Vespa

Web · Windows · Mac · Linux · Self-hosted · API · paid plans from $0.05/mo

Freedom report

Three barsScore 6.6

  • Free tierA free tier is on its own pricing page
  • Open codeNo open-source code on record
  • Runs widely4 of 6 device platforms
  • DocumentedPlans, terms and facts published

Vespa is an AI search platform for online, data-driven applications that combines retrieval, ranking, machine-learning inference, and real-time serving. It supports vector and tensor search, positional text search, and structured-data search. Ranking signals can be combined through tensor functions or models in formats such as ONNX and XGBoost; Vespa also supports inference using ONNX Runtime. Its functions are distributed across node clusters, and cluster size can change without affecting queries or writes. Teams can self-manage deployments, use the Vespa Kubernetes Operator, or deploy on Vespa Cloud. Local deployment guidance lists Linux, macOS, and Windows 10 Pro on x86_64 or arm64 with Docker Desktop or Podman Desktop. Vespa Cloud encrypts data at rest and in transit, uses node and endpoint certificates, and automatically updates OS patches. A cloud trial includes $300 in usage credits, requires no credit card, and stops the application when credits run out. Cloud plans have quotas; Startup is limited to development zones.

Who it is for

Vespa describes its platform for teams building AI applications where search quality, ranking, fresh real-time data, or growing retrieval traffic matter. It suits teams choosing between self-managed deployment, an operator, and Vespa Cloud.

What is good

  • Supports vector, tensor, positional text, and structured-data search.
  • Can scale clusters without impacting queries or writes.
  • Supports ONNX and XGBoost ranking models.
  • Cloud trial includes $300 in credits without a card.
  • Cloud handles encryption and automatic OS patching.

What to know first

  • Cloud plans have quotas.
  • Startup is limited to development zones.
  • Startup has community support only, with no SLA.
  • Enclave adds cloud-provider resource costs.

Verdict

Vespa offers varied search and ranking methods alongside self-managed and cloud deployment paths. Teams should account for Cloud quotas, the Startup plan’s development-zone limit, and trial credits that stop the application when depleted.

Vespa plans and pricing

All plans
Startup $0.05/mo vCPU $ 0.05 / hour; Memory GB $ 0.005 / hour; Disk GB $ 0.0002 / hour; GPU Memory GB $ 0.03 / hour Shared resources · Community support only · Dev zones only · No SSO or autoscaling cloud.vespa.ai · 22 Sept 2026
Basic $0.10/mo Initial unit prices per hour: vCPU $ 0.1 / hour; Memory GB $ 0.01 / hour; Disk GB $ 0.0004 / hour; GPU Memory GB $ 0.07 / hour Prices go down with volume · Suitable for applications that don't need 24/7 operational support cloud.vespa.ai · 4 Oct 2026
Commercial $0.15/mo Initial unit prices per hour: vCPU $ 0.145 / hour; Memory GB $ 0.0145 / hour; Disk GB $ 0.0005 / hour; GPU Memory GB $ 0.1 / hour Prices go down with volume · 24/7 operational support · Backup and disaster recovery cloud.vespa.ai · 4 Oct 2026
Enterprise $0.18/mo Initial vCPU price is $ 0.18 / hour; Memory GB $ 0.018 / hour; Disk GB $ 0.0007 / hour; GPU Memory GB $ 0.125 / hour; mi $20,000 minimum monthly spend cloud.vespa.ai · 22 Sept 2026
Self Managed Not published Self-managed Vespa deployment · Unlimited support cases · Dedicated support representative available cloud.vespa.ai · 22 Sept 2026
Startup Free Per hour; vCPU $ 0.05 / hour; Memory GB $ 0.005 / hour; Disk GB $ 0.0002 / hour; GPU Memory GB $ 0.03 / hour Dev zones only · Shared resources · No SSO or autoscaling · No redundancy by default · Community support only, no SLA cloud.vespa.ai · 4 Oct 2026

Compared on database software

Free plan
No

Best Vespa alternatives

See all 20