3b:I[603186,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"PageMetadata"] 3c:I[831915,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"SearchResultsImage"] 3d:I[66106,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],""] 3e:I[299632,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"default"] 3f:I[400402,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"EndpointCTA"] 40:I[331699,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"ModelContent"] 4b:I[593756,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"default"] 4c:I[946424,["/_next/static/chunks/1176bnf8oism6.js","/_next/static/chunks/0aiio4ivp1n07.js","/_next/static/chunks/3cauv554e_gxu.js","/_next/static/chunks/3byf1h7-4uxfn.js","/_next/static/chunks/3r5yd4k4rms8-.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/12haym2zhwrql.js","/_next/static/chunks/0gvbio555n823.js","/_next/static/chunks/3ygl6_80ds9-d.js","/_next/static/chunks/2m_mi71579pjv.js","/_next/static/chunks/3pjc6r7w9qxan.js","/_next/static/chunks/07t1rcdzji0vn.js","/_next/static/chunks/0ab2-46782ntx.js","/_next/static/chunks/3ex1ijq1gw1eb.js","/_next/static/chunks/27f80-sq8a9nm.js","/_next/static/chunks/21k90yd6lrzsc.js","/_next/static/chunks/00-5kse4g6azx.js","/_next/static/chunks/3giy7jirffwz9.js","/_next/static/chunks/2vsadn5_3a9ui.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/0gf5i4fmb2vxz.js","/_next/static/chunks/2bcd-9k-4fyab.js","/_next/static/chunks/18gle79tm4_vm.js","/_next/static/chunks/23c-cbn9bzzbb.js","/_next/static/chunks/1_lyn-lih218f.js","/_next/static/chunks/1c0w6764iswod.js","/_next/static/chunks/3d865g9_und-a.js","/_next/static/chunks/0tt83uyswwa6b.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/31pwnoicz230f.js","/_next/static/chunks/2dyt8rg18m736.js","/_next/static/chunks/312elt506g3__.js","/_next/static/chunks/1d4y2icymlumi.js","/_next/static/chunks/1qibxep3kn6qx.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0fpx6rmsgi4um.js","/_next/static/chunks/3x3-h1iyted1x.js","/_next/static/chunks/2fz52lc6kg1s_.js","/_next/static/chunks/2br2z5e4g144b.js","/_next/static/chunks/1hir463fky0ew.js"],"default"] 38:["$","$L3b",null,{"hasPartnerEndpoint":false}] 41:T2646,# NVIDIA Nemotron Parse 2.0 Overview ## Description: NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information. Given a Red, Green, Blue (RGB) document image and a task prompt, the model produces formatted text and spatial annotations for document elements such as titles, paragraphs, captions, tables, charts, page headers, page footers, footnotes, pictures, and bibliography entries. Compared with NVIDIA Nemotron Parse v1.2, NVIDIA Nemotron Parse 2.0 adds an approximately 20k-token vocabulary expansion for more efficient multilingual support, chart-aware document parsing with the `` class token, and updated training coverage for chart/table-heavy documents and stronger support for many languages. NVIDIA Nemotron Parse 2.0 is intended for document understanding, information retrieval, data extraction, and multimodal data-curation workflows. NVIDIA Nemotron Parse 2.0 was developed by NVIDIA as a part of Nemotron. _This model is ready for commercial or non-commercial use._ ### License/Terms of Use: **GOVERNING TERMS:** Use of this trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of the model is governed by the [OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1). ### Deployment Geography: Global ### Use Case: NVIDIA Nemotron Parse 2.0 is designed for developers and teams building document intelligence, retrieval-augmented generation (RAG), curator, extractor, and agentic AI applications. It converts scanned or rendered PDFs, presentation slides, forms, reports, tables, and mixed-content document pages into structured outputs for downstream indexing, retrieval, analytics, model training-data creation, and human-in-the-loop review. The model supports document understanding, OCR, layout parsing, table extraction, and text extraction with spatial grounding. ### Release Date: **Build.NVIDIA.com:** 09/11/2026 via [link](https://build.nvidia.com/nvidia/nemotron-parse-2.0) **HuggingFace:** 06/30/2026 via [link](https://huggingface.co/nvidia/NVIDIA-Nemotron-Parse-2.0) ## Reference(s): [Hugging Face Transformers mBART documentation](https://huggingface.co/docs/transformers/en/model_doc/mbart) [NVIDIA C-RADIO](https://huggingface.co/nvidia/C-RADIO) ## Model Architecture: **Architecture Type:** Transformer **Network Architecture:** Vision Encoder (ViT-H based on NVIDIA C-RADIO) + Adapter (1D convolutions and normalization layers) + Decoder (mBART with 10 blocks) **This model was developed based on mBART.