Skip to content
AI ConnectPowered by VELENTIS
AI-generated1 min

TwelveLabs Pegasus 1.5 Video Model Arrives on Amazon Bedrock

TwelveLabs has launched its Pegasus 1.5 video language model on Amazon Bedrock, allowing developers to process up to two hours of video into structured JSON metadata.

This article was AI-generated and published automatically. Context, labelling and all sources at the end of the article.

(KI-generiertes Symbolbild: Gemini / AI Connect)

Amazon Bedrock has expanded its available offerings with TwelveLabs Pegasus 1.5. The system operates as a video language model designed to convert long-form video recordings into structured, timestamped metadata. By specifying targeted events, users can define key points of interest and receive matching video segments formatted directly as JSON.

The deployment incorporates several key capabilities, including new video segmentation alongside multimodal prompting that accepts reference images. Additionally, the system provides on-the-fly processing for recordings reaching up to two hours in length. These tools enable users to query long-form media streams and extract granular segment information directly inside the cloud environment.

What this means for you

For businesses working with extensive media archives, integrating Pegasus 1.5 into Amazon Bedrock simplifies the pipeline required to index and search footage. Native JSON output and reference image prompting reduce custom software overhead for scene discovery. As a result, technical teams can automate video search and cataloging within their existing cloud footprint.

Evidence

Solidly sourced
46/100

  • TwelveLabs Pegasus 1.5 has become available to customers on Amazon Bedrock.

    single source
    Quote

    „TwelveLabs Pegasus 1.5 is now available in Amazon Bedrock.“

    AWS, Machine Learning

  • Pegasus 1.5 transforms extended video content into structured metadata containing timestamps.

    single source
    Quote

    „The video language model turns long-form video into structured, timestamped metadata“

    AWS, Machine Learning

  • Users can outline relevant moments to retrieve matching video clips returned in JSON format.

    single source
    Quote

    „define the moments that matter and get every matching segment back as JSON“

    AWS, Machine Learning

  • The model introduces new segmentation features and supports multimodal prompts with reference images.

    single source
    Quote

    „with new video segmentation, multimodal prompting with reference images“

    AWS, Machine Learning

  • The system supports immediate processing for video assets up to two hours long.

    single source
    Quote

    „on-the-fly processing of up to two hours of video.“

    AWS, Machine Learning

Sources

The evidence score is computed, not hand-set: from confidence, the number of sources and the share of verified statements.

Source & transparency

As of: October 19, 2026

AI-generatedAI-generated: produced automatically from vetted sources with technical quality checks (source, quote and figure verification); no human sign-off of each item before publication

Sources
1
Verified statements
0 / 5
Evidence score
46Solidly sourced
Generative AIUse Cases

Want to put this into practice?

We connect you with suitable AI providers from the DACH region, free of charge and without obligation.

What's next?

What does AI really cost?

Honest price ranges for your project, independent, with nothing to sell you.

See prices

Get your team ready (AI Act)

The EU AI Act requires providers and deployers to take measures supporting AI literacy in the team — not a specific level. Baseline training for your team is in development.

Find the right training

Find the right provider

Describe your project. We connect you with suitable providers at a fair price.

Start the analysis
Back to AI Radar