Pricing

Pricing

Startup

VPC deployment

All inference and optimization features

Single AWS region

Standard support

Startup

VPC deployment

All inference and optimization features

Single AWS region

Standard support

Enterprise

Everything in Startup, plus:

Multi-region deployments

SSO

Advanced RBAC

Audit logs and governance

Dedicated engineering support

Contractual SLAs

Enterprise

Everything in Startup, plus:

Multi-region deployments

SSO

Advanced RBAC

Audit logs and governance

Dedicated engineering support

Contractual SLAs

Compare plans

Feature

Startup

Enterprise

Inference Platform

Control Plane

R1 Orchestrator

Model Storage

vLLM Autotuner

Monitoring & Observability

CLI Tools

Python SDK

MCP Server

MCP Integration

Infrastructure

VPC Deployment

Auto Capacity Reservations

Multiple AWS Regions

—

Security & Governance

SSO

—

Advanced RBAC

—

Audit Logs

—

Governance Controls

—

Support

Standard Support

Dedicated Support

—

SLAs

—

Feature

Startup

Enterprise

Inference Platform

Control Plane

R1 Orchestrator

Model Storage

vLLM Autotuner

Monitoring & Observability

CLI Tools

Python SDK

MCP Server

MCP Integration

Infrastructure

VPC Deployment

Auto Capacity Reservations

Multiple AWS Regions

—

Security & Governance

SSO

—

Advanced RBAC

—

Audit Logs

—

Governance Controls

—

Support

Standard Support

Dedicated Support

—

SLAs

—

Feature

Startup

Enterprise

Inference Platform

Control Plane

R1 Orchestrator

Model Storage

vLLM Autotuner

Monitoring & Observability

CLI Tools

Python SDK

MCP Server

MCP Integration

Infrastructure

VPC Deployment

Auto Capacity Reservations

Multiple AWS Regions

—

Security & Governance

SSO

—

Advanced RBAC

—

Audit Logs

—

Governance Controls

—

Support

Standard Support

Dedicated Support

—

SLAs

—

Run models. Not infrastructure.