** **Number of model parameters:** 905M ## Computational Load **Cumulative Compute:** 1.50x10^21 FLOP **Estimated Energy and Emissions for Model Training:** ~4.64 MWh ## Input: **Input Type(s):** Image, Text **Input Format(s):** * Image: Red, Green, Blue (RGB) * Text: String **Input Parameters:** Two-Dimensional (2D), One-Dimensional (1D) **Other Properties Related to Input:** The model accepts RGB images with a recommended maximum resolution of 1664×2048 pixels and a minimum of 1024×1280 pixels. Input prompts consist of control tokens; the default prompt is `` to extract bounding boxes, classes, and markdown text. The model can also emit `` tokens for detected chart regions. ## Output: **Output Type(s):** Text **Output Format:** String **Output Parameters:** One-Dimensional (1D) **Other Properties Related to Output:** Maximum output length configurable via max_new_tokens parameter (default 9000, max determined by generation config). Supports streaming output via transformers generate. Output is UTF-8 encoded text in formats such as markdown, LaTeX, HTML, JSON, or plain text. Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration: **Runtime Engine(s):** * Transformers * vLLM **Supported Hardware Microarchitecture Compatibility:** * NVIDIA Ampere * NVIDIA Blackwell * NVIDIA Hopper * NVIDIA Turing **Supported Operating System(s):** Linux The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. This AI model can be embedded as an Application Programming Interface (API) call into the software environment described above. ## Model Version(s): NVIDIA Nemotron Parse 2.0 Integration requires Transformers or vLLM frameworks and runs on Linux with NVIDIA Ampere, NVIDIA Blackwell, NVIDIA Hopper, or NVIDIA Turing GPUs. ## Training, Testing, and Evaluation Datasets: ## Training Dataset: **Data Modality:** * Image * Text **Image Training Data Size:** 1 Million to 1 Billion Images **Text Training Data Size:** 1 Billion to 10 Trillion Tokens **Data Collection Method by dataset:** Hybrid: Automated/Manually-Collected/Synthetic **Labeling Method by dataset:** Hybrid: Automated/Manually-Labelled/Synthetic **Properties (Quantity, Dataset Descriptions, Sensor(s)):** The training set contains millions of image-text items aggregated from large document, table, and layout datasets. It consists of document-page and table images paired with OCR text, bounding boxes, and layout labels. Sources include rendered digital documents, scientific papers, PDFs, Wikipedia-style pages, and synthetic document, table, word, and character renderings. Annotations are derived from OCR and layout models, third-party OCR services, synthetic-generation pipelines, and human labeling. ### Testing Dataset: **Data Collection Method by dataset:** Hybrid: Automated/Manually-Collected/Synthetic **Labeling Method by dataset:** Hybrid: Automated/Manually-Labelled/Synthetic **Properties (Quantity, Dataset Descriptions, Sensor(s)):** Tested on internal and public document-understanding benchmarks covering OCR quality, layout structure, table parsing, reading order, and visual grounding. ### Evaluation Dataset: **Benchmark Score:** See benchmark table below. Benchmark coverage: * ParseBench evaluates document parsing across text fidelity, semantic formatting, tables, charts, and visual grounding with layout boxes/classes. * IndicVisionBench evaluates OCR quality for Indic-language pages, including Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu. * MOSCAR evaluates multilingual synthetic OCR across broad script coverage, including Latin, Arabic, Cyrillic, Chinese, Hangul, Japanese, Indic scripts, Hebrew, Thai, Greek, and others. * OmniDocBench Notes (Handwriting) evaluates text-block edit distance on note-style document pages from the `data_source: note` slice. The following results compare NVIDIA Nemotron Parse 2.0 with NVIDIA Nemotron Parse v1.2 on internal and public evaluation benchmarks. NVIDIA Nemotron Parse 2.0 results use the equal-weight checkpoint soup from training checkpoints 58k, 60k, 62k, 64k, and 66k. Unless marked otherwise, metrics are higher-is-better; arrows indicate the direction of the 2.0 change relative to v1.2. | Benchmark | Metric | NVIDIA Nemotron Parse v1.2 | NVIDIA Nemotron Parse 2.0 | Change | | :---- | :---- | :---- | :---- | :---- | | ParseBench | Overall score | 0.5782 | 0.6391 | ↑ +0.0609 | | OmniDocBench Notes (Handwriting) | Text edit distance (lower is better) | 0.9739 | 0.3395 | ↓ -0.6343 | | IndicVisionBench | Overall