Managed services - verified
Vespa Cloud
Vespa Cloud is listed under managed services (deployment type: managed provisioned). First listed price, in its own unit: $0.05, per vCPU-hour (Startup plan; memory $0.005/GB-hour, disk $0.0002/GB-hour, GPU memory $0.03/GB-hour). Stated: hybrid and sparse search and built-in embedding. Read from the vendor's own pages on October 18, 2026.
Read from docs.vespa.ai, vespa.ai, raw.githubusercontent.com. Docs - Pricing - License - Compare every vector database
Status
- Availability label
- Not stated
No status label is stated on the pages checked.
How Vespa Cloud charges
Every price Vespa Cloud states, in its own unit, with the quote and where it comes from. Nothing is converted.
| Price | Unit, as stated | Quote and source | Where it comes from |
|---|---|---|---|
| Per vCPU-hour | |||
| $0.05 | per vCPU-hour (Startup plan; memory $0.005/GB-hour, disk $0.0002/GB-hour, GPU memory $0.03/GB-hour) | “Unit prices - vCPU$ 0.05 / hour - Memory GB$ 0.005 / hour - Disk GB$ 0.0002 / hour - GPU Memory GB$ 0.03 / hour” | - |
| $0.1 | per vCPU-hour (Basic, initial) | “Initial unit prices - vCPU$ 0.1 / hour - Memory GB$ 0.01 / hour - Disk GB$ 0.0004 / hour - GPU Memory GB$ 0.07 / hour” | - |
| $0.145 | per vCPU-hour (Commercial, initial) | “Initial unit prices - vCPU$ 0.145 / hour - Memory GB$ 0.0145 / hour - Disk GB$ 0.0005 / hour - GPU Memory GB$ 0.1 / hour” | - |
| $0.18 | per vCPU-hour (Enterprise, initial) | “Initial unit prices - vCPU$ 0.18 / hour - Memory GB$ 0.018 / hour - Disk GB$ 0.0007 / hour - GPU Memory GB$ 0.125 / hour” | - |
| Plan price or monthly minimum | |||
| $20,000 | minimum monthly spend (Enterprise) | “Minimum monthly spend of $20,000” | - |
Plan labels in brackets come from the pricing table's column headings, which the quoted cell text does not always repeat.
Free tier and limits
- Free tier
- Not stated
No free tier is stated on the pricing page; the Startup plan has the lowest unit prices.
- Limits
- Not stated
Not stated on the pages checked.
Search and indexing
- Max dimensions
- Not stated
Not stated on the nearest neighbor or schema reference pages checked.
- Distance metrics
euclidean, angular, dotproduct, prenormalized-angular, hamming, geodegrees
“Vespa supports six different distance-metrics: - euclidean - angular - dotproduct - prenormalized-angular - hamming - geodegrees”
docs.vespa.ai - Index types
HNSW, exact nearest neighbor
“See how to use approximate nearest neighbor search with HNSW in the Approximate Nearest Neighbor Search document.”
docs.vespa.ai - Hybrid and sparse search
Yes: nearestNeighbor combinable with text query terms (BM25 rank features documented)
“This operator can be combined with other filters or query terms using the Vespa query language, making it easy to create hybrid solutions that combine modern vector based techniques with traditional information retrieval.”
docs.vespa.ai - Metadata filtering
Yes
“This operator can be combined with other filters or query terms using the Vespa query language”
docs.vespa.ai - Multi-tenancy
- Not stated
Not described on the pages checked.
Built-in embedding and reranking
- Built-in embedding
Yes: the embed indexing expression
“indexing: input my_document_field embed summary index”
docs.vespa.ai - Built-in reranking
- Not stated
Multi-phase ranking exists in Vespa rank profiles, but a reranking feature is not described on the pages checked.
Deployment, license and SDKs
- Regions and clouds
- Not stated
Not stated on the pages checked.
- BYOC and self-host
Self Managed plan (Vespa deployment including support)
“Self Managed Self Managed Vespa deployment including support.”
vespa.ai - License
Apache-2.0
“Apache License Version 2.0, January 2004”
raw.githubusercontent.com - SDKs
- Not stated
Not listed on the pages checked.
Vendor-stated claims
Performance, scale and SLA figures as Vespa Cloud states them. Not measured.
No performance, scale or SLA figure is recorded from the pages checked.
Research notes
Vespa Cloud charges per allocated machine resource each hour, with unit prices set by support level; the page notes "Prices go down with volume" for paid tiers.
FAQ
How much does Vespa Cloud cost?
In Vespa Cloud's own units: $0.05 (per vCPU-hour (Startup plan; memory $0.005/GB-hour, disk $0.0002/GB-hour, GPU memory $0.03/GB-hour)); $0.1 (per vCPU-hour (Basic, initial)); $0.145 (per vCPU-hour (Commercial, initial)); $0.18 (per vCPU-hour (Enterprise, initial)); $20,000 (minimum monthly spend (Enterprise)). As of October 18, 2026; prices are not converted.
What is the maximum vector dimension in Vespa Cloud?
Not stated. Not stated on the nearest neighbor or schema reference pages checked.
Does Vespa Cloud support hybrid search?
Yes: nearestNeighbor combinable with text query terms (BM25 rank features documented), per the vendor: "This operator can be combined with other filters or query terms using the Vespa query language, making it easy to create hybrid solutions that combine modern vector based techniques with traditional information retrieval."
Does Vespa Cloud have built-in embedding or reranking?
Embedding: Yes: the embed indexing expression. Reranking: not stated. Multi-phase ranking exists in Vespa rank profiles, but a reranking feature is not described on the pages checked.
Sources
Last verified from each vendor's own docs, pricing pages, READMEs and license files; every quote was string-matched against the page that day. This is a dated snapshot, not a benchmark: prices are shown in each product's own unit and change without notice, so check the linked source before you commit.
Newsletter
Know when a vector database changes its pricing
One email per week. New model releases, retrieval tooling and pricing changes and what they mean for what you build.