AI Potluck
Contribute
Back to Gap Map Product / UX / Search & retrieval

Jina Reader

Jina AI
open core / Overall score: 3.4

Jina Reader is a service and open-source codebase that converts a web page into markdown for language models when a URL is prefixed with r.jina.ai. It reads HTML, PDF and Microsoft Office documents and captions images. A companion endpoint, s.jina.ai, searches the web and returns the results as markdown.

Openness

4 high confidence
4.0
license
Apache-2.0(OSI)
source
public(TypeScript, stateless mode self-hostable via Docker)
core features withheld
yes — ReaderLM-v2 and jina-vlm, the models behind image captioning and the readerlm-v2 output, are CC-BY-NC 4.0
managed-tier
r.jina.ai/s.jina.ai hosted SaaS (free tier + paid API key)

Jina Reader's service code is Apache-2.0 and self-hostable in a stateless Docker mode, but the models it uses for image captioning and its ReaderLM output, ReaderLM-v2 and jina-vlm, are licensed for non-commercial use only. Commercial use of those features needs the Jina On-Prem license Elastic sells, so part of the product sits outside the open build.

  • https://github.com/jina-ai/reader recorded 2026-06-04

    Apache-2.0 license, public source, self-host Docker instructions, ~11k stars

  • https://jina.ai/reader recorded 2026-09-28

    The FAQ answers "Is the Reader API open source?" with "The Reader service code is available on the Jina AI GitHub organization." and says "The models used by Reader, including" ReaderLM-v2 and jina-vlm, "are licensed CC-BY-NC 4.0, which is not an open-source license", so "commercial production use requires a commercial license", the Jina On-Prem license Elastic sells.

  • https://raw.githubusercontent.com/jina-ai/reader/main/LICENSE recorded 2026-09-28

    Apache License

  • https://raw.githubusercontent.com/jina-ai/reader/main/README.md recorded 2026-09-28

    This repository is the open source branch of the codebase behind `https://r.jina.ai` and `https://s.jina.ai`. It runs in stateless or bucket-cached mode; the MongoDB-backed SaaS storage layer is not included here.

Adoption

3 low confidence
3.0

Jina Reader publishes no download, request or user count, and because it is consumed as a URL prefix rather than installed as a package, there is no registry to measure it either. GitHub stars are the only available signal, but a star is not a use, and the hosted endpoint's own traffic is not published anywhere.

  • https://github.com/jina-ai/reader recorded 2026-08-13

    Repo page, 11,865 stargazers, Apache-2.0, "Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/". No download, request or user figure.

Capability

4 medium confidence
4.0

Jina Reader's core interface, `r.jina.ai/<url>`, only converts a named URL to markdown; on its own that covers content extraction, not discovery. But the vendor also documents `s.jina.ai/<query>`, which searches the web, and using the two together, search then read, puts Jina Reader level with Firecrawl, which sells the same find-plus-content combination in one product.

Verified 2026-09-17