ANLS character | 0.0612 | 0.7203 | ↑ +0.6592 | | MOSCAR (Multilingual) | Overall BoC F1 | 0.4410 | 0.9102 | ↑ +0.4692 | **Data Collection Method by dataset:** Hybrid: Automated/Manually-Collected **Labeling Method by dataset:** Hybrid: Automated/Manually-Labelled **Properties (Quantity, Dataset Descriptions, Sensor(s)):** Evaluated on internal and public document-understanding benchmarks covering OCR quality, layout structure, table parsing, reading order, and visual grounding. ## Inference: **Acceleration Engine:** vLLM **Test Hardware:** * NVIDIA Ampere (A100, A10G) * NVIDIA Blackwell (B200, GB200, RTX PRO 6000) * NVIDIA Hopper (H100) * NVIDIA Lovelace (L40S) ## Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please make sure you have proper rights and permissions for all input image and video content; if image or video includes people, personal health information, or intellectual property, the image or video generated will not blur or maintain proportions of image subjects included. For more detailed information on ethical considerations for this model, please see the Model Card++ [Explainability](explainability.md), [Bias](bias.md), [Safety & Security](safety_security.md), and [Privacy](privacy.md) Subcards. Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). **Generated by NVIDIA Model Card Generator Toolkit.**42:Taf4,# Explainability Subcard ## Intended Task/Domain: Document Understanding and Optical Character Recognition (OCR) ## Model Type: Transformer ## Intended Users: Developers and teams building document intelligence, retrieval-augmented generation (RAG), curator, extractor, and agentic AI applications for converting scanned or rendered PDFs, presentation slides, forms, reports, tables, and mixed-content document pages into structured outputs for downstream indexing, retrieval, analytics, model training-data creation, and human-in-the-loop review. ## Output: Text ## Describe how the model works: This transformer-based model uses a Vision Encoder (ViT-H based on NVIDIA C-RADIO) for image processing, an Adapter with 1D convolutions and normalization layers, and a Decoder (mBART with 10 blocks) to transform document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information. ## Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: Not Applicable ## Technical Limitations and Mitigation: NVIDIA Nemotron Parse 2.0 may produce OCR and document-structure extraction errors, including omitted, substituted, duplicated, or misordered text; incorrect layout classes or bounding boxes; inaccurate reading order; and incomplete or malformed tables and charts. Performance may vary with image resolution, scan quality, handwriting, layout complexity, and language or script. To mitigate these limitations, follow the recommended input-resolution guidance, validate parsed output against the source document, and use human review for accuracy-sensitive workflows. ## Verified to have met prescribed NVIDIA quality standards: Yes ## Performance Metrics: Accuracy (Top-1) F-1 Score Throughput & Latency ## Potential Known Risks: Incorrect or incomplete document parsing can propagate inaccurate text, spatial annotations, or document structure into downstream indexing, retrieval, analytics, retrieval-augmented generation, model training-data creation, or agentic workflows. These errors may cause downstream systems to retrieve the wrong content, miss relevant content, or act on an incorrect representation of the source document. Do not rely on parsed output as the sole source for accuracy-sensitive or high-impact decisions; retain the original document for validation and review. ## Terms of Use/Licensing: **GOVERNING TERMS:** Use of this trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of the model is governed by the [OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1).43:T512,# Privacy Subcard ## Generatable or reverse engineerable personal data? No ## Personal data used to create this model? Yes ## Was consent obtained for any personal data used? Unknown (Externally-Sourced Data) ## How often is dataset reviewed? Before Every Release ## Is a mechanism in place to honor data subject right of access or deletion of personal data? Unknown (Externally-Sourced Data) ## If personal data was collected for the development of the model, was it collected directly by NVIDIA? No ## If personal data was collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? Not Applicable ## If personal data was collected for the development of this AI model, was it minimized to only what was required? Yes ## Was data from user interactions with the AI model (e.g. user input and prompts) used to train the model? No ## Is there provenance for all datasets used in training? Yes ## Does data labeling (annotation, metadata) comply with privacy laws? Yes ## Is data compliant with data subject requests for data correction or removal, if such a request was made? No, not possible with externally sourced data. ## Applicable Privacy Policy https://www.nvidia.com/en-us/about-nvidia/privacy-policy/44:T1018,{ "id": "chatcmpl-94444bbf3f421c5f", "object": "chat.completion", "created": 1786657564, "model": "nvidia/nemotron-parse-2.0", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "**CUDA C++ Programming Guide, Release 12.8**

\n\n\\begin{tabular}{cc}\n**Thread Scope** & **Description**\\\\cuda::thread\\_scope::thread\\_scope\\_thread & Only the CUDA thread which initiated asynchronous op- erations synchronizes.\\\\cuda::thread\\_scope::thread\\_scope\\_block & All or any CUDA threads within the same thread block as the initiating thread synchronizes.\\\\cuda::thread\\_scope::thread\\_scope\\_device & All or any CUDA threads in the same GPU device as the initiating thread syn- chronizes.\\\\cuda::thread\\_scope::thread\\_scope\\_system & All or any CUDA or CPU threads in the same system as the initiating thread syn- chronizes.\\\\\n\\end{tabular}\n\nThese thread scopes are implemented as extensions to standard C++ in the CUDA Standard C++ li- brary.\n\n## 5.6. Compute Capability

\n\nThe _compute capability_ of a device is represented by a version number, also sometimes called its “SM version”. This version number identifies the features supported by the GPU hardware and is used by applications at runtime to determine which hardware features and/or instructions are available on the present GPU.\n\nThe compute capability comprises a major revision number X and a minor revision number Y and is denoted by X.Y.\n\nDevices with the same major revision number are of the same core architecture. The major revision number is 9 for devices based on the _NVIDIA Hopper GPU_ architecture, 8 for devices based on the _NVIDIA Ampere GPU_ architecture, 7 for devices based on the _Volta_ architecture, 6 for devices based on the _Pascal_ architecture, 5 for devices based on the _Maxwell_ architecture, and 3 for devices based on the _Kepler_ architecture.\n\nThe minor revision number corresponds to an incremental improvement to the core architecture, possibly including new features.\n\n_Turing_ is the architecture for devices of compute capability 7.5, and is an incremental update based on the _Volta_ architecture.\n\n_CUDA-Enabled GPUs_ lists of all CUDA-enabled devices along with their compute capability. _Compute Capabilities_ gives the technical specifications of each compute capability.\n\n**Note:** The compute capability version of a particular GPU should not be confused with the CUDA version (for example, CUDA 7.5, CUDA 8, CUDA 9), which is the version of the CUDA _software platform_. The CUDA platform is used by application developers to create applications that run on many generations of GPU architectures, including future GPU architectures yet to be invented. While new versions\n\n**5.6. Compute Capability**

\n\n19

", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": null }, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null } ], "service_tier": null, "system_fingerprint": "vllm-0.24.0-4447e481", "usage": { "prompt_tokens": 6, "total_tokens": 683, "completion_tokens": 677, "prompt_tokens_details": null }, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null } 45:Tfee,{ "id": "chatcmpl-8b5e2de3961a811c", "object": "chat.completion", "created": 1786657659, "model": "nvidia/nemotron-parse-2.0", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Appl. Sci. 2023, 13, 12967\n4 of 21

\n\nTable 1. Adopted material properties.\n\n\\begin{tabular}{cccccc}\n\\multirow{2}{*}{**Quantity**} & \\multirow{2}{*}{**Symbol**} & \\multirow{2}{*}{**Units**} & \\multicolumn{3}{c}{**Materials**}\\\\\n{} & {} & {} & **Ti-6Al-4V** & **Al. 7075 T6** & **SikaPower®-1277**\\\\\nModulus of elasticity & E & MPa & 115,000 & 71,955 ± 224 & 2280 ± 533\\\\\nPoisson’s ratio & v & / & 0.34 & 0.3 & 0.33\\\\\nUltimate tensile strength & σuts & MPa & 950 & 610 ± 15 & 35.7 ± 1.4\\\\\nDensity & ρ & g/cc & 4.395 & 2.8 & 1.1\\\\\nLoss factor & LF & / & 2.96 × 10−4 & 3.5 × 10−3 & 2 × 10−2\\\\\nViscosity & V & Pa·s & / & / & 430 (at 20 °C)\\\\\n\\end{tabular}\n\nThe adopted experimental equipment for performing VHCF tests was an ultrasonic\nfatigue testing machine (UFTM). The UFTM is shown in Figure 1 and was developed at\nPolitecnico di Torino for testing components in the chosen fatigue range. The UFTM can\nperform tests at 20 ± 0.5 kHz under fully reversed tension–compression stress (R = −1),\nwhich significantly reduces the testing time compared to conventional testing apparatuses.