Inference platform for deploying AI models in production
Scalable self-hosted real-time messaging and state sync platform
Stage
Established
Established
Founded
2019
2023
Based in
Not given
CY
Pricing model
Paid
Open source
Pricing
Baseten offers three pricing tiers: Basic (pay-as-you-go starting at $0/month), Pro (with volume discounts available), and Enterprise (with custom SLAs and volume discounts). Compute pricing varies by GPU type, ranging from $0.00058/minute for CPU instances to $0.16633/minute for B200 GPUs. Model AP
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
Dedicated inference deployments
Pre-optimized model APIs
Multi-cloud deployment
Self-hosted and hybrid options
Training infrastructure with Loops SDK
Baseten Chains for compound AI
Advanced caching and decoding techniques
Baseten Embeddings Inference (BEI)
Forward-deployed engineering support
HIPAA and SOC 2 Type II compliance
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
99.99% uptime with cross-cloud high availability
Fastest embeddings with 2x higher throughput
Pay only for compute in use, not idle time
Optimized inference stack with custom kernels and latest decoding techniques
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