Fast, Affordable AI Inference for Developers
A unified AI inference platform with built-in playground, usage dashboard, and OpenAI-compatible API. Access DeepSeek, Qwen, and GLM models with competitive pricing.
One Endpoint, All Models
curl https://unillm.ccwu.cc/api/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-chat",
"messages": [{"role": "user", "content": "Hello!"}]
}'Drop-in compatible with OpenAI SDK. Just change the base URL and API key.
See UniLLM in Action
A powerful platform built for developers who need fast, reliable AI inference.
Playground
Test models interactively with our built-in playground.
Usage Dashboard
Monitor your API usage, costs, and performance in real time.
API Documentation
Comprehensive docs with examples in Python, Node.js, and cURL.
Why UniLLM
Built for developers who need reliable, fast, and affordable access to the best AI models.
Lightning Fast
Optimized inference with low latency. Your applications stay fast and responsive.
Multiple AI Models
DeepSeek, Qwen, and GLM accessible through a consistent API with competitive pricing and transparent routing.
Flexible Billing
Simple prepaid credits with no subscriptions. Pay for what you need, when you need it.
Supported Models
DeepSeek
DeepSeek-Chat, Reasoner
Open WeightQwen
Qwen-Max, Plus
GLM
GLM-4-Plus