\nTo perform fatigue tests, the UFTM adopts the following devices: (i) an electric generator\n(Branson DCX 4 kW, not visible in Figure 1) which generates an electrical sinusoidal wave\nat 20 kHz; (ii) a piezoelectric transducer, responsible for converting the electrical wave\ninto a mechanical vibration; (iii) a booster and a horn made of Ti–6Al–4V that amplify and\nconvey the vibration to the specimen under testing; (iv) the specimen under investigation,\nwhich was designed for the UFTM resonance conditions; (v) a laser displacement sensor\nthat measures the displacement at the specimen free end; (vi) vortex tubes to keep the\ntemperature controlled in the range (20–24) ◦C; and (vii) a temperature sensor to observe\nthe temperature evolution during the test execution.\n\nPiezoelectric\ntransducer\n\nVortex tube\n\nBooster\n\nHorn\n\nTemperature sensor\n\nSpecimen\n\nLaser-displacement\nsensor\n\nFigure 1. The UFTM equipment [43].\n\nPerforming fatigue tests with the UFTM consists of the application of alternated stress\nin specimens that are designed to work in resonance conditions. The specimen and the\nvibration components are thus designed to have a resonance frequency corresponding to a\nlongitudinal mode of vibration close to 20 kHz. Moreover, the UFTM adopts a closed-loop\nproportional–integrative–derivative (PID) control logic where the displacement measured", "refusal": null, "annotations": null, "audio": null, "function_call": null, "reasoning": null }, "logprobs": null, "finish_reason": "stop", "stop_reason": null, "token_ids": null, "routed_experts": null } ], "service_tier": null, "system_fingerprint": "vllm-0.24.0-4447e481", "usage": { "prompt_tokens": 6, "total_tokens": 934, "completion_tokens": 928, "prompt_tokens_details": null }, "prompt_logprobs": null, "prompt_token_ids": null, "prompt_text": null, "kv_transfer_params": null } 46:Tafe,<% const req = request || {}; const model = req.model || "nvidia/nemotron-parse-2.0"; const defaultPrompt = ""; const imagePart = { type: "image_url", image_url: { url: "https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg" } }; const rawMessages = Array.isArray(req.messages) ? req.messages : (typeof req.messages === "string" ? [{ role: "user", content: req.messages }] : []); const toMessage = (msg) => { const m = (msg && typeof msg === "object") ? msg : { content: msg }; const role = m.role || "user"; if (Array.isArray(m.content)) return { role, content: m.content }; const text = (m.content === undefined || m.content === null || String(m.content).trim() === "") ? defaultPrompt : String(m.content); return role === "user" ? { role, content: [{ type: "text", text }, imagePart] } : { role, content: text }; }; const messages = (rawMessages.length ? rawMessages : [{ role: "user", content: defaultPrompt }]).map(toMessage); const num = (v, d) => (v === undefined || v === null || v === "" || Number.isNaN(Number(v))) ? d : Number(v); const temperature = num(req.temperature, 0); const topP = num(req.top_p, 1); const maxTokens = num(req.max_tokens, 1024); const stream = req.stream === true || req.stream === "true"; const prettyJson = (value, level, py) => { const pad = " ".repeat(level); const inner = " ".repeat(level + 2); if (value === null || value === undefined) return py ? "None" : "null"; if (typeof value === "boolean") return py ? (value ? "True" : "False") : String(value); if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); if (Array.isArray(value)) return value.length ? "[\n" + value.map((v) => inner + prettyJson(v, level + 2, py)).join(",\n") + "\n" + pad + "]" : "[]"; const keys = Object.keys(value); return keys.length ? "{\n" + keys.map((k) => inner + JSON.stringify(k) + ": " + prettyJson(value[k], level + 2, py)).join(",\n") + "\n" + pad + "}" : "{}"; }; -%> from openai import OpenAI client = OpenAI( base_url = "https://integrate.api.nvidia.com/v1", api_key = "$NVIDIA_API_KEY" ) messages = <%- prettyJson(messages, 0, true) %> completion = client.chat.completions.create( model="<%- model %>", messages=messages, temperature=<%- temperature %>, top_p=<%- topP %>, max_tokens=<%- maxTokens %>, stream=<%- stream ? "True" : "False" %> ) <% if (stream) { %> for