FREE TOOL

AgentCore Limits Checker

Describe your agent and see which Amazon Bedrock AgentCore limits it will hit - the 15-minute request timeout, 8-hour sessions, 2 vCPU/8 GB, 100 MB payloads - and what a Runtime session costs in CPU and memory.

  • Your data never leaves your browser: everything is calculated by JavaScript on this page, not on a server.
  • Nothing you enter is uploaded, processed on a server or stored. Check it in your browser's developer tools (Network tab).
  • Once the page has loaded, the tool works without an internet connection.

Start from an example

Each fills in the whole form - then change what differs for your agent.

Deployment

How the agent reaches AgentCore Runtime, and the platform version it runs on - V2 starts from a snapshot and bills memory differently.

Requests

How the agent answers, and its longest and largest request.

Sessions

A session is one conversation's microVM: it lives across requests until it is idle too long or reaches its maximum lifetime.

AgentCore tools it uses

Each has limits of its own.

AgentCore Memory

Cost

How much of a session the agent spends waiting - for the model, a tool or an API. CPU is free while it waits; memory is not.

See the limits ↓
Designing within service quotas and choosing compute are Solutions Architect Associate topicsTry free SAA-C03 practice questions with answers and explanations.SAA-C03 questions →

The AgentCore limits that cannot be raised

Most AgentCore quotas - agents per account, sessions at once, requests per second - can be raised in Service Quotas. The limits below cannot; an agent that needs more has to be built around them. All apply to the default microVMs compute type (as of 2026-09-30):

LimitValue
Synchronous request15 minutes
Streamed response or WebSocket connection60 minutes
Background (asynchronous) task8 hours
Session lifetime (maxLifetime, settable 60 s - 8 h)8 hours
Idle timeout (idleRuntimeSessionTimeout, settable 60 s - 8 h)15 minutes by default
Request or response payload100 MB
Streamed chunk10 MB
WebSocket frame64 KB, 250 frames per second per connection
Hardware per session2 vCPU, 8 GB
Session storage1 GB, about 100,000-200,000 files
Docker image2 GB
ZIP package (direct code deployment)250 MB, 750 MB unzipped
Environment variables4 KB on V1; 2.5 KB (container) or 1.5 KB (ZIP) on V2 for now
V2: healthy /ping after start120 seconds
Memory: message / event / messages per event100 KB / 10 MB / 100
Memory: CreateEvent per actor and session5 per second (10 without conversational payloads)
Memory: event expiry / strategies per memory7-365 days / 6
Code Interpreter: session hardware / disk2 vCPU, 8 GB / 10 GB
Code Interpreter: synchronous call / asynchronous command15 minutes / 8 hours
Browser: session hardware / disk1 vCPU, 4 GB / 10 GB
Browser: automation streams per session1

When a timeout ends a session, the next request with the same session ID gets a new microVM: nothing from the old one's memory or disk is left. Keep a conversation in AgentCore Memory or S3, not in the process. The AgentCore Error Decoder reads the errors these limits produce.

CPU vs memory billing

AgentCore Runtime bills per second, for CPU and memory separately, and the two are counted differently:

  • CPU only while it works. Time spent waiting for the model's response, a tool, an API or a database - I/O wait - is free, as long as no background process keeps running.
  • Memory for every second the session exists, at the peak reached so far, from the microVM's start through idle periods until the session ends - which is after the idle timeout, 15 minutes after the last response by default. The minimum is 128 MB.

An agent mostly waits for its model, so CPU is a small part of the bill and memory held through pauses and the idle timeout a large one. The platform version decides how much of it stays: V1 ($0.0895 per vCPU-hour, $0.00945 per GB-hour) keeps memory until the session ends; V2 ($0.1276 and $0.0169) reclaims memory the agent has not used for 120 seconds. AWS's own example - a 10-minute session on V2, waiting 90% of the time on 1 vCPU - costs $0.002127 of CPU and $0.004576 of memory. On V1 a shorter idle timeout (idleRuntimeSessionTimeout) and a smaller memory footprint lower the bill most; a long idle timeout kept for users who pause costs its memory in every session. Browser and Code Interpreter sessions are billed the same way, at V1's rates.

Ways around each limit

  • Longer than 15 minutes: stream the response (up to 60 minutes), or answer at once and keep working in the background - the session reports HealthyBusy on /ping while it works, for up to 8 hours.
  • Longer than 8 hours, more than 2 vCPU or 8 GB, or a GPU: the Instances compute type runs a session on an EC2 instance of the type you choose, in your account, for up to 14 days. It is chosen when the runtime is created and cannot be changed later.
  • Payloads over 100 MB and files over 1 GB: put the data in S3 and pass its key; the agent reads it with its execution role.
  • Users who pause longer than the idle timeout: raise idleRuntimeSessionTimeout (up to 8 hours), or let the session end and load the conversation from AgentCore Memory when the next one starts - the cheaper choice when pauses are long.
  • More than one automation client on a browser: start a Browser session per client.

Frequently asked questions

Is what I enter sent anywhere?

No. The check runs in your browser. The page only counts that the checker was used, with which kind of response and which first limit hit, never the numbers.

Which limits can I raise?

Those marked "adjustable" in AWS's quota tables, through Service Quotas or AWS Support: active sessions (5,000 in US East (N. Virginia) and US West (Oregon), 2,500 elsewhere), 25 new sessions per second, 1,000 data plane requests per second, agents, versions and endpoints per account, and every Gateway quota. The limits on this page marked "cannot be raised" are fixed.

Should I use V1 or V2?

V2 starts every session from a snapshot, so cold starts stay about two seconds whatever the image size (P75 in AWS's tests with images of 200 MB to 2 GB), and it bills the memory the agent actually uses, at a higher rate. It is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Ireland) and Asia Pacific (Tokyo); CloudFormation and the CDK cannot set it yet, and a V2 runtime takes minutes to create or update. V1 stays the default when platformVersion is left out.

Does the estimate include the model's tokens?

No - only the Runtime session. The model calls are billed by Amazon Bedrock per token; the Bedrock Throttling Calculator shows whether your agent's requests fit the model's quotas.

References

Quotas for Amazon Bedrock AgentCore
AgentCore Runtime microVMs and platform versions
Configure AgentCore lifecycle settings
AgentCore Runtime Instances
Amazon Bedrock AgentCore pricing