> 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/vision-language-models/stepfun-ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# StepFun AI

> Browse NeMo AutoModel coverage for StepFun AI vision language models.

* [`Step-3.7-Flash`](/model-coverage/vision-language-models/stepfun-ai/Step-3.7-Flash)
* [`Step-5-Preview`](/model-coverage/vision-language-models/stepfun-ai/Step-5-Preview)

> Browse NeMo AutoModel coverage for StepFun AI vision language models.

## Docs

- [Step-3.7-Flash](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/stepfun-ai/Step-3.7-Flash.md): Fine-tune Step-3.7-Flash on MedPix with full or LoRA vision-language recipes in NeMo AutoModel for supervised image-text training.
- [Step-5-Preview](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/vision-language-models/stepfun-ai/Step-5-Preview.md): Step-5-Preview vision-language architecture, packed context-parallel inputs, and current preprocessing scope in NeMo AutoModel.