Spice AI pricing for open source, Cloud, and Enterprise
The Spice runtime is free and open source under Apache 2.0. Spice Cloud plans start at $19 per month, and Spice.ai Enterprise licenses self-hosted production clusters. All three run the same engine and the same spicepod.yaml.
Optimized For
Community
Managed Workloads
Self-Hosted Workloads
Scale
Single-node or self-managed multi-node cluster
Multi-node with clustering and high-availability
Multi-node with clustering and high-availability
Control Plane
Static, configuration-driven only (YAML)
Dynamic, remote (Portal/API-managed)
Dynamic, remote/local (API/YAML)
Remote control in preview
Commercial License
Apache 2.0
Consumption-based TOS
Enterprise Software License
Code / Security Audited
No
Yes
Yes
Security Updates
Latest minus-one release (6-8 weeks)
Rolling updates with automated patches
Tiered support up to 3 years with guaranteed patches
SLA
N/A
99.9% uptime with proactive failover
99.9% uptime with 24/7 on-call
Support
Community (GitHub Issues, Community Slack)
Standard support (email, Slack Connect)
Premium 24/7 support with dedicated account team (Slack Connect)
Distribution
Docker images and GitHub release binaries
Enterprise image via AWS Marketplace SaaS
Enterprise image via AWS Marketplace ECR & AMI
Hosting
Self-Hosted
Fully-managed, cloud-hosted; dedicated deployments (AWS)
Self-hosted BYOL; Kubernetes, AWS AMI
Monitoring & Observability
DIY via OpenTelemetry (e.g. Grafana)
Built-in dashboards with real-time monitoring
BYO (Datadog, New Relic, etc.) or Spice Cloud Connect
Compliance
N/A
SOC 2 Type II audited security & privacy controls
SOC 2 Type II audited security & privacy controls
One engine, nearly unlimited deployment options
Spice is an open-source data and AI runtime. It runs the same way on a laptop, on-prem, at the edge, or in the cloud, so you can change plans without changing your application.
Unified data and
AI engine
Federate data, accelerate queries, perform hybrid search, and run AI models all from one portable runtime that can be deployed locally, on-prem, at the edge, or in the cloud.
Read the deployment docs (opens in a new tab)
Built on
open-source
Spice builds on Apache Arrow, Apache DataFusion, Apache Ballista, Vortex, and Apache Iceberg. The runtime itself is Apache 2.0 licensed.
Read the Spice docs (opens in a new tab)
Designed for performance and scale
Spice accelerates datasets locally for low-latency queries. Run one node, or run a multi-node Apache Ballista cluster for distributed queries.
Read the acceleration docs (opens in a new tab)
Deployed in production
Teams trust Spice to bring inference closer to their data, enabling low-latency, enterprise-grade AI across industries.
“Spice opened the door to take these critical control-plane datasets and move them next to our services in the runtime path.”
Peter Janovsky
Software Architect, Twilio
100x
Faster queries
“It just spins up and works, which is really nice. The responsiveness is amazing, which is a huge gain for the customer.”
Darin Douglass
Principal Software Engineer, Barracuda
Learn how Barracuda gained 100x faster query responses and reduced costs 50% with Spice
“What I like the most about Spice is that it's very easy to collect data from different data sources, and I'm able to interact with this data and do everything in one place.”
Dustin Warner
Director of Software Engineering, NRC Health
FAQs
How pricing works in Spice for open-source, enterprise, and cloud deployments.
The open-source Spice runtime is free under the Apache 2.0 license. Spice Cloud costs $19 per month for Developer and $99 per month for Pro for Teams. Spice Cloud Enterprise and Spice.ai Enterprise use custom pricing. Compare the managed tiers on the Spice Cloud plans page.
Yes. Open source, Spice Cloud, and Spice.ai Enterprise run the same SQL federation and acceleration engine and read the same spicepod.yaml manifest. Your datasets, models, and SQL queries stay the same when you change plans. The plan changes the hosting, the support, and the license terms. Compare the hosting options on the edge-to-cloud deployments page.
Yes. Spice.ai Enterprise is listed on AWS Marketplace with two licensing models. Bring Your Own License (BYOL) uses a license you buy from Spice AI. The Plan model bills through your AWS Marketplace subscription. See the AWS Marketplace deployment guide for the images and the Helm chart.
Yes. Spice runs on-prem in Kubernetes, on virtual machines, or on bare metal. Spice.ai Enterprise adds an enterprise software license, 24/7 support, and SLAs for self-hosted clusters. Hybrid setups also work: run Spice next to the application and keep governance in one central place.
Spice Cloud Enterprise runs on a dedicated, multi-region AWS cluster with high availability. It adds custom vCPU and memory sizes, persistent object storage, JDBC and ODBC access, and up to 1024 concurrent queries. It also includes commercial resale rights, 24/7 on-call support, and a 99.9% SLA.
See Spice in action
Walk through your use case with an engineer and see how Spice handles federation, acceleration, and AI integration for production workloads.
Talk to an engineer (opens in a new tab)