OpenAI Compatible
OpenAI API proxy - Use GPT-4, GPT-4o, GPT-3.5-turbo with existing OpenAI SDK. Drop-in replacement for ChatGPT API with access to 200+ LLM models.
OpenAI Compatible API
UniterRouter provides full compatibility with OpenAI's API, allowing you to use any OpenAI SDK or library with 200+ models from multiple providers.
Quick Start
Simply change your base URL to use UniterRouter:
from openai import OpenAI
client = OpenAI(
base_url="https://api.uniterouter.ai/v1",
api_key="your_uniterouter_api_key",
)
response = client.chat.completions.create(
model="gpt-4o", # or any supported model
messages=[{"role": "user", "content": "Hello!"}]
)Drop-in Replacement: Any application using OpenAI SDK can switch to UniterRouter by changing only the base URL and API key.
Supported Endpoints
| Endpoint | Method | Description |
|---|---|---|
/v1/chat/completions | POST | Create chat completions |
/v1/embeddings | POST | Generate text embeddings |
/v1/images/generations | POST | Generate images from text |
/v1/audio/transcriptions | POST | Transcribe audio to text |
/v1/models | GET | List available models |
Features
Chat Completions
Core API for text generation
Streaming
Real-time token-by-token responses
Vision
Analyze images with multimodal models
Function Calling
Integrate external tools and APIs
Structured Output
JSON mode with schema validation
Reasoning Models
o1, o3, DeepSeek for complex problems
Embeddings
Text embeddings for semantic search
Images
Generate images from text
SDK Examples
Python
pip install openaiTypeScript/Node.js
npm install openaiEnvironment Variables
export OPENAI_API_KEY="your_uniterouter_api_key"
export OPENAI_BASE_URL="https://api.uniterouter.ai/v1"How is this guide?
API Reference
LLM API documentation - OpenAI, Claude, Gemini API reference for UniterRouter. Complete guide for GPT-4, Claude 3.5, Gemini Pro integration with code examples.
Chat Completions POST
OpenAI Chat Completions API - Create GPT-4, GPT-3.5 chat completions through UniterRouter. Compatible with OpenAI SDK, supports streaming and function calling.