Introduction
TwelveLabs is a video intelligence platform. Upload your videos and use the API to search, analyze, generate embeddings, or reason across an entire knowledge store. You can access all capabilities through REST APIs or the Python and Node.js SDKs.
Models or Agents?
TwelveLabs offers two ways to work with your content. Both ingest content the same way; they differ in how you reach an answer.
Call dedicated APIs for individual tasks: search for moments across your videos, analyze a video, or generate embeddings. You call each one and combine the results yourself.
Jockey is a unified agentic system that reasons across your videos and images. Ask it a question, and it plans its own steps, then answers with grounded, cited moments.
Which one fits your task?
Models
- Search for moments across your videos with text or image queries
- Analyze a single video for summaries or answers to your prompts
- Generate vector embeddings for your machine-learning pipeline
- Run each operation yourself
Agents
- Have Jockey reason over a knowledge store
- Ask a question that spans every video and image in the store
- Reason through a complex question that no single search or analysis can answer
- Track a person or object across multiple videos
- Organize or classify a video library by topic
- Build multi-step workflows that return structured JSON output
Need both? Use Models for embeddings and per-video analysis, and Agents for corpus-level reasoning. Both share the same way of ingesting content.
Already using Models? See Migrate from Models to compare the two and move your workflows.