---
title: "Introducing our /parse endpoint 🔥\n\nConvert any document into clean data for AI agents via API.\n\n- T..."
source_name: "Firecrawl(@firecrawl_dev)"
original_url: "https://x.com/firecrawl/status/2049159615703654469"
canonical_url: "https://www.traeai.com/articles/e2be8167-c74c-4c8f-b759-a53f2f20f293"
content_type: "tweet"
language: "中文"
score: 7.2
tags: ["Firecrawl","API","Rust","AI Agent","document parsing"]
published_at: "2026-04-28T16:11:38+00:00"
created_at: "2026-05-02T12:23:30.568566+00:00"
---

# Introducing our /parse endpoint 🔥

Convert any document into clean data for AI agents via API.

- T...

Canonical URL: https://www.traeai.com/articles/e2be8167-c74c-4c8f-b759-a53f2f20f293
Original source: https://x.com/firecrawl/status/2049159615703654469

## Summary

Firecrawl 推出新 /parse API 端点，支持 PDF/DOCX/XLSX 文档解析为 Markdown 或 JSON，保留阅读顺序与表格结构，并提供零数据留存选项，底层由 Rust 实现、性能提升 5 倍。

## Key Takeaways

- /parse 是面向 AI Agent 的文档结构化 API，专注输出干净、可编程的数据格式。
- 支持多格式输入（PDF/DOCX/XLSX）与双模输出（Markdown/JSON），兼顾人读与机读需求。
- Rust 实现的解析器带来 5 倍性能提升，并原生支持 Zero Data Retention 合规能力。

## Content

Title: Firecrawl on X: "Introducing our /parse endpoint 🔥

Convert any document into clean data for AI agents via API.

- Turn PDF, DOCX, and XLSX files into Markdown or JSON
- Preserves reading order and tables
- Zero Data Retention support

All powered by our 5x faster Rust-based parser. https://t.co/VdKSIdUZqc" / X

URL Source: http://x.com/firecrawl/status/2049159615703654469

Markdown Content:
## Post

## Conversation

[![Image 1: Square profile picture](https://pbs.twimg.com/profile_images/2034360486867951616/pa7H6cYB_normal.png)](https://x.com/firecrawl)

[Firecrawl](https://x.com/firecrawl)

[@firecrawl](https://x.com/firecrawl)

Introducing our /parse endpoint ![Image 2: 🔥](https://abs.twimg.com/emoji/v2/svg/1f525.svg) Convert any document into clean data for AI agents via API. - Turn PDF, DOCX, and XLSX files into Markdown or JSON - Preserves reading order and tables - Zero Data Retention support All powered by our 5x faster Rust-based parser.

![Image 3](https://pbs.twimg.com/ext_tw_video_thumb/2049159511772954624/pu/img/eQrRzKEmj8uYsveX.jpg)

[4:11 PM · Apr 28, 2026](https://x.com/firecrawl/status/2049159615703654469)

[146.8K Views](https://x.com/firecrawl/status/2049159615703654469/analytics)