Skip to content

Guide library

Comparison · Cloud AI platforms

AWS Bedrock vs Google Vertex AI: Cloud AI Platforms Compared

Google folded Vertex AI into Gemini Enterprise Agent Platform in April 2026. Here is how it compares with Amazon Bedrock on models, pricing tiers, RAG, agents and guardrails, with list prices as of Nov 11.

Metarix Editorial · Nov 10, 2026 · 13 min read

Documentation-based research

Metarix cover graphic: Amazon Bedrock vs Google Vertex AI, now Gemini Enterprise Agent Platform, comparing models, pricing tiers, RAG, agents, guardrails and MLOps

Amazon Bedrock and Google's Vertex AI do the same basic job: they give you managed access to foundation models inside a cloud account, with that cloud's identity, logging and billing. The real differences are which models each one carries, how you pay for capacity, and how much of the RAG, agent and safety stack comes built in.

One thing changed this year that many comparisons miss. On April 22, 2026, Google folded Vertex AI into Gemini Enterprise Agent Platform and renamed most of its parts (release notes). This guide uses the new names, with the old ones alongside. All prices are US list prices as of Nov 11, 2026, taken from AWS and Google Cloud pricing pages and linked inline.

Quick verdict

Pick the platform that already holds your data, identity and cloud commit. That rule settles most decisions. When it doesn't, the model you need comes next. Gemini is only on Google's platform, and OpenAI's proprietary GPT models are on Bedrock but not Google's. Claude costs the same per token on both.

Scroll the table horizontally on smaller screens.

Bedrock vs Agent Platform at a glance
AreaAmazon BedrockGemini Enterprise Agent Platform (ex-Vertex AI)
Exclusive model familyOpenAI GPT models (proprietary), Amazon NovaGemini
Shared modelsClaude, Llama, DeepSeek, Qwen, Mistral, GemmaClaude, Llama, DeepSeek, Qwen, Mistral, Gemma
Catalog size19 model providers listed on the pricing page200+ models in Model Garden
Claude Sonnet 5.5 (global)$2 input / $10 output per 1M tokens$2 input / $10 output per 1M tokens
Discount tiersFlex and Batch at 50% off Standard; Priority at a 75% premiumBatch (and Flex for Gemini 3) at 50% off; Priority at a premium
Reserved capacityReserved tier (1 or 3 months, per 1K TPM) and Provisioned Throughput (model units)Provisioned Throughput in GSUs (1 week to 1 year)
Managed RAGManaged Knowledge Bases: $5 per GB-month, $1 per 1,000 retrievalsRAG Engine, Vector Search, Agent Search
Web groundingWeb Search tool: $12 per 1,000 calls; AgentCore Web Search: $7 per 1,000 queriesGoogle Search grounding: 5,000 free queries a month, then $14 per 1,000
Agent platformAgentCore (Runtime, Memory, Gateway, Identity, Policy and more)Agent Runtime, Sessions, Memory Bank, Agent Gateway, ADK
Safety layerGuardrails, billed per 1,000 text units per filterModel Armor: 2M tokens a month free, then $0.10 per 1M tokens
Metarix summary of AWS and Google Cloud pricing pages and docs, prices as of Nov 11, 2026. Claude prices are for the global endpoint; regional endpoints cost 10% more on both clouds.
Diagram comparing Amazon Bedrock and Gemini Enterprise Agent Platform layer by layer: models, ways to pay, RAG and search, agents, safety, tuning and MLOps
Bedrock and Agent Platform, layer by layer. Graphic: Metarix, from AWS and Google Cloud docs and pricing pages, Nov 10, 2026.

First, the name: Vertex AI is now Agent Platform

Google's April 22 release notes say Vertex AI "is now part of Gemini Enterprise Agent Platform," and the old Agent Builder moved in with it (release notes). The Vertex AI API is now called the Agent Platform API, though Google's RAG Engine docs still point Python users to the Vertex AI SDK. Docs and pricing pages now use the new names, so it helps to know the mapping.

Scroll the table horizontally on smaller screens.

