The agent layer for
video understanding

Search

Find any moment by meaning.

Search across every video and photo in your library. No tags, no filenames, just what you’re looking for.

Search

Find any moment by meaning.

Search across every video and photo in your library. No tags, no filenames, just what you’re looking for.

Phrase

Image

Clip

Person

Place

Action

Understand

Know what happens inside your media.

Jockey reads each clip and explains what’s there, scene by scene, moment by moment.

Understand

Know what happens inside your media.

Jockey reads each clip and explains what’s there, scene by scene, moment by moment.

Scenes

Context

Captions

Topics

Sentiment

Key moments

Organize

Group videos and photos automatically.

Footage sorts itself into meaningful sets. No manual foldering, no naming conventions.

Organize

Group videos and photos automatically.

Footage sorts itself into meaningful sets. No manual foldering, no naming conventions.

Person

Place

Topic

Event

Character

Project

Assemble

Turn input into usable media.

Ask, and Jockey assembles finished media straight from your source footage. Refine it, trim it and export it as an MP4.

Assemble

Turn input into usable media.

Ask, and Jockey assembles finished media straight from your source footage. Refine it, trim it and export it as an MP4.

Clips

Collections

Timelines

Sequences

Roadmaps

Highlights

Works in

Claude

ChatGPT

Works in

Claude

ChatGPT

Creators & Editors

Your whole archive,
on tap.

Talk to your footage in the assistant you already use. Describe any moment and Jockey finds the exact clip, quote, or cut.

Search How You Think

Describe a moment in plain language and Jockey finds the exact clip, not the folder.

Find Any Quote

Search everything you've ever said on camera and jump straight to the line.

Instant Highlight Reels

Point Jockey at a topic and get an edit-ready cut of your best moments back.

Marketing Teams

Know every ad you’ve ever run.

The same intelligence, pointed at your creative library.

Automatic Ad Tagging

Every ad watched and labeled by hook, talent, format, and tone the moment it lands.

Winning Hook Detection

See which opening three seconds actually hold attention across your whole library.

Talent & Logo Recognition

Find every ad a creator, spokesperson, or brand mark appears in, without opening a file.

Format & Trend Breakdown

Compare performance across formats and spot the pattern before your next shoot.

Social & Trend Intelligence

See what's rising on YouTube, TikTok and Instagram Reels for your brief, from a social corpus we keep current.

Performance Insights

Every ad lands with its transcript, creator, views, and engagement, so you can rank by what performed.

Concept Video Previews

Turn a campaign direction into a playable 15–30s concept video, then save, share, or revoke it.

In production

Teams are already querying their video.

Marketers, creators, and builders running libraries through Jockey from ad tagging to streamlined creative workflows.

Kyle Chalmers

Content Creator,

KC AI Labs

“I pointed it at my catalog and let it watch every video.”

Jordaaan Hill

Founder,

Organized AI

“About 400 short-form videos, all within 14 hours. Without Jockey, that would have taken weeks.”

Nick Gebben

Professional Editor

“It pulls the exact clip with the timestamp instantly.”

MCP Integration

How to Get Started with Jockey

MCP Integration

How to Get Started with Jockey

MCP Integration

How to Get Started with Jockey

Models

Building your own? Here’s what’s underneath.

Marengo
Marengo

Finds it

Pegasus
Pegasus

Understands it

Jockey
Jockey

Acts on it

Marengo
Marengo

Finds it

Pegasus
Pegasus

Understands it

Jockey
Jockey

Acts on it

Marengo

Indexes media by meaning.

Indexes media by meaning.

Pegasus

Understands media in natural language.

Understands media in natural language.

Jockey

Orchestrates the workflow across the library.

Orchestrates the workflow across the library.

Developers

Video understanding, as an API.

Search, extract and embed what's inside your users' footage.

Search, extract and embed what's inside your users' footage.

Multimodal Embeddings

One embedding across video, image, audio, and text to power your own retrieval and ranking.

Natural-Language Search

Ship a search bar that understands what's in your users' videos, not just the filenames.

Structured Data Extraction

Define a JSON schema and get back timestamped, machine-readable metadata for every video.

Frame-Accurate Timestamps

Every result maps back to the exact moment, so you can deep-link straight into playback.

API & SDK

Bring Jockey into your own product.

