{"id":13699,"date":"2026-11-17T11:02:29","date_gmt":"2026-11-17T02:02:29","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=13699"},"modified":"2026-11-17T11:11:40","modified_gmt":"2026-11-17T02:11:40","slug":"baidus-unlimited-ocr-2-for-long-documents","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/baidus-unlimited-ocr-2-for-long-documents\/","title":{"rendered":"Unlimited-OCR-2 Vision-Language Model: 8GB+ VRAM"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/huggingface.co\/baidu\/Unlimited-OCR-2\">baidu\/Unlimited-OCR-2<\/a><\/td>\n<\/tr>\n<tr>\n<td>Family guide<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-baidu-unlimited-ocr-2-en\/\">Unlimited-OCR-2 guide (1 articles)<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-10-26<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>mit<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-safetensors-en\/\">safetensors<\/a><\/td>\n<\/tr>\n<tr>\n<td>Paper<\/td>\n<td><a href=\"https:\/\/arxiv.org\/abs\/2606.23050\">arXiv:2606.23050<\/a><\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>Baidu has released &#8220;Unlimited-OCR-2,&#8221; a vision-language model specialized in analyzing ultra-long documents. It is developed to build upon the design of the previous version, &#8220;Unlimited-OCR,&#8221; aiming to parse extremely long documents without increasing computational load or memory consumption.<\/p>\n<p>According to the abstract of the paper explaining the underlying technology of this model, &#8220;Unlimited OCR Works&#8221; (<a href=\"https:\/\/arxiv.org\/abs\/2606.23050\"><a href=\"https:\/\/arxiv.org\/abs\/2606.23050\">https:\/\/arxiv.org\/abs\/2606.23050<\/a><\/a>), recent end-to-end OCR models achieve high accuracy by adopting LLMs as decoders, but they face challenges where KV cache accumulates as the output sequence grows longer, leading to a sudden surge in memory consumption and a drop in generation speed. Focusing on the fact that humans do not drop efficiency even during lengthy transcription tasks, the authors proposed introducing &#8220;Reference Sliding Window Attention (R-SWA)&#8221; to mimic human working memory, keeping the KV cache constant throughout the entire decoding process. With this latest Unlimited-OCR-2, this mechanism is further evolved to achieve &#8220;Unlimited-Horizon Parsing&#8221; of entire documents within a finite context window.<\/p>\n<h2>Specifications<\/h2>\n<ul>\n<li>Architecture: UnlimitedOCRForCausalLM<\/li>\n<\/ul>\n<h2>Performance<\/h2>\n<p>While the model card does not include a comparison table with detailed score figures, qualitative evaluation results reported by the creators have been shared.<\/p>\n<p>According to the creators, Unlimited-OCR-2 has achieved state-of-the-art (SOTA) performance on both &#8220;MPDocBench,&#8221; a benchmark evaluating documents on the scale of dozens of pages, and &#8220;MarathonDocBench,&#8221; targeting extreme long-form documents spanning hundreds of pages.<\/p>\n<p>Making this long-form processing possible is the newly introduced &#8220;Sparse Reference Sliding Window Attention (SR-SWA)&#8221; in this version. According to the creators&#8217; explanation, it compresses the attention interaction between text and visual information in ultra-long sequences into a set of fixed-size working references, such as 512 tokens. This confines computational complexity within fixed boundaries, allowing the decoding latency and memory consumption per step to be maintained almost constant regardless of document length.<\/p>\n<p>In conventional standard attention mechanisms, computational costs tend to increase quadratically as inputs and outputs grow longer, easily causing out-of-memory (OOM) errors due to bloated KV caches. Unlimited-OCR-2 is reported to eliminate this quadratic scaling and memory bottleneck through SR-SWA, enabling virtually unlimited document analysis while maintaining a finite context length. The model card also demonstrates text analysis of an entire book executed in a single request from start to finish.<\/p>\n<p>However, it should be noted that these evaluation results and the SOTA positioning are claims reported by the model creators themselves, and detailed verification scores or numerical comparison tables with other models by independent third-party institutions are not provided.