Vertex AI names and their 2026 replacements
Old Vertex AI nameNew name on Agent Platform
Vertex AI PlatformAgent Platform
Vertex AI StudioAgent Studio
Vertex AI Model GardenModel Garden
Vertex AI Agent EngineAgent Runtime
Agent Engine Sessions / Memory BankAgent Platform Sessions / Memory Bank
Vertex AI SearchAgent Search
Vertex AI RAG EngineRAG Engine
Vertex AI Vector Search 2.0Agent Retrieval
Vertex AI Pipelines / Model Registry / Feature StoreAgent Platform Pipelines / Model Registry / Feature Store
Source: Gemini Enterprise Agent Platform release notes, April 22, 2026 entry, accessed Nov 10, 2026.

On AWS, the naming is more stable. Bedrock is the model and inference service. Amazon Bedrock AgentCore is the agent platform that sits beside it, and it works with models from inside or outside Bedrock.

Model catalog: who has what

Both platforms are multi-vendor now. The catalogs overlap more than older comparisons suggest. Claude is on both, and Bedrock lists 19 providers on its pricing page, from AI21 Labs to Z AI. Google says Model Garden offers "over 200 foundation models" (overview). The table shows where each major family is served as a managed API.

Scroll the table horizontally on smaller screens.

Where each model family runs as a managed API
Model familyAmazon BedrockAgent Platform
Gemini (Google)No. Only Google's open Gemma modelsYes, first-party (Gemini 4 Argon, Gemini 4 Carbon, Gemini 3.x Flash)
OpenAI GPT (proprietary)Yes, e.g. GPT-6.1 SolNo. Only open-weight gpt-oss-120b and gpt-oss-20b
Claude (Anthropic)Yes, incl. Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.2Yes, incl. Opus 5.5, Sonnet 5.5, Haiku 5.5, Fable 5.2
Amazon NovaYes, first-party (Nova 2.0 Pro, Lite, Omni, Sonic)No
xAI GrokListed as a providerYes (Grok 4.7, 4.6, 4.3 and others)
MetaLlama 4, 3.3, 3.2, 3.1Llama 4, 3.3 plus Muse models
Open-weight othersDeepSeek, Qwen, Mistral, MiniMax, Moonshot, Z AIDeepSeek, Qwen, Mistral, MiniMax, Moonshot (Kimi), GLM
Bring your own weightsCustom Model ImportDeploy open models from Model Garden to your own endpoints
Sources: Amazon Bedrock pricing page and AWS Price List API; Google Cloud Agent Platform and partner model pricing pages; accessed Nov 11, 2026. Model lists change often; check the console for your region.

If Claude is your main model, the platform choice barely changes the token bill, but features do differ between Anthropic's own API and the cloud versions. Our Claude API vs Bedrock vs Vertex AI comparison covers those gaps, rate limits and data handling in detail.

Pricing compared

Both clouds bill per million tokens and split input from output. Both also charge about 10% more for regional or data-residency endpoints than for the global endpoint. For Claude Sonnet 5.5 on Bedrock in us-east-1, the Price List shows $2 / $10 at global and $2.20 / $11 in-region. Google charges $4.40 / $22 for Gemini 4 Argon at non-global endpoints, against $4 / $20 global.

Token prices for headline models

Scroll the table horizontally on smaller screens.

List prices per 1M tokens, global endpoint, Standard tier
ModelPlatformInputOutput
Claude Opus 5.5Bedrock and Agent Platform$4.00$20.00
Claude Sonnet 5.5Bedrock and Agent Platform$2.00$10.00
Claude Haiku 5.5Bedrock and Agent Platform$0.10 ($0.50 for long-context prompts)$0.50 ($2.50 for long-context prompts)
Gemini 4 ArgonAgent Platform$4.00 from Dec 1 ($2.00 effective until Nov 30)$20.00 from Dec 1 ($10.00 effective until Nov 30)
Gemini 4 CarbonAgent Platform$4.00 from Dec 1 ($2.00 effective until Nov 30)$20.00 from Dec 1 ($10.00 effective until Nov 30)
Gemini 3.5 FlashAgent Platform$1.50$9.00
Gemini 3.5 Flash-LiteAgent Platform$0.30$2.50
Amazon Nova 2.0 ProBedrock$1.25$10.00
Amazon Nova 2.0 LiteBedrock$0.30$2.50
OpenAI GPT-6.1 SolBedrock$2.00$10.00
Sources: AWS Price List API for Amazon Bedrock (us-east-1, published Nov 9, 2026); Google Cloud Agent Platform pricing and partner model pricing pages. Prices as of Nov 11, 2026. The lower price for Gemini 4 Argon and Gemini 4 Carbon until Nov 30 comes as 50% credits back on net spend.

