Vespa Professional Plan

Service · Managed service · Engineering & development by Vespa.ai

Managed Vespa support and operations for customer-facing production workloads.

Vespa Professional Plan is a managed service tier designed for businesses running customer-facing production workloads on Vespa Cloud or Vespa Enclave. The service automates essential operational tasks such as CI validation, continuous deployment, and managed backups, allowing teams to focus on application development rather than infrastructure maintenance. It is available across major cloud providers including AWS, Azure, and GCP through the Enclave deployment model or as a fully managed service in Vespa Cloud. This plan ensures predictable performance and reliability for large-scale AI searc

Languages
English

Category: AI Infrastructure

Deployment
Vespa Cloud, Vespa Enclave (AWS, Azure, GCP)
Engagement model
Subscription (Resource-based hourly rates)
Delivery
Online / Managed Service
Team
Vespa engineers and developers
Production Support
24/7
Production Issue Response
1 hour
  • Automated CI validation and continuous deployment
  • Managed backups and disaster recovery included
  • Resource-based pricing starting at $0.145/vCPU hour

Overview

Vespa Professional Plan is a managed service tier designed for businesses running customer-facing production workloads on Vespa Cloud or Vespa Enclave. The service automates essential operational tasks such as CI validation, continuous deployment, and managed backups, allowing teams to focus on application development rather than infrastructure maintenance. It is available across major cloud providers including AWS, Azure, and GCP through the Enclave deployment model or as a fully managed service in Vespa Cloud. This plan ensures predictable performance and reliability for large-scale AI search and recommendation applications.

Operations and Reliability

  • CI/CD Automation: The plan includes automated CI validation and continuous deployment for application updates.
  • Backups & DR: Managed backup and disaster recovery services are included to protect application data.
  • Deployment Flexibility: The service is available for applications deployed in Vespa Cloud or Vespa Enclave environments.

Platform Management

  • Managed Infrastructure: Vespa manages the underlying infrastructure and operations, including automated upgrades and scaling.
  • Monitoring and Security: The platform provides built-in production monitoring and security for managed clusters.
  • Resource-Based Billing: Resource-based pricing allows teams to pay for vCPU, memory, disk, and GPU usage per hour.

Published results

  • 1-hour response for production issues, Next business day response for deployments

Use cases

  • Development teams automate their deployment pipeline using built-in CI validation and continuous deployment features.

Pricing

vCPU (Professional)
$0.145 / hour
Memory GB (Professional)
$0.0145 / hour
Disk GB (Professional)
$0.0005 / hour

Specifications

Deployment
Vespa Cloud, Vespa Enclave (AWS, Azure, GCP)
Engagement model
Subscription (Resource-based hourly rates)
Delivery
Online / Managed Service
Team
Vespa engineers and developers
Production Support
24/7
Production Issue Response
1 hour
Deployment Response
Next business day
vCPU Rate
$0.145 / hour
Memory Rate
$0.0145 / hour per GB
Disk Rate
$0.0005 / hour per GB
Deployment Platforms
Vespa Cloud, AWS, Azure, GCP

FAQ

Does the Professional plan include backups?

Yes, both managed backups and disaster recovery (DR) are included in the Professional plan.

How is the Professional plan priced?

Pricing is resource-based, with initial unit rates of $0.145 per vCPU hour, $0.0145 per GB of memory per hour, and $0.0005 per GB of disk per hour.

Added by AntSpace from public sources (vespa.ai).

Related

More services by Vespa.ai