Pegasus 1.5
Turn 2-hour videos into structured JSON metadata with a single API call
The Panel's Take
Pegasus 1.5 is TwelveLabs' latest video understanding API, capable of processing raw video up to 2 hours long and returning consistent, timestamped, structured metadata in a single API call. Developers define a custom schema — 'detect product mentions with timestamps, speaker identity, and sentiment' — and receive agent-ready JSON matching that schema regardless of video length or content type. The model also supports reference image uploads, letting users locate specific visual moments across hours of footage (e.g., 'find every frame where this person appears' or 'detect all instances of this product on screen'). The structured output format is designed to feed directly into downstream agents and databases without additional parsing layers. Video-to-structured-metadata at this duration and via developer-defined schemas is a new primitive for the AI stack. Media companies cataloging archives, sports analytics teams tagging game footage, surveillance platforms detecting events, and AI agents that need to 'watch' user-provided content all have immediate use cases that weren't economically viable before.
Share this verdict
Pegasus 1.5 verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/pegasus-15-twelvelabs-2hr-video-structured-metadata-schema-api-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Pegasus 1.5 with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/pegasus-15-twelvelabs-2hr-video-structured-metadata-schema-api-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/pegasus-15-twelvelabs-2hr-video-structured-metadata-schema-api-2026" alt="Pegasus 1.5 Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/pegasus-15-twelvelabs-2hr-video-structured-metadata-schema-api-2026)<iframe src="https://shiporskip.io/embed/pegasus-15-twelvelabs-2hr-video-structured-metadata-schema-api-2026" title="Pegasus 1.5 ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“The schema-defined output is the killer feature — instead of getting a blob of unstructured transcript, you get exactly the JSON shape your database or downstream agent expects. For anything involving long video content (meetings, interviews, lectures, games), this is genuinely infrastructure-level useful.”
“Video AI APIs have a history of impressive demos and disappointing production accuracy, especially on noisy audio or fast-cutting video. TwelveLabs hasn't published precision/recall benchmarks for the schema extraction task, and enterprise pricing for 2-hour video processing could be prohibitive for smaller teams — check costs before building a pipeline on this.”
“Structured video metadata is a foundational layer for the agent economy. Right now, 99% of the world's video content is dark to AI agents — unsearchable, unactionable. APIs like Pegasus 1.5 are the indexing layer that turns passive archives into queryable knowledge. This is infrastructure for the next decade.”
“For video creators and post-production teams, auto-generating searchable metadata across an entire archive — without manually tagging or transcribing — is a genuine time save. The reference image feature for locating specific visual moments is particularly useful for brand safety review and highlight reel creation.”