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>Unlimited-OCR-2 excels at bulk OCR (optical character recognition) and text extraction tasks for ultra-long documents ranging from dozens to hundreds of pages.<\/p>\n<p>As seen in the model card description and function tags (<code>ocr<\/code>, <code>vision-language<\/code>, <code>multilingual<\/code>), this model specializes in image-text-to-text conversion for multilingual documents. In particular, it features two encoding methods that can be used depending on the application: &#8220;gundam mode&#8221; (dynamic tiling), which reads a single page by dividing it into fine segments, and &#8220;base mode,&#8221; which captures the entire page globally. By feeding multi-page documents in bulk, analysis can proceed while taking cross-page context into account.<\/p>\n<p>Additionally, as mentioned in the paper&#8217;s abstract, it adopts a sliding window attention design that mimics working memory, suppressing drops in decoding speed and bloating of the KV cache even as the page count increases. This makes it suitable for integration into pipelines that convert extremely long materials\u2014such as academic papers, technical specifications, manuals, and books\u2014into text in a single inference request, without needing to split them page by page and send individual requests.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong> \u2014 3.3B parameters<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Your VRAM<\/th>\n<th>Quantization<\/th>\n<th>File size<\/th>\n<th>Est. memory needed<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>8GB (RTX 4060 \/ 3060 Ti, etc.)<\/td>\n<td>I64<\/td>\n<td>6.2GB<\/td>\n<td>7.5GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><strong>Inference engine support<\/strong> (architecture name matched against each project&#8217;s own model registry in its source code, checked 2026-11-17): llama.cpp: registered, vLLM: registered, MLX (mlx-lm): not registered. &#8220;Not registered&#8221; means the name is absent from that registry today, not that the model cannot run.<\/p>\n<p><em>Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model&#8217;s authors. Compare with other models in our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a>. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:hardware --><\/p>\n<p><!-- lmw:runnability --><\/p>\n<h2>Can You Run It Locally?<\/h2>\n<p><strong>Not usable in Ollama, LM Studio and llama.cpp yet \u2014 we have found no GGUF build.<\/strong><\/p>\n<p>The publisher ships safetensors only. However, llama.cpp&#8217;s registry does list this architecture, so <strong>conversion to GGUF is possible<\/strong> and the model will run once someone publishes a converted build. 14 converted build(s) from other uploaders exist. Today it can be run with transformers, vLLM or MLX (Apple Silicon), using the memory figures in the table above.<\/p>\n<p><strong>License \u2014 <code>mit<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution, provided the copyright notice and license text are retained.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats, converted builds we have found, and each engine&#8217;s own model registry. &#8220;Not found&#8221; means we have not seen such a build, not that none exists. License summaries are not legal advice \u2014 check the publisher&#8217;s original terms before relying on them.<\/em><\/p>\n<p><!-- \/lmw:runnability --><\/p>\n<p><!-- lmw:peers --><\/p>\n<h2>Recent Models in the Same Size Class<\/h2>\n<p><em>Models with <\/em><em>up to 4B<\/em><em> parameters that Local Model Watch covered recently, listed by code from our article log for comparison. VRAM tiers are this site&#8217;s estimates; licenses are as stated on the model cards.<\/em><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Parameters<\/th>\n<th>Smallest VRAM tier<\/th>\n<th>License<\/th>\n<th>Our article<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>LiquidAI\/d1-omni-600M<\/td>\n<td>587M<\/td>\n<td>4GB<\/td>\n<td>lfm1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-d1-omni-600m-multimodal-decision-model\/\">d1-omni-600M Multimodal Decision Model: 4GB+ VRAM, GGUF Builds<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>LiquidAI\/d1-3B<\/td>\n<td>3.1B<\/td>\n<td>4GB<\/td>\n<td>lfm1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/d1-3b-decision-model\/\">d1-3B Vision-Language Model: 4GB+ VRAM, GGUF Builds<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>openbmb\/MiniCPM-OCR-1.0-DSpark<\/td>\n<td>297M<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/minicpm-ocr-1-0-dspark-overview\/\">MiniCPM-OCR-1.0-DSpark OCR Acceleration Draft Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>openbmb\/MiniCPM-OCR-Jev-GPTQ<\/td>\n<td>2.2B<\/td>\n<td>4GB<\/td>\n<td>apache-2.