Cloud platforms

Lane A uses models you already buy. Lane B runs in your VPC.

Lane A: models you already buy

Models you already buy on AWS Bedrock, Azure OpenAI or Google Vertex connect with your own credentials, the same way as any other provider. Replay and switching use them only while they stay enabled. The same open-weight model can have a different price on each host: Parezen keeps those prices versioned and prefers the cheaper healthy host when your policy allows it. Marketplace listings come after launch.

Lane B: gateway in your own cloud (later)

Self-hosted options come after launch, for teams that must keep traffic in their own cloud: Docker, AWS (ECS, EKS), Azure (Container Apps, AKS), Google Cloud Run and Kubernetes. At launch, every team uses the hosted gateway at https://api.parezen.com/v1.