Access multiple AI models through a single OpenAI-compatible endpoint. Simple pricing, powerful analytics, full control.
Access all models through a single unified endpoint
More models added regularly. Login to request specific models.
Everything you need to integrate AI into your applications
Drop-in replacement for OpenAI SDK. Use your existing code with zero changes — just swap the base URL and API key.
Real-time token streaming via Server-Sent Events. Build responsive UIs with instant model responses.
Built-in per-user rate limits and token quotas. Protect your budget and ensure fair usage across all consumers.
Track every request — tokens used, latency, costs, and model performance. All accessible from your dashboard.
Generate unique API keys with individual limits. Revoke anytime. Keys are hashed and only shown once.
Use simple aliases instead of full model IDs. Switch underlying models without changing your code.
Start calling AI models in seconds
# List available models curl -s https://nexus.aaizu.id/v1/models \ -H "Authorization: Bearer YOUR_API_KEY" # Chat completion curl -s https://nexus.aaizu.id/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "glm-5", "messages": [{"role": "user", "content": "Hello!"}], "stream": false }'