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/openbmb-releases-quantized-minicpm-ocr-jev\/\">OpenBMB Releases Quantized Versions of MiniCPM-OCR-Jev<\/a> (2026-11-17)<\/td>\n<\/tr>\n<tr>\n<td>LiquidAI\/d1-2B-GGUF<\/td>\n<td>1.9B<\/td>\n<td>4GB<\/td>\n<td>lfm1.0<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/liquidai-d1-2b-gguf-2\/\">d1-2B-GGUF Text, Image, and Video Decision-Making Model: 4GB+ VRAM<\/a> (2026-11-17)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:peers --><\/p>\n<h2>How to Get It<\/h2>\n<p>Unlimited-OCR-2 is available on Hugging Face, distributing weight files in safetensors format. It has no gating restrictions and can be freely downloaded and used under the MIT license.<\/p>\n<p>For lightweight verification, the model card provides Python code using the Transformers library, while SGLang, a high-speed inference framework, is recommended for production deployment and server use.<\/p>\n<p>When using Transformers, install the necessary libraries, then load the model and tokenizer with custom code permitted as follows:<\/p>\n<pre><code class=\"language-python\">import torch\nfrom transformers import AutoModel, AutoTokenizer\n\nmodel_name = &quot;baidu\/Unlimited-OCR-2&quot;\ntokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)\nmodel = AutoModel.from_pretrained(\n    model_name,\n    trust_remote_code=True,\n    use_safetensors=True,\n    torch_dtype=torch.bfloat16\n).eval().cuda()\n<\/code><\/pre>\n<p>When analyzing multi-page documents together, pass a list of page images and call the <code>infer_multi<\/code> method.<\/p>\n<pre><code class=\"language-python\">pages = [f&quot;your_doc\/page_{i}.jpg&quot; for i in range(1, 8)]\ntext, num_tokens = model.infer_multi(\n    tokenizer,\n    image_files=pages,\n    output_path=&quot;output\/multi&quot;,\n    save_results=True\n)\n<\/code><\/pre>\n<p>For single-page images, use the <code>infer<\/code> method. This enables dynamic tiling processing (gundam mode) by default.<\/p>\n<pre><code class=\"language-python\">text = model.infer(\n    tokenizer,\n    image_file=&quot;your_doc\/page_1.jpg&quot;,\n    output_path=&quot;output\/single&quot;,\n    save_results=True\n)\n<\/code><\/pre>\n<p>To launch an inference server using SGLang, install the custom build wheels and related packages (PyMuPDF, fastokens, etc.) noted in the model card, then run the <code>python -m sglang.launch_server<\/code> command. Environment variables allow adjustments tailored to long document processing, such as page-window-based scheduling (e.g., <code>SGLANG_UOCR_DOC_GUNDAM_PAGE_WINDOW<\/code>) and output token limits per page (<code>SGLANG_UOCR_MAX_PAGE_TOKENS<\/code>). Once the server is running, text analysis can be executed by sending image data via the OpenAI-compatible chat completions API (<code>\/v1\/chat\/completions<\/code>).<\/p>\n<p><!-- lmw:variants --><\/p>\n<h2>Quantized and Converted Variants<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Added<\/th>\n<th>Publisher<\/th>\n<th>Format<\/th>\n<th>Repository<\/th>\n<th>Smallest VRAM tier (build, est. memory)<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>2026-11-17<\/td>\n<td>mlx-community<\/td>\n<td>MLX<\/td>\n<td><a href=\"https:\/\/huggingface.co\/mlx-community\/Unlimited-OCR-2-8bit\">mlx-community\/Unlimited-OCR-2-8bit<\/a><\/td>\n<td>MLX 8bit 4.4GB (fits in 8GB VRAM)<\/td>\n<\/tr>\n<tr>\n<td>2026-11-17<\/td>\n<td>mlx-community<\/td>\n<td>MLX<\/td>\n<td><a href=\"https:\/\/huggingface.co\/mlx-community\/Unlimited-OCR-2-4bit\">mlx-community\/Unlimited-OCR-2-4bit<\/a><\/td>\n<td>MLX 4bit 2.7GB (fits in 4GB VRAM)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>File sizes of each build:<\/p>\n<ul>\n<li>Available builds in mlx-community\/Unlimited-OCR-2-8bit: MLX 8bit 3.7GB<\/li>\n<li>Available builds in mlx-community\/Unlimited-OCR-2-4bit: MLX 4bit 2.3GB<\/li>\n<\/ul>\n<p>In addition, 14 converted build(s) from other uploaders exist on Hugging Face; this site lists only builds from the model&#8217;s publisher or established quantization maintainers.