Two Google details are worth noting. First, Gemini 4 Argon and Gemini 4 Carbon share the same per-token price: $2 input and $10 output per million tokens until Nov 30, then $4 and $20 from Dec 1. The lower November price isn't a list price. Google applies it as 50% credits back, and standard pricing starts on December 1 (pricing). Carbon became generally available on Nov 10, 2026. Our Gemini 4 Carbon pricing piece covers why the same rate can still produce a higher bill per task. Second, from November 13, 2026, Gemini 4 completions longer than 32K tokens are billed for retrievable tokens even if the request fails on a client or server timeout. Set sensible max-output limits on long-running jobs.

Service tiers and discounts

Bedrock now has four inference tiers, chosen per request with a service_tier parameter (AWS docs). Google sells the same idea through Standard, Priority and Flex/Batch options on its pricing tables.

Scroll the table horizontally on smaller screens.

How each platform discounts or prioritises traffic
OptionAmazon BedrockAgent Platform
StandardDefault on-demand priceDefault pay-as-you-go price
Priority75% premium; requests jump ahead of Standard and FlexPriority tables, e.g. Gemini 4 Argon and Carbon at $7.20 / $36 per 1M tokens from Dec 1
Flex50% discount for work that can waitFlex/Batch tables for Gemini 3 models
Batch50% lower than on-demand for select models50% off, e.g. Gemini 4 Argon and Carbon at $2 / $10 from Dec 1; Claude Sonnet 5.5 at $1 / $5
Reserved capacityReserved tier: 1 or 3 months, fixed price per 1K tokens-per-minute, 99.5% uptime targetProvisioned Throughput (below)
Sources: Amazon Bedrock service tiers documentation and pricing page; Google Cloud Agent Platform and partner model pricing pages; accessed Nov 11, 2026.

On Bedrock, Priority, Standard and Flex share one on-demand quota, while a Reserved tier booking sits outside it. Traffic above the reservation overflows to Standard instead of failing. Reserved tier needs at least 100,000 input and 10,000 output tokens per minute, and AWS says you arrange it through your account team.

Provisioned Throughput

Bedrock's older Provisioned Throughput still exists for some models. It is sold in model units per hour with no commitment, a 1-month term or a 6-month term. Cohere Command, for example, costs $49.50, $39.60 or $23.77 per model-unit-hour. For Anthropic models, the pricing page tells you to contact your account team. Google sells Provisioned Throughput in generative AI scale units (GSUs). Each GSU gives a fixed amount of per-second throughput, and the price falls with longer terms.

Scroll the table horizontally on smaller screens.

Google Provisioned Throughput, price per GSU (global)
CommitmentPer hourRoughly per month
1 week$7.14about $1,200 per week
1 month$3.70about $2,700
3 months$3.29about $2,400
1 year$2.74about $2,000
Source: Google Cloud Agent Platform pricing page, accessed Nov 10, 2026. Monthly figures are Google's own worked example. Non-global endpoints cost about 10% more per GSU. Until Nov 30, 2026, Google credits back 50% of Provisioned Throughput spend on Gemini 4 Argon.

A worked monthly bill

To make the list prices concrete, here is one monthly workload priced on each platform: 1 billion input tokens and 200 million output tokens, Standard tier, global endpoint, no caching. These models are not equal in quality, so treat this as a price map, not a recommendation. Our guide to cost per successful task explains why the cheapest token isn't always the cheapest answer.

Scroll the table horizontally on smaller screens.

Illustrative bill: 1B input + 200M output tokens per month
ModelWhereInput costOutput costMonthly total
Claude Opus 5.5Either$4,000$4,000$8,000
Gemini 4 Argon (from Dec 1)Agent Platform$4,000$4,000$8,000
Gemini 4 Carbon (from Dec 1)Agent Platform$4,000$4,000$8,000
Claude Sonnet 5.5Either$2,000$2,000$4,000
Gemini 3.5 FlashAgent Platform$1,500$1,800$3,300
Amazon Nova 2.0 ProBedrock$1,250$2,000$3,250
Gemini 3.5 Flash-LiteAgent Platform$300$500$800
Amazon Nova 2.0 LiteBedrock$300$500$800
Claude Haiku 5.5 (short prompts)Either$100$100$200
Metarix calculation from the list prices above, as of Nov 11, 2026. Moving the work to Batch roughly halves each total where batch is offered. Prompt caching can cut input costs further.

