> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/large-language-models/reflection/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Reflection AI

> Browse NeMo AutoModel coverage for Reflection AI large language models.

* [`Beam-1.0-501B-A23B`](/model-coverage/large-language-models/reflection/Beam-1.0-501B-A23B)

> Browse NeMo AutoModel coverage for Reflection AI large language models.

## Docs

- [Beam-1.0-501B-A23B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/large-language-models/reflection/Beam-1.0-501B-A23B.md): Fine-tune Beam-1.0-501B-A23B, Reflection AI's 501B sparse MoE language model, with NeMo AutoModel: a one-node LoRA recipe and an 8-node full-parameter recipe.