Skip to content

SageMaker AI bidirectional streaming inference adds usage-based billing

What happened

AI digest

On 11 November 2026, the AWS Machine Learning Blog reported that Amazon SageMaker AI's bidirectional streaming inference now supports usage-based billing. Model providers can report actual usage to AWS Marketplace within the real-time stream over a separate metadata WebSocket connection, enabling billing based on actual consumption. Deepgram is the launch partner, bringing usage-based speech-to-text (STT) and text-to-speech (TTS) services to AWS Marketplace. The report also notes that infrastructure costs for SageMaker AI endpoints continue to be charged as before and are unchanged by the new metering method. The capability is available with the announcement, and no further developments have been reported.

Written by AI from the reports · updated 4 d ago

Timeline

Follow the reports to see the event from each side.

Nov 11
  1. AWS Machine Learning Blog
    Introducing usage-based pricing for Amazon SageMaker AI bidirectional streaming

    AWS Marketplace now supports usage-based metering for Amazon SageMaker bidirectional streaming inference, so model providers can charge for what customers actually consume during a live stream. Deepgram is the launch partner, bringing usage-based speech-to-text and text-to-speech billing to AWS Marketplace.

Heat of this event

Current heat 3·Peak in the comparable range 9(Nov 12 04:00)·Change over 24 hours in the comparable range -50%

02.557.510Nov 1204:00Nov 1218:00Nov 1309:00Nov 1323:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.