Bedrock AgentCore Pricing Calculator
Estimate AgentCore Runtime, Memory, Gateway, and Browser charges alongside model inference — budget production agents before autonomous tool access scales.
- No signup
- Instant results
- ~3 min
Rates reviewed
AgentCore components
us-east-1list rates, pricing as of 2026-07-04. Model inference billed separately. Active CPU/memory only — I/O wait not charged. Source: AWS public pricing.
Runtime sessions
Active CPU time only — LLM I/O wait is not billed.
128 MB minimum memory charge applies.
Gateway, Memory, Browser, Code Interpreter
$0.005 per 1,000 invocations.
$0.025 per 1,000 searches.
$0.02 per 100 tools/month.
Estimated AgentCore Platform Cost
Platform fees excluding model inference
Total Monthly Cost
live resultPlatform vs inference split unlocks after email
Unlock platform vs inference budget guidance
See memory retention tips and link to Bedrock token pricing for full agent TCO.
Full breakdown unlocked
TCO guidance is now visible.
Want this applied to your real account?
FactualMinds designs production Bedrock Agents with AgentCore — guardrails, IAM tool boundaries, and cost-aware model routing.
Talk to GenAI Experts →Who This Tool Is For
AI platform teams, CTOs, and architects budgeting production agents with autonomous tool access — beyond token inference alone.
Why We Built This Tool
AgentCore bills Runtime, Gateway, and Memory separately from Bedrock model tokens — agents that call tools frequently can accumulate platform fees before inference dominates.
What Problem It Solves
- Platform vs inference split. Budget AgentCore Runtime and Gateway alongside token costs.
- Memory retention. Long-term memory events and retrievals add recurring platform charges.
- Tool fan-out. Gateway invocations scale with every tool call an agent makes.
Pair with our Bedrock Pricing Calculator, GenAI Readiness Assessment, or Generative AI on AWS service.
Frequently Asked Questions
How is AgentCore Runtime priced?
Runtime charges $0.0895 per vCPU-hour and $0.00945 per GB-hour based on active consumption. I/O wait during LLM or tool calls is not billed as CPU time — only actual processing seconds count.
Is AgentCore separate from Bedrock model inference?
Yes. AgentCore covers the agent platform (Runtime, Gateway, Memory, Browser, Code Interpreter). Bedrock foundation model token costs are billed separately — use our Bedrock pricing calculator for inference.
What does AgentCore Gateway cost?
Gateway charges $0.005 per 1,000 API invocations, $0.025 per 1,000 semantic searches, and $0.02 per 100 tools indexed per month. Busy agents making hundreds of tool calls per session accumulate Gateway fees quickly.
How does Memory billing work?
Memory bills short-term events at $0.25 per 1,000 events, long-term storage at $0.75 per 1,000 events per month, and retrievals at $0.50 per 1,000 retrievals. Trim retention for stateless agents.
When does platform cost exceed inference?
At low token volumes with heavy tool use, Gateway and Memory can dominate. At high inference volumes, model tokens typically remain the largest line item — this calculator shows the platform portion only.
How accurate is this estimate?
Rates are AWS us-east-1 list prices as of 2026-07-04. AgentCore is actively evolving — verify current rates on the AgentCore pricing page before production budgeting.