Python
Node.js
1from twelvelabs import TwelveLabs, ResponseInputItem
2 
3client = TwelveLabs(api_key="<YOUR_API_KEY>")
4 
5response = client.responses.create(
6 knowledge_store_id="<YOUR_KNOWLEDGE_STORE_ID>",
7 session_id="<YOUR_SESSION_ID>",
8 input=[
9 ResponseInputItem(
10 type="message",
11 role="user",
12 content="Now list the three most important moments as bullet points.",
13 )
14 ],
15)
Python
Node.js
1from twelvelabs import TwelveLabs, ResponseInputItem
2 
3client = TwelveLabs(api_key="<YOUR_API_KEY>")
4 
5response = client.responses.create(
6 knowledge_store_id="<YOUR_KNOWLEDGE_STORE_ID>",
7 session_id="<YOUR_SESSION_ID>",
8 input=[
9 ResponseInputItem(
10 type="message",
11 role="user",
12 content="Now list the three most important moments as bullet points.",
13 )
14 ],
15)
Python
Node.js
1from twelvelabs import TwelveLabs, ResponseInputItem
2 
3client = TwelveLabs(api_key="<YOUR_API_KEY>")
4 
5response = client.responses.create(
6 knowledge_store_id="<YOUR_KNOWLEDGE_STORE_ID>",
7 session_id="<YOUR_SESSION_ID>",
8 input=[
9 ResponseInputItem(
10 type="message",
11 role="user",
12 content="Now list the three most important moments as bullet points.",
13 )
14 ],
15)

Pricing

Start free. Choose a plan as you grow.

Every plan includes storage, media processing, and access to TwelveLabs APIs. Choose based on your media volume and monthly usage.

Free

Explore and test our APIs

$0

/yr

3 GB

Basic

Rate limits

Basic

Environment

Shared

Overage

SSO/SAML

Plus

Recommended

Build with more storage and usage

$290

/yr

50 GB

Medium

Rate limits

High

Environment

Shared

Overage

SSO/SAML

Pro

Scale with growing usage

$990

/yr

200 GB

High

Rate limits

High

Environment

Shared

Overage

Optional

SSO/SAML

Enterprise

Organizations with custom needs

Custom

Custom

Custom

Rate limits

Custom

Environment

Dedicated

Overage

By agreement

SSO/SAML

Included

Pricing

Start free. Choose a plan as you grow.

Every plan includes storage, media processing, and access to TwelveLabs APIs. Choose based on your media volume and monthly usage.

Free

Explore and test our APIs

$0

/yr

3 GB

Basic

Rate limits

Basic

Environment

Shared

Overage

SSO/SAML

Plus

Recommended

Build with more storage and usage

$290

/yr

50 GB

Medium

Rate limits

High

Environment

Shared

Overage

SSO/SAML

Pro

Scale with growing usage

$990

/yr

200 GB

High

Rate limits

High

Environment

Shared

Overage

Optional

SSO/SAML

Enterprise

Organizations with custom needs

Custom

Custom

Custom

Rate limits

Custom

Environment

Dedicated

Overage

By agreement

SSO/SAML

Included

Pricing

Start free. Choose a plan as you grow.

Every plan includes storage, media processing, and access to TwelveLabs APIs. Choose based on your media volume and monthly usage.

Free

Explore and test our APIs

$0

/yr

3 GB

Basic

Rate limits

Basic

Environment

Shared

Overage

SSO/SAML

Plus

Recommended

Build with more storage and usage

$290

/yr

50 GB

Medium

Rate limits

High

Environment

Shared

Overage

SSO/SAML

Pro

Scale with growing usage

$990

/yr

200 GB

High

Rate limits

High

Environment

Shared

Overage

Optional

SSO/SAML

Enterprise

Organizations with custom needs

Custom

Custom

Custom

Rate limits

Custom

Environment

Dedicated

Overage

By agreement

SSO/SAML

Included

FAQ

Common questions

Yes. When you delete your library or account, we permanently remove your original files, the generated index, associated metadata, and your usage history. You can manage deletions directly from your account settings.
Jockey supports standard video (MP4, MOV, AVI, MKV, WebM) and photo (JPEG, PNG, HEIC, HEIF, WebP, BMP, GIF) formats. Please refer to the documentation for specific storage and per-file size limits.
Jockey uses multimodal AI, analyzing visual, motion, and contextual cues, to group people across your library, rather than relying on traditional facial recognition. We do not build biometric databases, compare your data against external records, or share identity information between accounts.