CodeFormula
docling-project基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
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 ↗DISCOVER & COMPARE
探索 AI 模型 21
CodeFormulaV2
docling-projectThe **Code Formula Model** processes an image of a code snippet or formula at 120 DPI and outputs its content. - **Code Snippets**: The model identifies the programming language and outputs the code repsecting the indendation shown in the given image. The output format will be: " \_> \ " Example: " System.out.println("Hello World.");" This model was trained using the following two datasets: 1. https://huggingface.co/datasets/ds4sd/SynthFormulaNet 2. https://huggingface.co/datasets/ds4sd/SynthCodeNet
译文排队中 · 当前显示来源原文
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 ↗DeskForge-Gemma4-E4B
docling-project**DeskForge-Gemma4-E4B** is Gemma 4 E4B (instruction-tuned) fine-tuned on 200K grounding examples from DeskForge-1M. Given a desktop screenshot and a natural-language instruction, it answers with the next action as a `pyautogui` call whose coordinates are fractions of the screen. **Live demo** · **Project page** · **Dataset** · **Code** · **Paper** · Also available: DeskForge-Qwen3.5-4B **Grounding on DeskForge-1M held-out conditions** (accuracy, %). New Scenes are unseen scenes with seen attributes; Theme, App and Resolution hold an appearance preset, three applications and a display resolution out of training entirely.
译文排队中 · 当前显示来源原文
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 ↗DeskForge-Qwen3.5-4B
docling-project**News — v1.1:** Updated fine-tuning with additional GUI workflows improves performance on all five external grounding benchmarks. The original paper checkpoint remains available at revision `v1.0`. **DeskForge-Qwen3.5-4B** is Qwen3.5-4B fine-tuned for desktop GUI grounding and next-action prediction using grounding and GUI-workflow supervision. Given a desktop screenshot and a natural-language instruction, it answers with the next action as a `pyautogui` call whose coordinates are fractions of the screen. **Live demo** · **Project page** · **Dataset** · **Code** · **Paper** · Also available: DeskForge-Gemma4-E4B
译文排队中 · 当前显示来源原文
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 ↗docling-layout-egret-large
docling-project📄 For an in-depth description of the model architecture, training datasets, and evaluation methodology, please refer to our technical report: **"Advanced Layout Analysis Models for Docling"**, Nikolaos Livathinos *et al.*, 🔗 https://arxiv.org/abs/2509.11720
译文排队中 · 当前显示来源原文
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 ↗docling-layout-egret-medium
docling-project基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
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 ↗docling-layout-egret-xlarge
docling-project📄 For an in-depth description of the model architecture, training datasets, and evaluation methodology, please refer to our technical report: **"Advanced Layout Analysis Models for Docling"**, Nikolaos Livathinos *et al.*, 🔗 https://arxiv.org/abs/2509.11720
译文排队中 · 当前显示来源原文
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 ↗docling-layout-heron
docling-project🚀 **`heron`** is the **default layout analysis model** of the Docling project, designed for robust and high-quality document layout understanding. 📄 For an in-depth description of the model architecture, training datasets, and evaluation methodology, please refer to our technical report: **"Advanced Layout Analysis Models for Docling"**, Nikolaos Livathinos *et al.*, 🔗 https://arxiv.org/abs/2509.11720
译文排队中 · 当前显示来源原文
输入 文本→ 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 ↗docling-layout-heron-101
docling-project🚀 **`heron-101`** is a Document Layout Analysis Model used in the Docling project. 📄 For an in-depth description of the model architecture, training datasets, and evaluation methodology, please refer to our technical report: **"Advanced Layout Analysis Models for Docling"**, Nikolaos Livathinos *et al.*, 🔗 https://arxiv.org/abs/2509.11720
译文排队中 · 当前显示来源原文
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 ↗docling-layout-heron-onnx
docling-projectThis is an ONNX export of the docling-layout-heron model. Please refer to the original model card for more details.
译文排队中 · 当前显示来源原文
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 ↗docling-layout-old
docling-project`docling-layout-old` is the old Layout Model of Docling project. This model uses the RT-DETR architecture and has been trained from scratch on a variety of document datasets.
