AgentsThe story, in brief

Pay-per-inference for AI agents: How BlockRun and Incarna use Amazon Bedrock AgentCore payments

Incarna's agents now pay BlockRun for inference on demand—spending limits enforced by infrastructure, setup time cut from months to days.

Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

Amazon Bedrock AgentCore Payments operationalizes agent-to-service transactions with built-in spend controls and x402 settlement, lowering the friction for autonomous agents to purchase external compute. This is infrastructure for the agentic economy—agents acquiring resources autonomously rather than pre-provisioning.

The key facts

6 to know
  1. Amazon Bedrock AgentCore Payments enables pay-per-inference billing for agents

  2. Incarna agents pay BlockRun for model inference requests over x402 protocol

  3. Setup time reduced from months to days for payment-enabled agent workflows

  4. Spending limits enforced by infrastructure (not agent-side soft controls)

  5. Case study: production deployment by Incarna and BlockRun

  6. Published: October 8, 2026

Go to the source

AWS Machine Learning Blogaws.amazon.com

Publisher excerpt: Amazon Bedrock AgentCore payments gives AI agents a managed way to pay for services on demand, with spending limits enforced by the infrastructure. See how Incarna's agents pay BlockRun for model inference one request at a time over x402, cutting the work of adding x402 payment support from months…
Read original report
Back to today's editionMore agents news

Keep reading

Related stories

More from Agents