Cloud Equivalents

AI agents · AWS vs Google Cloud

Amazon Bedrock Agents Classic / Amazon Bedrock AgentCore vs Agent Studio (formerly Vertex AI Studio) / Agent Runtime (formerly Agent Engine)

For console-configured agents like classic Bedrock Agents, Google Cloud's path is to prototype in Agent Studio and deploy to Agent Runtime.

Partial match Use it to: Define an agent by configuration (instructions, action groups, and knowledge bases) instead of writing orchestration code.

Last verified: · Edit on GitHub · Report an error

Side-by-side comparison

Configuration-based agents (legacy Bedrock Agents): AWS vs Google Cloud side by side
AspectAmazon Web ServicesGoogle Cloud
ServiceAmazon Bedrock Agents Classic Maintenance
Amazon Bedrock AgentCore
Agent Studio (formerly Vertex AI Studio)
Agent Runtime (formerly Agent Engine)
LifecycleThe original Bedrock Agents (launched Nov 2023), renamed Agents Classic. Not open to new customers from July 30, 2026. AWS recommends migrating to AgentCore.
Generally available
Generally available
Renamed from Vertex AI Agent Engine on Apr 22, 2026.
What it isConfiguration-based agents with action groups and knowledge bases.
Modular agent platform. Harness (managed agent loop), Runtime, Memory, Gateway (MCP), Identity, Code Interpreter, Browser, Observability, Evaluations, Optimization, Policy, Registry, Payments. Works with any framework and any model.
Console workspace for trying models, refining system instructions and prompts, and prototyping agents.
Managed runtime to deploy and scale agents built with ADK or other frameworks, with Sessions, Memory Bank, code execution, and observability.
Pricing modelAgents Classic charges no separate agent fee. You pay for model tokens and the resources invoked.Agent Runtime compute (vCPU-hours and GiB-hours) plus model tokens.
DocsAmazon Bedrock Agents Classic docs
Amazon Bedrock AgentCore docs
Agent Studio (formerly Vertex AI Studio) docs
Agent Runtime (formerly Agent Engine) docs
Pricing pageAmazon Bedrock Agents Classic pricing
Amazon Bedrock AgentCore pricing
Agent Studio (formerly Vertex AI Studio) pricing
Agent Runtime (formerly Agent Engine) pricing

Key differences

  • Bedrock Agents (classic) is in maintenance in favor of AgentCore; Google's equivalent path is also code-first (ADK on Agent Runtime).
  • Action groups map to ADK tools or MCP servers; knowledge bases map to RAG Engine or Agent Search.

Pricing summary

Pricing models only. No prices are quoted because they change by region and over time.

AWS
Agents Classic charges no separate agent fee. You pay for model tokens and the resources invoked. Amazon Bedrock Agents Classic pricing → Amazon Bedrock AgentCore pricing →
GCP
Agent Runtime compute (vCPU-hours and GiB-hours) plus model tokens. Agent Studio (formerly Vertex AI Studio) pricing → Agent Runtime (formerly Agent Engine) pricing →

And on Azure?

Partial match Azure's equivalent is Foundry Agent Service. AWS vs Azure comparison →

FAQ

What is the Google Cloud equivalent of Amazon Bedrock Agents Classic and Amazon Bedrock AgentCore?

For console-configured agents like classic Bedrock Agents, Google Cloud's path is to prototype in Agent Studio and deploy to Agent Runtime.

How does pricing compare between Amazon Bedrock Agents Classic and Amazon Bedrock AgentCore and Agent Studio (formerly Vertex AI Studio) and Agent Runtime (formerly Agent Engine)?

AWS: Agents Classic charges no separate agent fee. You pay for model tokens and the resources invoked. Google Cloud: Agent Runtime compute (vCPU-hours and GiB-hours) plus model tokens. Check the official pricing pages for current rates.

What is the Azure equivalent?

Foundry Agent Service (partial match). Bedrock Agents Classic is in maintenance (no new customers since July 30, 2026).

Related AWS vs GCP comparisons

Official sources