What it is
ReaderLM v2 is an advanced API designed to convert raw HTML into well-structured markdown or JSON, leveraging two new small language models for enhanced accuracy and context handling. It allows users to easily transform webpages into formats suitable for large language models by using a simple URL prefix.
Gabriel’s notes
an API that transforms any webpage into LLM-friendly markdown by simply adding r.jina.ai as a URL prefix. In September 2024, we launched two small language models, reader-lm-0.5b and reader-lm-1.5b, specifically designed to convert raw HTML into clean markdown. Today, we’re excited to introduce ReaderLM’s second generation, a 1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON with superior accuracy and improved longer context handling. ReaderLM-v2 handles up to 512K tokens combined input and output length.
Good fit if you want to:
- generate, edit, or enhance creative assets (images, design, branding).
- build, test, or ship software faster (APIs, dev tooling, code assistance).
Pricing snapshot (auto-enriched): No free tier mentioned; usage-based pricing with charges based on consumption; additional AWS infrastructure costs may apply; subscriptions can be canceled anytime.
Work-use / compliance snapshot (auto-enriched): ReaderLM v2 by Jina AI is suitable for workplace use, offering secure data handling with SOC 2 Type 1 and Type 2 compliance, strong encryption, role-based access controls, and customer data isolation, though specific details on training data retention and SSO availability are not explicitly stated.
Alternatives (auto-enriched): Alternative: Qwen2.5-32B-Instruct | Comparison: Qwen2.5-32B-Instruct is a larger model that offers comparable HTML-to-JSON extraction but is less efficient than ReaderLM v2 for HTML-to-Markdown conversion due to its size.
Reading tip: skim headings first, then focus on the sections that match your current project or question.
Author: Jina AI
Note: pricing and policy details can change—verify on the official site before making decisions.