Vespa pricing
Vespa starts at $0.05/hour, with self-serve signup.
Last checked 2026-09-01. Verify on the vendor's own page before you commit spend.
Plans
| Plan | Price | Included |
|---|---|---|
| Startup | vCPU $0.05/hour, Memory GB $0.005/hour, Disk GB $0.0002/hour, GPU Memory GB $0.03/hour | Shared resources, no SSO, no autoscaling, no redundancy by default, dev zones only |
| Basic | vCPU $0.1/hour, Memory GB $0.01/hour, Disk GB $0.0004/hour, GPU Memory GB $0.07/hour | Next business day support |
| Commercial | vCPU $0.145/hour, Memory GB $0.0145/hour, Disk GB $0.0005/hour, GPU Memory GB $0.1/hour | 24/7 operational support, 1 hour response time |
| Enterprise | vCPU $0.18/hour, Memory GB $0.018/hour, Disk GB $0.0007/hour, GPU Memory GB $0.125/hour | Minimum monthly spend of $20,000, 15 minutes response time 24/7 |
| Self Managed | Contact Sales | Unlimited support cases per contract |
There is no free entry plan, so an agent needs a paid account before its first call. The top plan (Self Managed) is quoted rather than listed, so anything at that volume goes through a person.
Can an agent buy this on its own?
A price is only half the question. The other half is whether software can get from landing on the site to making a paid call without a person, which is what the AgentReady measures under adopt.
For Vespa, it can create an account itself.
Against that, a sales call gates access; the signup flow assumes a human at a browser; credentials must be minted by hand in a dashboard. Each of those is a point where an unattended run stops and waits for a human.
That works out to 55/100 on adopt, against 56/100 overall.
What you are paying for
Vespa.ai develops the Vespa AI Search Platform, a distributed serving engine that unifies retrieval, ranking, machine learning inference, and real-time serving for business-critical AI applications. It lets users query, organize, and make inferences in vectors, tensors, text and structured data, scaling to billions of constantly changing data items with thousands of queries per second and latencies below 100 milliseconds.
Next
Vespa's full agent-readiness profile breaks down all 41 signals. Alternatives to Vespa ranks what else does the same job.
An agent can fetch this as data: GET /v1/pricing?domain=vespa.ai