---

title: 'Spice.ai Deployment Guide' sidebar_label: 'Deployment' description: 'Deploy Spice.ai in your environment using Docker, Kubernetes, AWS, Azure, or the Spice Cloud Platform. Learn about sidecar, microservice, tiered, and cluster deployment architectures.' keywords: [ spice.ai, deployment, docker, kubernetes, aws, azure, sidecar, microservice, cluster, helm, cloud platform ] image: /img/og/spiceai.png sidebar_position: 11

Spice runs as a single binary, a container, a Kubernetes workload, or a fully managed app on the Spice Cloud Platform. This guide helps choose a target environment and a deployment architecture to match an application's latency, scale, and operational requirements.

Choose a deployment target

Most users fall into one of three groups:

• Run Spice next to an application — start with Docker (opens in a new tab) for a local container, or follow Getting Started (opens in a new tab) to run the binary directly.
• Operate Spice in production on Kubernetes — use the Spice Helm chart (opens in a new tab). For automated rollouts, see the CI/CD guide (opens in a new tab) for Helm pipelines and GitOps with Argo CD (opens in a new tab) or Flux (opens in a new tab).
• Use a managed service — deploy a Spicepod to the Spice Cloud Platform (opens in a new tab) and connect a GitHub repository (opens in a new tab) for continuous delivery.

:::tip Self-hosted enterprise deployments For production self-hosted clusters, the Spice.ai Enterprise Kubernetes Operator (opens in a new tab) provides per-replica StatefulSets, automatic PVC resizing, configurable update strategies, crashloop protection, and distributed query execution through SpicepodSet and SpicepodCluster custom resources. :::

Deployment architectures

Architecture refers to where Spice runs in relation to the application and data sources, and how it scales. Pick an architecture before choosing a guide; the same target environment can host any of these patterns.

• Overview (opens in a new tab) — when to choose each architecture.
• Sidecar (opens in a new tab) — Spice runs alongside the application for the lowest latency.
• Microservice (opens in a new tab) — single or multiple replicas behind a load balancer.
• Tiered (opens in a new tab) — separate read and write tiers for mixed workloads.
• Cluster-Sidecar (opens in a new tab) — combine local and remote Spice instances.
• Hosted (opens in a new tab) — managed on the Spice Cloud Platform.
• Sharded (opens in a new tab) — partition data across multiple Spice instances.
• Cluster (opens in a new tab) — distributed query execution with Spice.ai Enterprise.

Deployment guides

Step-by-step instructions for each target environment.

Guide	When to use
Kubernetes (opens in a new tab)	Self-hosted production deployments. Covers Helm, Argo CD, and Flux.
Docker (opens in a new tab)	Local development, single-host deployments, and container-based pipelines.
Spice Cloud (opens in a new tab)	Fully managed deployments without operating infrastructure.
AWS (opens in a new tab)	Deployments on AWS using the published CloudFormation template.
Azure (opens in a new tab)	Deployments on Azure using ARM/Bicep templates.
GCP (opens in a new tab)	Deployments on Google Cloud using GKE, Cloud Run, or Compute Engine.
CI/CD (opens in a new tab)	Automating any of the above through pipelines or GitOps.
Read/Write Separation (opens in a new tab)	Production pattern that splits ingest from reads using shared snapshots.