Fast, affordable AI inference API with pay-per-token pricing and dedicated GPU compute
Scalable self-hosted real-time messaging and state sync platform
Stage
Not given
Established
Founded
Not given
2023
Based in
US
CY
Pricing model
Paid
Open source
Pricing
Inference API: DeepSeek V4.1 Flash from $0.1275/M input tokens and $0.51/M output tokens. DeepSeek V4 Flash from $0.14/M input and $0.28/M output. DeepSeek V4 Pro 0813 from $0.561/M input and $1.683/M output. MiniMax M3 from $0.255/M input and $1.02/M output. GLM-5.3 from $1.19/M input and $3.74/M o
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
Pay-per-token pricing with no subscriptions or minimums
Access to 10+ frontier open-source models including DeepSeek, MiniMax, GLM, Kimi and MiMo
OpenAI-compatible API for drop-in integration
NVIDIA B200 and B300 GPUs with speculative decoding
Multi-region deployment for low-latency responses
Zero cold start times with always-warm inference
SOC/2 approved infrastructure with zero data retention
Dedicated 8-GPU HGX nodes available prepaid for 12-36 months
Compatible with 20+ coding tools including Cursor and Claude Code
Vision analysis, web search and native tool calling built-in
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
Industry-leading inference speed: 489 tokens per second on DeepSeek V4.1 Flash
Dramatically lower costs than competitors: $0.51 per million output tokens vs $10.00 for GPT-4o
First to deploy DeepSeek R1 at scale with 351 tokens per second
Enterprise-grade security with SOC/2, GDPR compliance and zero data retention
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
Centrifugo