TwelveLabs Pegasus 1.5 model now available on Amazon Bedrock

Amazon Bedrock Updates
Amazon Bedrock now supports TwelveLabs Pegasus 1.5, a video-to-text model that generates structured, time-coded metadata from video. This feature allows you to query large video libraries by defining business-relevant moments, such as editorial segments, speaker changes, sports plays, or brand appearances, and retrieving them with timestamps.
Pegasus 1.5 analyzes video content in a single pass, without requiring pre-indexing or an ingestion pipeline. It is accessible through the US and Global cross-Region inference profiles.
What to do
- Visit the Amazon Bedrock product page to learn more.
- Access the model in the Amazon Bedrock console.
- Refer to the Amazon Bedrock documentation for supported Regions, APIs, features, and pricing.
Source: AWS release notes
If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.