Caching usually changes this picture more than the choice of platform. A Claude Sonnet 5.5 cache hit costs $0.10 per million tokens on both clouds, a twentieth of the normal input price. See our prompt caching break-even guide for the math.

RAG and grounding

Both platforms will host retrieval for you, but they charge for it differently. Bedrock's Managed Knowledge Bases are the fully managed option. You pay $5 per GB of raw data a month for the index and $1 per 1,000 Retrieve calls. Parsing, embeddings and reranking with AWS's managed models cost nothing extra, and connectors cover S3, SharePoint, Confluence and more. Self-managed Knowledge Bases, where you bring your own vector store, are still available.

On Google, RAG Engine ingests from sources such as Cloud Storage and Google Drive, builds a corpus and retrieves context for Gemini. It supports VPC Service Controls and CMEK, but Google's docs say data residency and AXT security controls aren't supported. Several US and EU regions also need allowlist access for new projects. Agent Search (the old Vertex AI Search) and Vector Search are the other managed retrieval options.

Scroll the table horizontally on smaller screens.

Managed retrieval and web grounding
FeatureAmazon BedrockAgent Platform
Managed RAGManaged Knowledge Bases: $5 per GB-month index, $1 per 1,000 Retrieve callsRAG Engine; grounding with your data at $2.50 per 1,000 requests
Multi-step retrievalAgentic Retrieval: $4 per 1,000 calls plus underlying Retrieve callsAgent Search and Vector Search, priced separately
Web groundingWeb Search tool: $12 per 1,000 calls (OpenAI GPT-5.4 and later). AgentCore Web Search: $7 per 1,000 queriesGrounding with Google Search: 5,000 free queries a month, then $14 per 1,000
Maps groundingNo equivalent on the pricing pageGrounding with Google Maps: 5,000 free, then $14 per 1,000
Connectors and controlsNative connectors for S3, SharePoint, Confluence and moreCloud Storage and Google Drive ingestion; VPC-SC and CMEK supported; no data residency
Sources: Amazon Bedrock pricing page and Price List API (Web Search tool); Amazon Bedrock AgentCore pricing page and Price List API (Web Search); Google Cloud Agent Platform pricing and RAG Engine overview; accessed Nov 11, 2026.

Web grounding looks close on price at moderate volume, but AWS now sells two different search products. At 100,000 grounded prompts a month with one search each, Google would bill about $1,330 after the free 5,000. The Bedrock Web Search tool, at $12 per 1,000 calls, would cost about $1,200. AgentCore Web Search, priced at $7 per 1,000 queries, would cost about $700; AWS made a direct InvokeWebSearch API generally available on Nov 10, 2026, at that same $7 rate. Google counts every query a prompt triggers, so prompts that fire several searches cost more. The $12 Bedrock tool is a server-side feature on OpenAI GPT-5.4 and later, while AgentCore Web Search can be called from agents on any model. Bedrock's domain controls for web search are covered in our Bedrock web search filtering piece.

Agents: AgentCore vs Agent Runtime

This is where the two platforms look most alike. AgentCore is a set of modular services: Harness (a managed agent loop), Runtime, Memory, Gateway, Identity, Code Interpreter, Browser, Observability, Evaluations, Policy, Registry and Payments. AWS says it works with any framework, including LangGraph, CrewAI, Strands, Google ADK and the OpenAI Agents SDK, and with models outside Bedrock.

Google's equivalent is split into Build, Scale, Govern and Optimize pillars (overview). It includes the Agent Development Kit, Agent Studio, Agent Runtime with Sessions and Memory Bank, plus Agent Identity, Agent Gateway, Agent Registry and agent evaluation. The release notes say Agent Runtime supports sub-second cold starts and long-running operations of up to 7 days.

Scroll the table horizontally on smaller screens.

Agent hosting prices (US list)
ItemAgentCore (us-east-1)Agent Platform
Runtime compute$0.0895 per vCPU-hour$0.085 per vCPU-hour
Runtime memory$0.00945 per GB-hour$0.009 per GiB-hour
Idle timeCPU not billed during I/O wait; idle memory reclaimed after 120 s in Runtime v2Idle time between turns not billed
Tool gateway$0.005 per 1,000 Gateway invocations1 vCPU-hour ($0.085) per 15,000 Gateway calls, about $0.0057 per 1,000
Code sandbox / browserCode Interpreter and Browser at $0.0895 per vCPU-hourCode Execution billed as Agent Compute
Memory storagePriced per memory record stored and retrievedMemory Bank: $0.30 per GiB-month, plus read/write operations
Sources: AWS Price List API for AgentCore (us-east-1) and AgentCore pricing page; Google Cloud Agent Platform pricing page (Agents section); accessed Nov 10, 2026. AgentCore Runtime v2 lists $0.1276 per vCPU-hour and $0.0169 per GB-hour.

