Unified multi-provider AI infrastructure with intelligent routing, provider fallback, and usage-based billing
Scalable self-hosted real-time messaging and state sync platform
Stage
Not given
Established
Founded
Not given
2023
Based in
Not given
CY
Pricing model
Free trial
Open source
Pricing
Usage-based post-paid billing: USD $0.00024 per API request and USD $0.0046 per 1,000 tokens. Six-day free trial available for new accounts.
Open source version is free. Centrifugo PRO available with flat licensing (no per-connection or per-message fees) and requires contacting sales for a quote.
Key features
Chat and inference through public model aliases
Intelligent provider routing across 10 AI providers
Web search capability through the gateway
Web fetch for retrieving content without exposing credentials
Audio transcription workflows
Centralized usage analytics and request logging
Single API key authentication for all providers
Usage-based post-paid billing with no fixed plans
Public model aliases for simplified integration
WebSocket, HTTP-streaming, SSE, WebTransport, and gRPC transports
Channel history and message recovery
Flexible authentication and authorization
State synchronization with transactional consistency
Connection event proxying to backend
Online presence detection for users
Efficient binary Protobuf protocol
Resumable streams and transport fallback for AI applications
What makes it different
One unified API gateway eliminates managing separate integrations for multiple AI providers
Automatic provider fallback reduces dependence on any single AI service
OpenAI-style API simplifies developer integration
Centralized visibility of usage, routing, and billing across all providers
Set up once and works forever with no ongoing configuration needed
Handles millions of concurrent connections with minimal hardware
Self-hosted so messages and data never leave your infrastructure
No per-connection or per-message billing
Works in production at scale with proven reliability
AstraKinetic
Centrifugo