> This page is for version v1.3 (default).
> For other versions, use one of these documentation indexes:
> - v1.3 (default): https://docs.twelvelabs.io/v1.3/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.twelvelabs.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.twelvelabs.io/_mcp/server.

# TwelveLabs documentation

> Search, understand, and build with video. Use Jockey from Claude, ChatGPT, or the Agents API. Or build with the Marengo and Pegasus models through the Models API.

TwelveLabs documentation

# Search, understand, and build with video

TwelveLabs finds the exact moments in your videos and answers questions about what happens in it. Use Jockey from Claude, ChatGPT, or the Agents API. Or build with the Marengo and Pegasus models through the Models API.

## Jockey or Models?

Every path below follows the same four steps. Choose Jockey or Models, then choose how you want to use it. Not sure which to choose? See [Choose between Models and Agents](/v1.3/docs/get-started/models-or-agents).

1. 1Set upAdd Jockey to Claude or ChatGPT, sign in, or create an API key
2. 2Add videosUpload your videos
3. 3Ask or runAsk a question or run a task
4. 4Read resultsCited moments, clips, text, or embeddings

Jockey

Ask questions across your videos and receive cited moments. Jockey plans its own steps.

[<path d="M21 12a8 8 0 0 1-11.6 7.1L4 20l1-4.6A8 8 0 1 1 21 12z" /> No code](/v1.3/agents/get-started/start-with-jockey)

Jockey MCP →

Connect Jockey to Claude or ChatGPT, then ask about your videos in plain English.

[<path d="M8 7l-5 5 5 5M16 7l5 5-5 5M13.5 5l-3 14" /> Code](/v1.3/agents/get-started/quickstart)

Agents API →

Create a knowledge store, then create a response or search it from Python or Node.js.

Models

Call Marengo and Pegasus directly to search, analyze, segment, or create embeddings. You choose exactly what runs.

[<rect x="3" y="4" width="18" height="16" rx="3" /><path d="M10 9l6 3-6 3z" /> No code](/v1.3/docs/resources/playground)

Playground →

Try search, analysis, and segmentation on your own videos in the browser.

[<path d="M12 3l9 5-9 5-9-5 9-5zM3 12.5l9 5 9-5M3 17l9 5 9-5" /> Code](/v1.3/docs/get-started/quickstart)

Models API →

Search, analyze, segment, or embed from Python or Node.js.

## Jockey

#### [What is Jockey?](/v1.3/agents/concepts/jockey)

A short explanation of how Jockey reasons across your videos and images.

#### [Start with the Agents API](/v1.3/agents/get-started/quickstart)

Create a knowledge store and ask Jockey questions from your own code.

#### [Recipes](/v1.3/agents/recipes)

Ready-made tasks for your videos, like highlight reels, agentic search, and organizing a video library.

Check your videos in Connect

Claude and ChatGPT only show the chat. Connect shows what Jockey has stored: your knowledge stores, uploads, collections, usage, and billing. Sign in with the account you used to connect Jockey, then open a knowledge store to see your videos and usage.

[Open Connect](https://connect.twelvelabs.io)

## Models

#### [Quickstarts](/v1.3/docs/get-started/quickstart)

Search, analyze, segment, or create embeddings. Choose a task and run it.

#### [Playground](/v1.3/docs/resources/playground)

Try search, analysis, and segmentation on your own videos in the browser before writing code.

#### [Plans and rate limits](/v1.3/docs/get-started/manage-your-plan)

See what your plan includes before you build.

## Reference

#### [Python and Node.js SDKs](/v1.3/sdk-reference/python)

Typed clients with full reference for every endpoint.

#### [API Reference](/v1.3/api-reference/introduction)

Endpoints, authentication, and request and response schemas.

## Learn from real examples

#### [Connect Jockey to Claude or ChatGPT](https://www.twelvelabs.io/blog/how-to-connect-jockey-to-claude-or-chatgpt-a-step-by-step-guide)

No-code guide. Search your videos from the assistant you already use.

#### [Retail CCTV into actionable intelligence](https://www.twelvelabs.io/blog/pegasus-jockey-retail-cctv-intelligence)

Developer tutorial. Build an app on Pegasus and Jockey that turns security camera video into searchable insights.

#### [Automate computer vision data labeling](https://www.twelvelabs.io/blog/how-ai-automates-computer-vision-training-data-labeling)

How AI-first pipelines can reduce annotation timelines from months to days.

#### [Sample apps](/v1.3/docs/resources/sample-applications)

Working projects you can clone and adapt.

## Keep up and get help

#### [Release notes](/v1.3/docs/get-started/release-notes)

See what changed in each release.

#### [Join the community](https://discord.com/invite/Sh6BRfakJa)

Ask questions and share what you are building on Discord.

#### [Migrate or upgrade](/v1.3/docs/get-started/migration-guides)

Move to the latest models and API version.