Features
Unified API key for 100+ LLMs (GPT-5.5, Claude, Gemini, DeepSeek, Qwen, etc.)
Zero platform fee – pay only official provider prices
Global network acceleration with nodes in Tokyo, Singapore, Frankfurt
99.99% uptime with multi-region automatic failover
Granular cost controls: daily/weekly/monthly budgets per key or user
Zero content retention – prompts never logged or used for training
Support for vision, image generation, audio, video, and file modalities
Streaming responses and prompt caching across models
Function calling and structured output support
IP allowlisting for API keys
Google single sign-on (SSO) for team authentication
Usage and cost analytics dashboard
Automatic provider routing and fallback
OpenAI, Anthropic, and Gemini protocol compatibility
Prompt caching with configurable cache duration
One-command install on macOS, Linux, Windows
Run hundreds of open models locally
MLX engine for Apple Silicon (faster, less memory)
GGUF model support via llama.cpp (Ollama 0.30)
NVIDIA Nemotron 3 Ultra for high-throughput reasoning
Cloud scaling with Free, Pro, Max tiers
Run multiple cloud models in parallel (1, 3, 10)
Web-enabled cloud agents for real-time info retrieval
Fully offline operation for mission-critical work
Data never used for training; privacy-first design
CLI tool with model management and configuration
REST API for building AI applications
Upload and share private models (Pro and above)
40,000+ community integrations
Desktop app for macOS, Linux, Windows