chunk in completion: if not getattr(chunk, "choices", None): continue if chunk.choices[0].delta.content is not None: print(chunk.choices[0].delta.content, end="") <% } else { %> print(completion.choices[0].message.content) <% } %> 47:Ta19,<% const req = request || {}; const model = req.model || "nvidia/nemotron-parse-2.0"; const defaultPrompt = ""; const imagePart = { type: "image_url", image_url: { url: "https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg" } }; const rawMessages = Array.isArray(req.messages) ? req.messages : (typeof req.messages === "string" ? [{ role: "user", content: req.messages }] : []); const toMessage = (msg) => { const m = (msg && typeof msg === "object") ? msg : { content: msg }; const role = m.role || "user"; if (Array.isArray(m.content)) return { role, content: m.content }; const text = (m.content === undefined || m.content === null || String(m.content).trim() === "") ? defaultPrompt : String(m.content); return role === "user" ? { role, content: [{ type: "text", text }, imagePart] } : { role, content: text }; }; const messages = (rawMessages.length ? rawMessages : [{ role: "user", content: defaultPrompt }]).map(toMessage); const num = (v, d) => (v === undefined || v === null || v === "" || Number.isNaN(Number(v))) ? d : Number(v); const temperature = num(req.temperature, 0); const topP = num(req.top_p, 1); const maxTokens = num(req.max_tokens, 1024); const stream = req.stream === true || req.stream === "true"; const prettyJson = (value, level, py) => { const pad = " ".repeat(level); const inner = " ".repeat(level + 2); if (value === null || value === undefined) return py ? "None" : "null"; if (typeof value === "boolean") return py ? (value ? "True" : "False") : String(value); if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); if (Array.isArray(value)) return value.length ? "[\n" + value.map((v) => inner + prettyJson(v, level + 2, py)).join(",\n") + "\n" + pad + "]" : "[]"; const keys = Object.keys(value); return keys.length ? "{\n" + keys.map((k) => inner + JSON.stringify(k) + ": " + prettyJson(value[k], level + 2, py)).join(",\n") + "\n" + pad + "}" : "{}"; }; -%> from langchain_nvidia_ai_endpoints import ChatNVIDIA client = ChatNVIDIA( model="<%- model %>", api_key="$NVIDIA_API_KEY", temperature=<%- temperature %>, top_p=<%- topP %>, max_tokens=<%- maxTokens %>, ) messages = <%- prettyJson(messages, 0, true) %> <% if (stream) { %> for chunk in client.stream(messages): print(chunk.content, end="") <% } else { %> response = client.invoke(messages) print(response.content) <% } %> 48:Taf8,<% const req = request || {}; const model = req.model || "nvidia/nemotron-parse-2.0"; const defaultPrompt = ""; const imagePart = { type: "image_url", image_url: { url: "https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg" } }; const rawMessages = Array.isArray(req.messages) ? req.messages : (typeof req.messages === "string" ? [{ role: "user", content: req.messages }] : []); const toMessage = (msg) => { const m = (msg && typeof msg === "object") ? msg : { content: msg }; const role = m.role || "user"; if (Array.isArray(m.content)) return { role, content: m.content }; const text = (m.content === undefined || m.content === null || String(m.content).trim() === "") ? defaultPrompt : String(m.content); return role === "user" ? { role, content: [{ type: "text", text }, imagePart] } : { role, content: text }; }; const messages = (rawMessages.length ? rawMessages : [{ role: "user", content: defaultPrompt }]).map(toMessage); const num = (v, d) => (v === undefined || v === null || v === "" || Number.isNaN(Number(v))) ? d : Number(v); const temperature = num(req.temperature, 0); const topP = num(req.top_p, 1); const maxTokens = num(req.max_tokens, 1024); const stream = req.stream === true || req.stream === "true"; const prettyJson = (value, level, py) => { const pad = " ".repeat(level); const inner = " ".repeat(level + 2); if (value === null || value === undefined) return py ? "None" : "null"; if (typeof value === "boolean") return py ? (value ? "True" : "False") : String(value); if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); if (Array.isArray(value)) return value.length ? "[\n" + value.map((v) => inner + prettyJson(v, level + 2, py)).join(",\n") + "\n" + pad + "]" : "[]"; const keys = Object.keys(value); return keys.length ? "{\n" + keys.map((k) => inner + JSON.stringify(k) + ": " + prettyJson(value[k], level + 2, py)).join(",\n") + "\n" + pad + "}" : "{}"; }; -%> import OpenAI from 'openai'; const openai = new OpenAI({ apiKey: '$NVIDIA_API_KEY', baseURL: 