← Back
AWS ML Blog

Cost attribution and controls for AI developer and productivity tools on Amazon Bedrock

•14 min read•
#bedrock#amazon#inference
Level:Advanced
For:ML Engineers, Cloud Architects, DevOps
✦TL;DR

Amazon Bedrock now offers zero‑instrumentation cost attribution that automatically ties every inference call back to the IAM principal that initiated it. By leveraging IAM Identity Center, session tags, and CUR 2.0, the post demonstrates how to slice Bedrock spend per user for AI developer and productivity tools. The approach eliminates manual tagging and provides fine‑grained billing visibility without adding overhead to inference pipelines. This enables teams to enforce cost controls and audit usage at the individual level in real time.

⚡ Key Takeaways

  • Bedrock’s built‑in cost attribution records each inference call with the caller’s IAM principal ID, eliminating the need for custom instrumentation.
  • IAM Identity Center session tags are propagated to Bedrock requests, allowing downstream CUR 2.0 to map usage to specific users or projects.
  • CUR 2.0’s enhanced cost allocation fields expose Bedrock usage per principal, enabling cost allocation at the granularity of individual developers or service accounts.
  • Integrating Bedrock with IAM Identity Center and CUR 2.0 requires adding a session tag (e.g., `User=alice`) during the IAM Identity Center login flow and enabling the `bedrock:InvokeModel` permission for that principal.
  • This solution presumes that the account has CUR 2.0 enabled and that the Bedrock service is accessed through the AWS SDK or CLI, which automatically forwards session tags.
  • WhyItMatters: For teams shipping AI services on Bedrock, this mechanism provides instant, accurate per‑user cost visibility, simplifying budgeting, compliance, and automated cost‑control policies in production environments.
  • TechnicalLevel: Advanced
  • TargetAudience: ML Engineers, Cloud Architects, DevOps
  • PracticalSteps:
  • In IAM Identity Center, create a session tag key (e.g.,
💡 Why It Matters

For teams shipping AI services on Bedrock, this mechanism provides instant, accurate per‑user cost visibility, simplifying budgeting, compliance, and automated cost‑control policies in production environments.

✅ Practical Steps

  1. In IAM Identity Center, create a session tag key (e.g.,

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod

AWS ML Blog•#deployment

Helping AI text detectors keep up with changing conditions

MIT News AI•#llm

Hugging Face and OpenRouter join forces to make open-weight models easy to run

Hugging Face Blog•#inference

Activation and Floating-Point Quantization

Machine Learning Mastery•#inference

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING