---
title: "Amazon SageMaker AI Async Inference now supports inline request payloads"
slug: "amazon-sagemaker-ai-async-inference-now-supports-inline-request-payloads"
date: 2026-06-17
category: tech-pub
tags: [amazon]
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/amazon-sagemaker-ai-async-inference-now-supports-inline-request-payloads
---

# Amazon SageMaker AI Async Inference now supports inline request payloads

**Published**: 2026-06-17 | **Category**: tech-pub | **Sources**: 1

---

## TL;DR

- Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync.

---

## Summary

- Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync. For inputs up to 128,000 bytes, customers no longer need to upload data to Amazon S3 before every invocation.
- That makes small async workloads cleaner: one API call instead of S3 upload code, an input bucket, S3 write permissions, UUID key handling, and stale-object cleanup.
- S3 output behavior does not change. Body and InputLocation are mutually exclusive, and size or parameter violations return synchronous ValidationError responses.
- For images, audio, large documents, or audit and replay needs, the S3 input path still fits better. AWS says the feature is available in 31 commercial regions, including Frankfurt and Zurich.

---

## Why it matters

Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync. For inputs up to 128,000 bytes, customers no longer need to upload data to Amazon S3 before every invocation.

---

## Key Points

- Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync. For inputs up to 128,000 bytes, customers no longer need to upload data to Amazon S3 before every invocation.
- That makes small async workloads cleaner: one API call instead of S3 upload code, an input bucket, S3 write permissions, UUID key handling, and stale-object cleanup.
- S3 output behavior does not change. Body and InputLocation are mutually exclusive, and size or parameter violations return synchronous ValidationError responses.
- For images, audio, large documents, or audit and replay needs, the S3 input path still fits better. AWS says the feature is available in 31 commercial regions, including Frankfurt and Zurich.

---

## Nauti's Take

AWS frames this as a convenience feature, and that is exactly what it is: small, technical, but genuinely useful in day-to-day infrastructure work. Anyone who has built Async Inference pipelines around tiny JSON requests knows the odd detour through S3. Still, teams should not blindly move everything inline. For traceable inputs, larger data, or later replay, S3 remains the cleaner path.

---


## FAQ

**Q:** What is Amazon SageMaker AI Async Inference now supports inline request payloads about?

**A:** - Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync.

**Q:** Why does it matter?

**A:** Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync. For inputs up to 128,000 bytes, customers no longer need to upload data to Amazon S3 before every invocation.

**Q:** What are the key takeaways?

**A:** Amazon SageMaker AI Async Inference now accepts inline payloads in the Body field of InvokeEndpointAsync. For inputs up to 128,000 bytes, customers no longer need to upload data to Amazon S3 before every invocation.. That makes small async workloads cleaner: one API call instead of S3 upload code, an input bucket, S3 write permissions, UUID key handling, and stale-object cleanup.. S3 output behavior does not change. Body and InputLocation are mutually exclusive, and size or parameter violations return synchronous ValidationError responses.

---

## Related Topics

- [amazon](https://news.ainauten.com/en/tag/amazon)

---

## Sources

- [Amazon SageMaker AI Async Inference now supports inline request payloads](https://aws.amazon.com/blogs/machine-learning/amazon-sagemaker-ai-async-inference-now-supports-inline-request-payloads/) - AWS Machine Learning Blog

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-06-18*