.
Universal Proxy
OpenRouter
200+ models
GLM (Z.ai)
Z1 & GLM-4 series
More Soon
Coming providers
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"}] }'
OpenRouter and GLM currently supported, more providers coming soon
Drop-in replacement for OpenAI SDK and compatible tools
Server-Sent Events (SSE) support for responsive experiences
Intelligent routing to the most cost-effective providers
Access to 200+ models from various providers through OpenRouter's API
ChatGLM models including GLM-4.6, GLM-4.5, and Z1 series
Standard /v1/chat/completions endpoint. Compatible with OpenAI SDK and tools like Cursor, Continue.dev
Ollama-compatible endpoints: /api/chat, /api/generate, /api/tags
Access multiple AI providers through a single unified interface. Switch between OpenRouter, GLM, and more without changing your code.
Browse providers →Compatible with OpenAI and Ollama formats. Works with existing tools like Cursor, Continue.dev, LangChain, and any OpenAI SDK.
View formats →Full support for Server-Sent Events (SSE) streaming. Get tokens as they're generated for responsive user experiences.
Learn more →Route requests to the most cost-effective provider for each task. Access free models when possible, premium models when needed.
Compare costs →