Vespa Ai Plans Pricing
Vespa Cloud pricing tiers — Startup, Basic, Commercial, Enterprise, Self-Managed. Pricing is resource-based (vCPU-hour, GiB-memory-hour, GiB-disk-hour, GiB-GPU-memory-hour) with volume discounts up to 50% and a 15% committed-spend discount.
Vespa Ai Plans Pricing is the machine-readable pricing-plan profile for Vespa on the APIs.io network, conforming to the API Commons Plans specification.
It defines 6 plans, covering paid, custom, and free tiers, with named plans including Startup, Basic, Commercial, Enterprise, Self Managed, and 1 more.
Tagged areas include AI Search and Vector Database.
Plans
Lowest-cost plan for testing and early-stage businesses. Shared resources, dev zones only, community support, no SLA.
- Shared resources
- Dev zones only
- No redundancy by default
- Community / Slack support
- No SLA
For applications without 24/7 support needs. Next-business-day support for production / deployment issues.
- Dedicated resources
- NBD support response
- 2 business-day response for non-production
Production-ready with 24/7 operational support, 1-hour response for production issues, backup and disaster recovery.
- 24/7 operational support
- 1-hour response for production issues
- Backup and disaster recovery included
Premium tier with a $20,000 monthly minimum, 15-minute response SLA, SSO, named support representative, dedicated Slack channel, and on-site visits.
- 15-minute SLA for production
- SSO
- Named support representative
- Dedicated Slack channel
- On-site visits available
Run open-source Vespa on your own infrastructure with a commercial support contract and dedicated representative. Pricing per contract.
- Run on your own infrastructure
- Apache 2.0 open-source license
- Dedicated support representative
- Custom contract terms
Apache 2.0 open-source Vespa engine, self-hosted. Free of license cost; community support only.
- Apache 2.0 license
- Full Vespa engine
- Community support via Slack and GitHub