<\/p>\n<p><em>This section is appended automatically by Local Model Watch when a converted build of this model appears after publication. Memory figures are estimated from the size of the distributed files. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:variants --><\/p>\n<p><!-- lmw:same-task --><\/p>\n<h2>Other Models for the Same Task<\/h2>\n<p><em>Recent vision-language models covered by Local Model Watch, newest first. Grouped by the task each publisher declares on Hugging Face (pipeline_tag); the smallest VRAM tier is this site&#8217;s estimate.<\/em><\/p>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/qwen3-5-4b-gguf-released\/\">Qwen3.5-4B-GGUF Vision-Language Model: 4GB+ VRAM<\/a> (4.7B, 4GB)<\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/zoomgain-9b-gguf-released\/\">ZoomGain-9B-GGUF Vision-Language Model: 8GB+ VRAM<\/a> (8GB)<\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/singvl-s1-4b-qwen3-5-multimodal-decision-model\/\">SingVL_S1_4B Multimodal Decision Model with Image Support: 4GB+ VRAM<\/a> (4.5B, 4GB)<\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/kimi-k3-1-pro\/\">Kimi-K3.1-Pro 1M-Context Multimodal Agent Model: ~1128GB Memory<\/a> (Over 80GB)<\/li>\n<\/ul>\n<p><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/models-by-task-en\/#task-vision\">See all vision-language models \u2192<\/a><\/p>\n<p><!-- \/lmw:same-task --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Find models by VRAM<\/strong> (This model runs from the 8GB tier) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-8gb-en\/\">Other models that run on a 8GB GPU<\/a><\/li>\n<li><strong>Explore the same model family<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/model-baidu-unlimited-ocr-2-en\/\">Unlimited-OCR-2 family overview (1 articles, 2 converted builds)<\/a><\/li>\n<li><strong>Engines that run this model<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-vllm-en\/\">vLLM<\/a><\/li>\n<li><strong>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-mlx-en\/\">MLX format guide and models<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li>Hugging Face Model Page: <a href=\"https:\/\/huggingface.co\/baidu\/Unlimited-OCR-2\"><a href=\"https:\/\/huggingface.co\/baidu\/Unlimited-OCR-2\">https:\/\/huggingface.co\/baidu\/Unlimited-OCR-2<\/a><\/a><\/li>\n<li>Paper (arXiv:2606.23050): <a href=\"https:\/\/arxiv.org\/abs\/2606.23050\"><a href=\"https:\/\/arxiv.org\/abs\/2606.23050\">https:\/\/arxiv.org\/abs\/2606.23050<\/a><\/a><\/li>\n<\/ul>\n<p><!-- lmw:updates --><\/p>\n<h2>Update History<\/h2>\n<ul>\n<li>2026-11-17: Added converted builds to \u201cQuantized and Converted Variants\u201d: mlx-community\/Unlimited-OCR-2-8bit, mlx-community\/Unlimited-OCR-2-4bit<\/li>\n<\/ul>\n<p><!-- \/lmw:updates --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Learn about Baidu&#8217;s Unlimited-OCR-2, a vision-language model for parsing extremely long documents with constant KV cache and SOTA performance.<\/p>\n","protected":false},"author":1,"featured_media":13698,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[310],"tags":[4141,1492,169,4143,1547,4145,1952],"class_list":["post-13699","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-new-models","tag-baidu-en","tag-ocr-en","tag-sglang-en","tag-unlimited-ocr-2-en","tag-verified","tag-vision-language-en","tag-vlm-en"],"lang":"en","translations":{"en":13699,"ja":13697},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13699","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=13699"}],"version-history":[{"count":3,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13699\/revisions"}],"predecessor-version":[{"id":17948,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/13699\/revisions\/17948"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/13698"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=13699"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=13699"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=13699"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}