Who should use HunyuanOCR?

HunyuanOCR is a consumer product built for researchers.

Yes — HunyuanOCR is free to use.

What platforms does HunyuanOCR run on?

HunyuanOCR runs on the web. It can also be self-hosted.

Is HunyuanOCR still active?

Unverified. HunyuanOCR 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.

What are alternatives to HunyuanOCR?

Similar projects tracked by PulseGate include HunyuanOCR, Hunyuan3D-2.0, and HunyuanImage-3.0.

Who makes HunyuanOCR?

HunyuanOCR is developed by tencent.

When did HunyuanOCR launch?

HunyuanOCR first shipped in 2024.

Back to the index

HunyuanOCR

Name: HunyuanOCR
Author: tencent

huggingface.coComputer vision, OCR & document AI

HunyuanOCR allows users to upload images and extract printed text, generate summaries, or answer questions about the image content using AI. It streamlines the process of obtaining structured information from visual data, making it useful for researchers and students.

FreeWebSelf-hostedCloud-managed

Visit huggingface.co

Overview

5 features

HunyuanOCR sits in PulseGate's Computer vision, OCR & document AI category. It focuses on extracting and understanding text or visual information from images without manual transcription or analysis. It is built as a consumer product for researchers. HunyuanOCR costs nothing to use. It ships for the web, and it can be self-hosted.

It is developed by tencent, and it first shipped in 2024. Key capabilities include OCR extraction, visual question answering, and image upload.

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

OCR extraction
Visual question answering
Image upload
Text summary
Printed text recognition

Built with & integrations

Hosting

AWS

AI providers

local_oss

Runs on

BrowserSelf-hostedCloud-managed

Detected from

AWS: x-amz-cf-id header · x-amz-cf-pop header · via header
local_oss: huggingface in the HTML

Trust & compliance

Verified signals

HTTPSFree tier

Indexing history

What PulseGate has recorded for this listing

Indexed10 Jul · 22:24 UTC
tencent/HunyuanOCR verified against its public source
Source: PulseGate · Open

Frequently asked questions about HunyuanOCR

What does HunyuanOCR do?: HunyuanOCR focuses on extracting and understanding text or visual information from images without manual transcription or analysis. It is catalogued under Computer vision, OCR & document AI on PulseGate.
Who should use HunyuanOCR?: HunyuanOCR is a consumer product built for researchers.
Is HunyuanOCR free?: Yes — HunyuanOCR is free to use.
What platforms does HunyuanOCR run on?: HunyuanOCR runs on the web. It can also be self-hosted.
Is HunyuanOCR still active?: Unverified. HunyuanOCR 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.
What are alternatives to HunyuanOCR?: Similar projects tracked by PulseGate include HunyuanOCR, Hunyuan3D-2.0, and HunyuanImage-3.0.HunyuanOCR Hunyuan3D-2.0 HunyuanImage-3.0
Who makes HunyuanOCR?: HunyuanOCR is developed by tencent.
When did HunyuanOCR launch?: HunyuanOCR first shipped in 2024.

At a glance

Platforms: Web
Languages: English
Built for: researchers
Model: B2C
Solves: Extracting and understanding text or visual information from images without manual transcription or analysis.

Registered as

Hugging Face Spaces: tencent/HunyuanOCR

Developer

tencent

Index record

Indexed: 10 Jul 2026
Lifecycle: Alive
Last seen: 10 Jul 2026

Identity audit (12)

Slug: tencent-hunyuanocr-huggingface-co
Lifecycle last checked: 8 Aug 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 10 Jul 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: Recorded source: taxonomy-pass-a.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Canonical URL: https://huggingface.co/spaces/tencent/HunyuanOCR

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

Similar projects

Closest matches by what these projects do