At these rates, hosting will rarely decide the choice. Model tokens and tool calls will dominate most agent bills. Pick the runtime that matches your identity provider, observability stack and framework. Both run open frameworks, so you aren't locked into one SDK. If you are already on AWS, our AgentCore tool page collects our related coverage.

Guardrails and safety

Bedrock Guardrails is a configurable filter layer for model inputs and outputs. Each filter is billed separately per 1,000 text units, and a text unit is up to 1,000 characters (pricing). Google's Model Armor screens prompts, responses and agent interactions for prompt injection, data leaks and harmful content. It is billed per token across Agent Platform, Google's MCP servers, Apigee and other integrations.

Scroll the table horizontally on smaller screens.

Safety layers compared
CheckBedrock GuardrailsModel Armor
Harmful contentContent filters: $0.15 per 1,000 text unitsIncluded in Model Armor screening
Prompt attacksPrompt attack filter: $0.08 per 1,000 text units (InvokeGuardrailChecks API)Prompt injection and jailbreak detection
Sensitive dataPII filters: $0.10 per 1,000 text units; regex filters freeSensitive data leak detection
Off-limits topicsDenied topics: $0.15 per 1,000 text unitsNot listed as a separate filter
Grounding / logic checksContextual grounding: $0.10; Automated Reasoning: $0.17 per 1,000 text units per policyNot offered as a separate check
Free allowanceWord and regex filters free2M tokens a month free, then $0.10 per 1M tokens
Sources: Amazon Bedrock pricing page (Guardrails) and Google Cloud Model Armor page, accessed Nov 10, 2026.

The units make a direct comparison hard, so here is a rough one. Take 1 million requests a month, each with about 1,000 characters of prompt and 1,000 of response. That is 2 million text units per filter, so running content and PII filters on Bedrock would cost about $500. On Model Armor, assuming about 4 characters per token, the same traffic is roughly 500 million tokens, or about $50. Bedrock's extra grounding and Automated Reasoning checks have no direct Model Armor equivalent, so price the checks you actually need.

Fine-tuning and MLOps

Bedrock lists three customization methods (AWS docs). Supervised fine-tuning uses labeled examples. Reinforcement fine-tuning uses reward functions written in AWS Lambda. Distillation fine-tunes a smaller student model on a larger teacher model's outputs. You pay for tokens processed in training plus monthly model storage. Serving depends on the model: custom Nova models cost the same on demand as base Nova, while some other customized models are served through Provisioned Throughput. Custom Model Import lets you bring your own weights. AWS says a Llama 3.1 70B model with 128K context needs 8 Custom Model Units.

Google tunes Gemini directly. Gemini 3.5 Flash supports supervised and reinforcement fine-tuning at $0.01 per 1,000 training tokens, and Gemini 3.5 Flash-Lite supports supervised tuning at $0.003 per 1,000 (pricing). A tuned Gemini 3 or later model costs the same as its base model at the global endpoint and 1.5 times as much at non-global endpoints. Open models such as Llama 3.3 70B and Qwen 3 can be tuned too.

Scroll the table horizontally on smaller screens.

Customization and ML lifecycle
CapabilityAmazon BedrockAgent Platform
Supervised fine-tuningYes, on supported modelsYes, Gemini 3.5 Flash and Flash-Lite, Gemini 2.5, Gemma, Llama, Qwen
Reinforcement fine-tuningYes, with Lambda reward functionsYes, Gemini 3.5 Flash
DistillationYes, teacher to studentNot listed on the pricing page
Bring your own weightsCustom Model Import, billed per Custom Model Unit-minuteDeploy open models to endpoints from Model Garden
Classic ML lifecycleIn Amazon SageMaker, a separate serviceBuilt in: Pipelines, Model Registry, Feature Store, Experiments, Model Monitoring
NotebooksVia SageMakerColab Enterprise and Workbench, integrated with BigQuery
Sources: Amazon Bedrock model customization docs and pricing page; Google Cloud Agent Platform pricing page and product page; accessed Nov 10, 2026.

