> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.twelvelabs.io/v1.3/docs/concepts/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.twelvelabs.io/_mcp/server.

# Concepts

## Docs

- [Models](https://docs.twelvelabs.io/docs/concepts/models.md): Use Marengo for embeddings, and Pegasus for text generation.
- [Marengo](https://docs.twelvelabs.io/docs/concepts/models/marengo.md): Marengo is an embedding model. It analyzes visual, audio, and text information.
- [Marengo 3.5](https://docs.twelvelabs.io/docs/concepts/models/marengo/marengo-3-5.md): Marengo 3.5 is an embedding model. It analyzes video, audio, images, and documents.
- [Marengo 3.0](https://docs.twelvelabs.io/docs/concepts/models/marengo/marengo-3-0.md): Marengo 3.0 is an embedding model. It analyzes visual, audio, and text information.
- [Pegasus](https://docs.twelvelabs.io/docs/concepts/models/pegasus.md): Pegasus is a generative model. It analyzes multiple modalities to generate contextually relevant text.
- [Pegasus 1.6](https://docs.twelvelabs.io/docs/concepts/models/pegasus/pegasus-1-6.md): Pegasus 1.6 is a generative model. It analyzes videos or images to generate contextually relevant text. New capabilities include egocentric video understanding, image analysis, improved entity recognition, improved metadata extraction, in-segment events, and segmentation without a token limit.
- [Pegasus 1.5](https://docs.twelvelabs.io/docs/concepts/models/pegasus/pegasus-1-5.md): Pegasus 1.5 is a generative model. It analyzes multiple modalities to generate contextually relevant text.
- [Upload and processing methods](https://docs.twelvelabs.io/docs/concepts/upload-methods.md): Learn how to upload or import content and choose the processing mode based on content duration.
- [Indexes](https://docs.twelvelabs.io/docs/concepts/indexes.md): Use indexes to group related videos.
- [Modalities](https://docs.twelvelabs.io/docs/concepts/modalities.md): Understand how the platform analyzes your video content.
- [Multimodal large language models](https://docs.twelvelabs.io/docs/concepts/multimodal-large-language-models.md): Understand how multimodal large language models understand videos by combining visual, audio, and text information.