'https://integrate.api.nvidia.com/v1', }) async function main() { const completion = await openai.chat.completions.create({ model: "<%- model %>", messages: <%- prettyJson(messages, 4) %>, temperature: <%- temperature %>, top_p: <%- topP %>, max_tokens: <%- maxTokens %>, stream: <%- stream %>, }) <% if (stream) { %> for await (const chunk of completion) { process.stdout.write(chunk.choices[0]?.delta?.content || '') } <% } else { %> process.stdout.write(completion.choices[0]?.message?.content ?? '') <% } %> } main();49:T992,<% const req = request || {}; const model = req.model || "nvidia/nemotron-parse-2.0"; const defaultPrompt = ""; const imagePart = { type: "image_url", image_url: { url: "https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg" } }; const rawMessages = Array.isArray(req.messages) ? req.messages : (typeof req.messages === "string" ? [{ role: "user", content: req.messages }] : []); const toMessage = (msg) => { const m = (msg && typeof msg === "object") ? msg : { content: msg }; const role = m.role || "user"; if (Array.isArray(m.content)) return { role, content: m.content }; const text = (m.content === undefined || m.content === null || String(m.content).trim() === "") ? defaultPrompt : String(m.content); return role === "user" ? { role, content: [{ type: "text", text }, imagePart] } : { role, content: text }; }; const messages = (rawMessages.length ? rawMessages : [{ role: "user", content: defaultPrompt }]).map(toMessage); const num = (v, d) => (v === undefined || v === null || v === "" || Number.isNaN(Number(v))) ? d : Number(v); const temperature = num(req.temperature, 0); const topP = num(req.top_p, 1); const maxTokens = num(req.max_tokens, 1024); const stream = req.stream === true || req.stream === "true"; const prettyJson = (value, level, py) => { const pad = " ".repeat(level); const inner = " ".repeat(level + 2); if (value === null || value === undefined) return py ? "None" : "null"; if (typeof value === "boolean") return py ? (value ? "True" : "False") : String(value); if (typeof value === "number") return String(value); if (typeof value === "string") return JSON.stringify(value); if (Array.isArray(value)) return value.length ? "[\n" + value.map((v) => inner + prettyJson(v, level + 2, py)).join(",\n") + "\n" + pad + "]" : "[]"; const keys = Object.keys(value); return keys.length ? "{\n" + keys.map((k) => inner + JSON.stringify(k) + ": " + prettyJson(value[k], level + 2, py)).join(",\n") + "\n" + pad + "}" : "{}"; }; const body = { model, messages, temperature, top_p: topP, max_tokens: maxTokens, stream }; -%> curl https://integrate.api.nvidia.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $NVIDIA_API_KEY" \ -d '<%- prettyJson(body, 0).split("'").join("'\"'\"'") %>' 4a:T5a7,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Pull and run the NVIDIA NIM with the command below. This will download the optimized model for your infrastructure. ```bash export NGC_API_KEY= export LOCAL_NIM_CACHE=~/.cache/nim mkdir -p "$LOCAL_NIM_CACHE" docker run -it --rm \ --gpus all \ --shm-size=16GB \ -e NGC_API_KEY \ -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \ -u $(id -u) \ -p 8000:8000 \ nvcr.io/nim/nvidia/nemotron-parse-v2.0:latest ``` ## Step 3. Test the NIM You can now make a local API call using this curl command: ```bash curl -X 'POST' \ 'http://0.0.0.0:8000/v1/chat/completions' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -d '{ "model": "nvidia/nemotron-parse-v2.0", "messages": [{"role":"user", "content":[ { "type": "text", "text": "" }, { "type": "image_url", "image_url": {"url": "https://assets.ngc.nvidia.com/products/api-catalog/nemotron-parse/example_2.jpg"} } ]}], "max_tokens": 256 }' ``` For more details on getting started with this NIM, visit the [NVIDIA NIM Docs](https://docs.nvidia.com/nim/vision-language-models/latest/getting-started.html).39:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L3c",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-parse-2-0.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L3d",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"nemotron-parse-2.0"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Cutting-edge vision-language model excelling in retrieving text and metadata from images."