Predictable pricing at any scale

Your costs are based on the resources your application uses, not how many queries you run. Scale compute, memory, storage, and GPUs as your workload grows.

Choose how you run Vespa

Choose the deployment option that best fits your infrastructure, operational, and business requirements. Vespa Cloud, Vespa Enclave, and Vespa Enterprise each offer different levels of control and flexibility, with support options tailored to your needs.

  • Cloud

    Fully managed by Vespa, in Vespa Cloud

    • Vespa manages infrastructure & operations
    • Automated deployment, upgrades, & scaling
    • Built-in production monitoring & security

    Resource-based pricing

    Rates vary by PLAN

    Best when time to market matters. Vespa runs the platform, so our engineers can see your cluster directly and act on it.

    Start free trial

  • Enclave

    Fully managed by Vespa, in your cloud

    • Vespa manages infrastructure & operations
    • Data stays in your cloud environment (AWS, Azure, GCP)
    • Use your cloud commitments

    Resource-based pricing

    Rates vary by PLAN

    Best when data must remain in your cloud environment.

    Talk to us

  • Enterprise

    Operated by your team, with Vespa support

    • Your team manages operations
    • Runs in your cloud or data center
    • Includes Kubernetes operator

    Custom pricing

    Annual license sized to your deployment

    Contact us to discuss licensing and support options

    Best for environments where a managed service is not an option.

    Talk to us

More ways to get started

Whether you're an early-stage startup or prefer to manage your own infrastructure, Vespa offers flexible ways to build and scale. Explore our startup offering or deploy Vespa's open-source platform on your own terms.
Startup
Designed for early-stage companies developing and testing applications on Vespa Cloud. Get managed infrastructure and predictable resource pricing.

Unit prices*
- vCPU: $0.05 / hour
- Memory GB: $0.005 / hour
- Disk GB: $0.0002 / hour
- GPU GB: $0.03 / hour
*Low fixed unit cost

Community support only, with no SLA.
Start free trial
Open Source
The full Vespa core engine, Apache 2.0, released as monthly snapshot builds. No hardened image — critical fixes arrive with the next snapshot rather than on an SLA. For teams that want to run and operate Vespa themselves. Community support only, no SLA.
View on GitHub

Select the plan that fits your workload

Select the level of support that matches your team's needs and workload requirements. Plans are available for Vespa Cloud, Vespa Enclave, and Vespa Enterprise, with faster response times and additional capabilities at higher tiers. Startup and Open Source offerings are not included in these support plans.

  • Basic

    Non-critical production workloads

    Initial unit pricing

    • vCPU: $0.10 / hour
    • Memory GB: $0.01 / hour
    • Disk GB: $0.0004 / hour

    What's included

    • Next business day response
    • CI validation & continuous deployment

  • Professional

    Customer-facing production workloads

    Initial unit pricing

    • vCPU: $0.145 / hour
    • Memory GB: $0.0145 / hour
    • Disk GB: $0.0005 / hour

    What's included

    • 24/7 support
    • Production issues: 1-hour response
    • Deployment: Next business day response
    • Other: Next business day response
    • CI validation & continuous deployment
    • Backups & DR

  • Premium

    Critical workloads requiring the fastest response and named experts

    Pricing

    • Custom pricing
    • $20k / month minimum

    What's included

    • 24/7 support
    • Production issues: 15-minute response
    • Deployment: 1-hour response
    • Other: Next business day response
    • CI validation & continuous deployment
    • Backups & DR
    • Named experts

GPU and Enclave rates are in Pricing details below. Visit the Developer Center for additional helpful resources.

Vespa offerings at a glance

Explore the differences in deployment, infrastructure management, features, and support to find the Vespa offering that best fits your needs.