That last row matters for teams with predictive ML as well as generative AI. Google keeps training, pipelines, monitoring and notebooks on one platform, close to BigQuery (product page). On AWS, the same work spans Bedrock and SageMaker. For evaluating either platform's outputs, our LLM-as-a-judge guide covers grader design.

How to choose

Four-step decision flow for choosing between Amazon Bedrock and Gemini Enterprise Agent Platform: required model family, existing cloud, managed features, traffic pattern
A four-step decision flow. Graphic: Metarix, based on AWS and Google Cloud documentation, Nov 10, 2026.

Choose Amazon Bedrock when

  • Your workloads, data in S3 and identity already run on AWS, and you want model calls in CloudTrail under the same IAM roles.
  • You need OpenAI's proprietary GPT models or Amazon Nova through your cloud account.
  • You want built-in contextual grounding or Automated Reasoning checks on model output.
  • You need capacity guarantees on Claude and prefer a token-per-minute Reserved tier to a unit-based commitment.
  • Your agents need ready-made browser, code interpreter, payments and policy services under one AWS bill.

Choose Gemini Enterprise Agent Platform when

  • Your data and analytics live in BigQuery and Cloud Storage, and your team already uses Google Cloud IAM.
  • You want Gemini, or you want to run Gemini and Claude side by side on one bill.
  • Live Google Search or Google Maps grounding is part of the product.
  • You run classic ML too and want pipelines, a feature store and model monitoring on the same platform.
  • You want a cheap safety layer billed per token, with a free monthly allowance.

When either is fine

If Claude or an open-weight model is your main model, and you aren't already committed to one cloud, the token price is identical or close. In that case, decide on the surrounding services and on which cloud's credits and discounts you already have. Teams that need the best price on steady traffic should also compare reserved options, as in our spot vs reserved GPUs guide. For bursty jobs where you want a GPU without a reservation, our serverless GPU inference comparison covers list prices and cold starts.

Verdict

For most teams this isn't a model-quality contest. Claude costs the same on both clouds, both offer 50% batch discounts and a roughly 10% regional premium, and their agent runtimes charge nearly the same per vCPU-hour. The real differences are exclusive models (Gemini on Google; OpenAI GPT and Nova on AWS), how reserved capacity is sold, and how safety checks are billed.

Start with your cloud. Use Amazon Bedrock if you live on AWS or need OpenAI's GPT models in your account. Use Gemini Enterprise Agent Platform if your data is in BigQuery, you want Gemini, or you need Google Search grounding. Then run the same evaluation set on your top two models, at Batch prices where you can, before you sign any capacity commitment.

Sources

Tools covered in this guide

Frequently asked questions

Is Vertex AI still called Vertex AI?
Not officially. On April 22, 2026, Google made Vertex AI part of Gemini Enterprise Agent Platform and renamed most features: Agent Engine became Agent Runtime, Vertex AI Studio became Agent Studio and Vertex AI Search became Agent Search. Model Garden and RAG Engine kept their names without the Vertex AI prefix.
Is Claude cheaper on Amazon Bedrock or Google Cloud?
Neither. As of Nov 11, 2026, Claude's list prices at the global endpoint are the same on both, for example $2 input and $10 output per million tokens for Claude Sonnet 5.5. Regional endpoints cost about 10% more on both clouds.
Can I use Gemini on Amazon Bedrock?
No. Bedrock's catalog includes Google's open Gemma models but not Gemini. Gemini runs on Google's Agent Platform and Google's own Gemini API. Bedrock AgentCore can call Gemini as an external model if you bring your own access.
Does Bedrock or Vertex AI have a batch discount?
Both do. Bedrock prices batch inference 50% below on-demand for select models and also offers a Flex tier at 50% off. Google's Agent Platform lists batch prices at about half of standard, for example Gemini 4 Argon and Gemini 4 Carbon at $2 input and $10 output per million tokens from Dec 1, 2026.
Which is cheaper for AI agents, AgentCore or Agent Runtime?
They are close. AgentCore Runtime lists $0.0895 per vCPU-hour and $0.00945 per GB-hour in us-east-1, while Google's Agent Runtime lists $0.085 per vCPU-hour and $0.009 per GiB-hour. Neither bills idle time between turns. For most agents, model tokens cost far more than hosting.

More in Cloud AI platforms

Share