Who is Qianfan OCR for?

Qianfan OCR is an open-source project built for developers.

What platforms does Qianfan OCR run on?

Qianfan OCR runs on the web, the command line, and API.

Is Qianfan OCR still active?

Unverified. Qianfan OCR has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.

Who makes Qianfan OCR?

Qianfan OCR is developed by Baidu, based in China.

When did Qianfan OCR launch?

Qianfan OCR first shipped in 2025.

Is Qianfan OCR open source?

Qianfan OCR has a public GitHub repository.

Back to the index

Qianfan OCR

Name: Qianfan OCR
Author: Baidu

huggingface.coInfrastructure🇨🇳

baidu/Qianfan-OCR is a vision-language model from Baidu's Qianfan platform designed for optical character recognition and document understanding tasks. It accepts image inputs and produces structured text output, supporting both English and Chinese content. The model is hosted on Hugging Face and can be used via the Transformers library or Baidu's inference services.

MITWebCLIAPI

Visit huggingface.co

421stars

28forks

1alternative

3features

2025since

Overview

3 features

Qianfan OCR sits in PulseGate's Foundation models & chat category. It focuses on extracting and understanding text from images or scanned documents using AI without building custom OCR pipelines. It is built as an open-source project for developers. Qianfan OCR is available on the web, the command line, and API.

Baidu builds and maintains Qianfan OCR, and it first shipped in 2025. The project is developed in the open on GitHub with 421 stars. Among its 3 catalogued features are Optical Character Recognition, Multimodal Input, and Chat Template Support.

Summary written by a language model from the project’s public pages.

Optical Character Recognition
Multimodal Input
Chat Template Support

Built with & integrations

Hosting

AWS

AI providers

local_ossgoogle_geminimultiple

Runs on

BrowserCLIAPI-only

Detected from

AWS: x-amz-cf-id header · x-amz-cf-pop header · via header
multiple: bLlamaIndex in the HTML
local_oss: bollama in the HTML · bllama in the HTML · bvllm in the HTML
google_gemini: bgemini- in the HTML

Trust & compliance

License

MIT

Verified signals

HTTPSGitHub · ★ 421

Indexing history

What PulseGate has recorded for this listing

Indexed5 Aug · 08:37 UTC
baidu/Qianfan-OCR verified against its public source
Source: PulseGate · Open

Frequently asked questions about Qianfan OCR

What is Qianfan OCR?: Qianfan OCR focuses on extracting and understanding text from images or scanned documents using AI without building custom OCR pipelines. It is catalogued under Foundation models & chat on PulseGate.
Who is Qianfan OCR for?: Qianfan OCR is an open-source project built for developers.
What platforms does Qianfan OCR run on?: Qianfan OCR runs on the web, the command line, and API.
Is Qianfan OCR still active?: Unverified. Qianfan OCR has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
Who makes Qianfan OCR?: Qianfan OCR is developed by Baidu, based in China.
When did Qianfan OCR launch?: Qianfan OCR first shipped in 2025.
Is Qianfan OCR open source?: Qianfan OCR has a public GitHub repository.

At a glance

Pricing: Paid · pricing page detected
Platforms: Cli · Web
Languages: English
Open source: Yes · ★ 421
License: MIT
Built for: developers
Model: Open source
Solves: Extracting and understanding text from images or scanned documents using AI without building custom OCR pipelines.

Registered as

GitHub: baidubce/Qianfan-VL
Hugging Face: baidu/Qianfan-OCR

Developer

🇨🇳Baidu

Small team

GitHub

Open source

View on GitHub

Stars: 421
Forks: 28
Open issues: 11
Last commit: 18 Mar 2026
Commits 90d: 0
Contributors: 2
Authorship: Small team
Default branch: main

Live coverage

Identity confidence: Medium · 70.4
Indexed: 5 Aug 2026
Lifecycle: Alive
Last seen: 5 Aug 2026

Identity audit (13)

Slug: baidu-qianfan-ocr-huggingface-co
Lifecycle state recorded: 5 Aug 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 5 Aug 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Derived from the project's own page and URL.
Category from: Derived from the model's own Hugging Face metadata.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Last updated: 5 Aug 2026
Canonical URL: https://huggingface.co/baidu/Qianfan-OCR

Ship this? Send a correction — no account, and you get a link to follow it.

Similar apps

Closest matches by what these projects do