译文排队中 · 当前显示来源原文
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 ↗docling-models
docling-projectThis page contains models that power the PDF document converion package docling. The layout model will take an image from a page and apply RT-DETR model in order to find different layout components. It currently detects the labels: Caption, Footnote, Formula, List-item, Page-footer, Page-header, Picture, Section-header, Table, Text, Title. As a reference (from the DocLayNet-paper), this is the performance of standard object detection methods on the DocLayNet dataset compared to human evaluation, The tableformer model will identify the structure of the table, starting from an image of a table. It uses the predicted table regions of the layout model to identify the tables. Tableformer has SOTA table structure identification,
译文排队中 · 当前显示来源原文
输入 文本→ 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 ↗DocumentFigureClassifier
docling-projectThis is an image classification model based on **Google EfficientNet-B0**, fine-tuned to classify input images into one of the following 16 categories: 1. **bar_chart** 2. **bar_code** 3. **chemistry_markush_structure** 4. **chemistry_molecular_structure** 5. **flow_chart** 6. **icon** 7. **line_chart** 8. **logo** 9. **map** 10. **other** 11. **pie_chart** 12. **qr_code** 13. **remote_sensing** 14. **screenshot** 15. **signature** 16. **stamp**
译文排队中 · 当前显示来源原文
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 ↗DocumentFigureClassifier-v2.0
docling-projectThis is an image classification model based on **Google EfficientNet-B0**, fine-tuned to classify input images into one of the following 26 categories: 1. **logo** 2. **photograph** 3. **icon** 4. **engineering_drawing** 5. **line_chart** 6. **bar_chart** 7. **other** 8. **table** 9. **flow_chart** 10. **screenshot_from_computer** 11. **signature** 12. **screenshot_from_manual** 13. **geographical_map** 14. **pie_chart** 15. **page_thumbnail** 16. **stamp** 17. **music** 18. **calendar** 19. **qr_code** 20. **bar_code** 21. **full_page_image** 22. **scatter_plot** 23. **chemistry_structure** 24. **topographical_map** 25. **crossword_puzzle** 26. **box_plot**
译文排队中 · 当前显示来源原文
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 ↗DocumentFigureClassifier-v2.5
docling-projectThis is an image classification model based on **Google EfficientNet-B0**, fine-tuned on a subset of the subset of HuggingFace/finepdfs to classify document figures into one of the following 26 categories: 1. **logo** 2. **photograph** 3. **icon** 4. **engineering_drawing** 5. **line_chart** 6. **bar_chart** 7. **other** 8. **table** 9. **flow_chart** 10. **screenshot_from_computer** 11. **signature** 12. **screenshot_from_manual** 13. **geographical_map** 14. **pie_chart** 15. **page_thumbnail** 16. **stamp** 17. **music** 18. **calendar** 19. **qr_code** 20. **bar_code** 21. **full_page_image** 22. **scatter_plot** 23. **chemistry_structure** 24. **topographical_map** 25. **crossword_puzzle** 26. **box_plot** **Note:** This model uses the same architecture and implementation as v2.0. The improved performance is achieved by training on a dataset that is 10 times larger than the one used for v2.0.
译文排队中 · 当前显示来源原文
输入 图像→ 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 ↗granite-docling-2stage-258m
docling-project基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
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 ↗ScreenParser
docling-project基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 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 ↗ScreenVLM
docling-project基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
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 ↗SmolDocling-256M-preview
docling-project📢 New Release: We’ve released granite-docling-258M , the successor to SmolDocling . It will now receive updates and support, check it out! SmolDocling-256M-preview SmolDocling is a multimodal Image-Text-to-Text model designed for efficient document conversion. It retains Docling's most popular features while ensuring full compatibility with Docling through seamless support for DoclingDocuments . This model was presented in the paper SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion.
译文排队中 · 当前显示来源原文
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 ↗SmolDocling-256M-preview-mlx-bf16
docling-project基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
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 ↗TableFormerV2
docling-project> [!WARNING] > **Preview model.** TableFormerV2 is a preview release. Its weights, outputs, and > integration options can change in future releases without notice. The default > table structure model in Docling is still > TableFormer V1. TableFormerV2 is a table structure recognition model for Docling. It takes an image of a table and predicts its structure as an OTSL token sequence, together with a bounding box for each cell. Docling then maps the cells back to the text of the document to build a `TableItem` in the `DoclingDocument`. Docling downloads the weights from this repository automatically the first time you use the model. To download them before you run a conversion (for example, for offline use), run:
译文排队中 · 当前显示来源原文
输入 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 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
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
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。