Deployment
Open Source
Self-managed
Cloud
Fully managed
Enclave
Managed in your cloud
Enterprise
Supported self-hosted
Runs in
Your infrastructure
Vespa Cloud
Your cloud account (AWS, Azure, GCP)
Your infrastructure
Managed by
Your team
Vespa
Vespa
Your team, with Vespa support
Cloud / environment options
Cloud or on-premises
Supported Vespa Cloud regions
Supported Vespa Cloud regions
Cloud or on-premises

Core Engine
Open Source
Self-managed
Cloud
Fully managed
Enclave
Managed in your cloud
Enterprise
Supported self-hosted
Vector, lexical & hybrid search
Filtered vector search
Multi-phase ranking & reranking
Tensor computation & ML inference
Custom query processing
Grouping, aggregation, & faceting
Streaming search (personal mode)
Real-time indexing & partial updates

Platform & management
Open Source
Self-managed
Cloud
Fully managed
Enclave
Managed in your cloud
Enterprise
Supported self-hosted
Managed embedding/inference
Autoscaling
via Kubernetes
Automated verification and deployment pipeline
Metrics dashboards
Console

Operations & reliability
Open Source
Self-managed
Cloud
Fully managed
Enclave
Managed in your cloud
Enterprise
Supported self-hosted
Cluster provisioning & setup
Your team
Automated
Automated
Automated, with playbooks
Vespa releases
Monthly build snapshots, manually applied
Releases and automatic upgrades several times per week
Releases and automatic upgrades several times per week
Releases several times per week
Multi-AZ high availability
with Professional plan
with Professional plan
Your team
Multi-region failover
with Premium plan
with Premium plan
Your team
Backups & disaster recovery
with Professional plan
with Professional plan
Your team
Monitoring & observability
Uptime SLA
Based on support plan
Based on support plan
Based on contract
OS & platform upgrades
Your team
Automatic, zero downtime
Automatic, zero downtime
Your team, with hardened image updates from Vespa
CVE and bug-fix SLA
Resource management
Failed node replacement, resource type optimization
Failed node replacement, resource type optimization
Failed node replacement

Security & compliance
Open Source
Self-managed
Cloud
Fully managed
Enclave
Managed in your cloud
Enterprise
Supported self-hosted
SOC 2 Type II
GDPR-aligned data residency
EU regions
Private endpoint
SSO / SAML
with Premium plan
with Premium plan
Audit logging
Hardened images
Intrusion detection

Frequently asked questions

How does Vespa's $300 trial work?
You sign up without a credit card and get $300 in trial credit on Vespa Cloud. Use it to build, index your real data, and run real queries. When the credit runs out, the cluster tears down automatically. There are no surprise charges.
How difficult is going from trial to production?
It's the same Vespa Cloud underneath, with no migration necessary. Going from trial to a production-sized cluster is a config change in your application package. You pick a higher plan, increase node count, and redeploy.
Why not a per-query price?
Two queries can differ by 100x in the work they do. A keyword lookup against a million docs and a hybrid query that runs an ML reranker over a billion are not the same product. Pricing on resources reflects what is actually being computed.
What's the difference between Open Source and Vespa Cloud?
Open Source provides the core Vespa engine for self-managed deployments. Vespa Cloud adds managed infrastructure, automated operations, monitoring, security capabilities, and commercial support, allowing your team to focus on building applications rather than managing the platform.
When does Vespa Enterprise make sense?
Vespa Enterprise makes sense when a managed service isn't an option (air-gapped, regulated, or strict on-prem environments). Vespa Enterprise is the supported way to run Vespa yourself: security-hardened image, Kubernetes operator for automated ops, CVE and bug-fix SLAs, vendor support.

Pricing details

Each plan sets an hourly unit price for machine resources.

Resource (per hour)
Cloud: Basic
Cloud: Professional
Enclave: Basic
Enclave: Professional
vCPU
$0.10
$0.145
$0.08
$0.12
Memory GB
$0.01
$0.0145
$0.008
$0.012
Disk GB
$0.0004
$0.0005
$0.0003
$0.0004
GPU GB
$0.07
$0.10
$0.06
$0.08

You'll be charged for the resources allocated to the application at each point in time. These are the resources specified in services.xml for production clusters, and scaled-down versions of these resources for other zones (either explicitly deployed or ephemeral for tests). In addition, Vespa Cloud may temporarily allocate resources for necessary operational tasks such as migration off failed nodes or migration due to node type changes.

You are only charged for container and content clusters; all control plane resources are provided at no additional cost.

Unit prices decrease linearly with the amount of total resources allocated to the application across all clusters, up to a 50% reduction (83% on Enclave). Enclave prices are lower since your own cost for compute resources comes in addition.

Ready to build with Vespa?

Start building with $300 in Vespa Cloud credits, or talk with our team about pricing, configuration options, and finding the right fit for your workload.

Start free trial Talk to us