**MinerU-HTML** is an advanced HTML main content extraction tool based on Small Language Models (SLM). It can accurately identify and extract main content from complex web page HTML, automatically filtering out auxiliary elements such as navigation bars, advertisements, and metadata. **MinerU-HTML-v1.1-hunyuan0.5B-compact** is a Model Derivative of **Tencent Hunyuan 0.5B**. This model support 256k context-length, so it can support processing more complex web pages. We use a more compact output format, which reduces the inference latency and improves the speed of web page processing. Welcome to try our online document extraction tool! Supports HTML main content extraction and OCR for various document formats.

译文排队中 · 当前显示来源原文

分类待补充

输入待核验→ 输出待核验

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

MinerU2.5-2509-1.2B

opendatalab

**MinerU2.5** is a 1.2B-parameter vision-language model for document parsing that achieves state-of-the-art accuracy with high computational efficiency. It adopts a two-stage parsing strategy: first conducting efficient global layout analysis on downsampled images, then performing fine-grained content recognition on native-resolution crops for text, formulas, and tables. Supported by a large-scale, diverse data engine for pretraining and fine-tuning, MinerU2.5 consistently outperforms both general-purpose and domain-specific models across multiple benchmarks while maintaining low computational overhead. For convenience, we provide `mineru-vl-utils`, a Python package that simplifies the process of sending requests and handling responses from MinerU2.5 Vision-Language Model. Here we give some examples to use MinerU2.5. For more information and usages, please refer to mineru-vl-utils. 📌 We strongly recommend using vllm for inference, as the `vllm-async-engine` can achieve a concurrent inference speed of **2.12 fps** on one A100.

译文排队中 · 当前显示来源原文

视觉问答

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

MinerU2.5-Pro-2604-1.2B

opendatalab

**MinerU2.5-Pro** is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board: **1. Defeating Leading Models on OmniDocBench v1.6** On the newly proposed, highly rigorous OmniDocBench v1.6, MinerU2.5-Pro achieves the absolute **SOTA overall score of 95.69**. It comprehensively outperforms both top-tier specialized OCR models (**GLM-OCR, PaddleOCR-VL-1.5**) and massive frontier VLMs (**Gemini 3 Pro, Qwen3-VL-235B**). **2. Massive Leap from MinerU 2.5 via Data Engineering** Compared to the previous MinerU 2.5 baseline, the overall score skyrocketed from **92.98 to 95.69**. This breakthrough was achieved not by scaling model parameters, but through meticulous data engineering—drastically expanding data scale, enriching distribution and difficulty diversity, and systematically elevating annotation quality.

译文排队中 · 当前显示来源原文

视觉问答

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

MinerU2.5-Pro-2605-1.2B

opendatalab

2026.05.21 🎉🎉 We are pleased to announce the release of MinerU2.5-Pro-2605, an updated version of our model. - **Enhanced Layout Detection** To address the category misclassification issues observed in the 2604 version during layout detection, we conducted a comprehensive data cleaning process. This has substantially reduced category errors in layout detection. Notably, the missed detection rate for the `image_block` category has been significantly reduced. - **Improved Image Analysis** To overcome the limitations of the 2604 version in image analysis, we constructed a large-scale training dataset for this task. As a result, the 2605 version demonstrates markedly enhanced recognition capabilities across a wide range of charts, flowcharts, and even seals.

译文排队中 · 当前显示来源原文

视觉问答

输入文本 · 图像→ 输出文本

价格待核验多模态与渠道费用须分别核对

查看详情 ↗

加入对比来源 / 文档 ↗

COST EXPLORER

好模型，也要算好成本。

费用分析

调整月度 Token 用量，直观比较不同模型的预估 API 开支。

每月输入 Token 10 M每月输出 Token 2 M1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价

使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。

MODEL HANDBOOK

读懂模型，再做选择

选型与常见问题

API 价格应该怎么比较？+

先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。

开放权重，就代表可以免费商用吗？+

不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。

排行榜第一，就是最适合我的模型吗？+

榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。

找到适合你的 AI 模型。

探索 AI 模型 6

MinerU-Diffusion-V1-0320-2.5B

MinerU-HTML

MinerU-HTML-v1.1-hunyuan0.5B-compact

MinerU2.5-2509-1.2B

MinerU2.5-Pro-2604-1.2B

MinerU2.5-Pro-2605-1.2B

暂未找到匹配模型

好模型，也要算好成本。

读懂模型，再做选择

资讯看趋势，工具提效率，模型筑可能。