# Introducing /parse

Upload PDFs, Word docs, and spreadsheets, and /parse turns them into clean Markdown, JSON, or summaries for AI agents and RAG pipelines.

- Published: April 28, 2026

The `/parse` endpoint turns documents into clean, structured data for AI agents and RAG pipelines. Powered by a new Rust-based engine that's up to 5x faster, it works across PDFs, Word docs, spreadsheets, and more.

![/parse Endpoint](/images/blog/parse-endpoint-cover.webp)

### Highlights

* **Clean, LLM-ready output**: Get back Markdown, JSON, or a summary, with tables and reading order preserved. No post-processing required.
* **Rust-based engine**: A high-performance Rust core delivers up to 5x faster parsing, cutting latency in document ingestion and embedding workflows.
* **Zero Data Retention support**: Enterprise plans with ZDR enabled ensure parsed output is never stored, so data from contracts, medical records, and internal reports stays secure.
* **Upload files up to 50 MB**: Supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, and HTML.

View the full documentation [here](https://docs.firecrawl.dev/api-reference/endpoint/parse).

_Canonical HTML: https://www.firecrawl.dev/changelog/parse_

## Site Navigation

### Global Hub
- [Home](/index.md)
- [Pricing](/pricing.md)
- [Blog](/blog.md)
- [Glossary](/glossary.md)
- [Alternatives](/alternatives.md)
- [Tools](/tools.md)
- [Use Cases](/use-cases.md)
- [Integrations](/integrations.md)
- [Changelog](/changelog.md)

### On This Topic
- [Changelog index](/changelog.md)
- [Newer entry: Lockdown Mode](/changelog/lockdown-mode.md)
- [Older entry: Introducing web-agent](/changelog/open-source-agent.md)