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L3e",null,{"artifactType":"ENDPOINT","density":"standard","labels":["document parsing","nimType:endpoint:nim_type_run_anywhere","supported language - english","text and table extraction"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L3f",null,{"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/nemotron-parse"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L40",null,{"artifact":{"artifactType":"ENDPOINT","name":"nemotron-parse-2.0","displayName":"nemotron-parse-2.0","publisher":"nvidia","shortDescription":"Cutting-edge vision-language model excelling in retrieving text and metadata from images.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-parse-2-0.jpg","labels":"$39:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"updatedDate":"2026-09-11T21:29:41.274Z","bias":"# Bias Subcard\n\n## Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing:\n\nNone of the Above\n\n## Measures taken to mitigate against unwanted bias:\n\nNone of the Above\n\n## Bias Metric (If Measured):\n\nNot Applicable","canGuestDownload":true,"createdDate":"2026-09-11T21:29:41.274Z","description":"$41","explainability":"$42","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$43","safetyAndSecurity":"# Safety & Security Subcard\n\n## Model Application Field(s):\n\nImage Understanding/Object Detection\n\n## Describe the life critical impact (if present).\n\nNot Applicable\n\n## Use Case Restrictions:\n\n**GOVERNING TERMS:** Use of this trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of the model is governed by the [OpenMDW License Agreement, version 1.1](https://github.com/OpenMDW/OpenMDW/blob/main/1.1/LICENSE.OpenMDW-1.1).\n\n## Model and dataset restrictions:\n\nThe Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to."},"endpointName":"nemotron-parse-2.0","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/nemotron-parse","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-parse for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"NVIDIA Software and Model Evaluation License Agreement","url":"https://developer.download.nvidia.com/licenses/NVIDIA_Software_and_Model_Evaluation_License_Agreement.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using document content extraction models"}],"paths":{"/chat/completions":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters.","operationId":"invokeFunction","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"},"example":{"model":"nvidia/nemotron-parse-2.0","messages":[{"role":"user","content":[{"type":"text","text":""},{"type":"image_url","image_url":{"url":"https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg"}}]}],"max_tokens":1024,"temperature":0}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object.\n","path":"create","examples":[{"name":"document1","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/nemoretriever-parse/example_1.jpg","prompt":""},"requestJson":"{\n \"model\": \"nvidia/nemotron-parse-2.0\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"<%- input.prompt %>\"\n },\n {\n \"type\": \"image_url\",\n \"image_url\": {\n \"url\": \"<%- input.image %>\"\n }\n }\n ]\n }\n ],\n \"max_tokens\": 1024,\n \"temperature\": 0\n}\n","responseJson":"$44"},{"name":"document2","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/nemotron-parse/example_2.jpg","prompt":""},"requestJson":"{\n \"model\": \"nvidia/nemotron-parse-2.0\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"<%- input.prompt %>\"\n },\n {\n \"type\": \"image_url\",\n \"image_url\": {\n \"url\": \"<%- input.image %>\"\n }\n }\n ]\n }\n ],\n \"max_tokens\": 1024,\n \"temperature\": 0\n}\n","responseJson":"$45"}],"templates":[{"title":"Default","requestEjs":{"python":"$46","langChain":"$47","node.js":"$48","curl":"$49"},"response":"{\n \"id\": \"...\",\n \"object\": \"chat.completion\",\n \"created\": ...,\n \"model\": \"nvidia/nemotron-parse-2.0\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\",\n \"stop_reason\": null\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 5,\n \"total_tokens\": 35,\n \"completion_tokens\": 30\n },\n \"prompt_logprobs\": null\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array","contains":{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},"minContains":0,"maxContains":1}],"title":"Content","description":"The contents of the message.\n
To pass media (only with role=`user`):\n
- Use content parts. Text is passed with `type`=`text`.\n
- Images are passed with `type`=`image_url`; set `image_url.url` to an image URL or a base64 data URI like `data:image/{format};base64,{base64encodedimage}`.\n
- The model processes a single document image per request: include at most one `image_url` part.\n
For `system` and `assistant` roles, the object list format is not supported.\n"}},"type":"object","required":["role","content"],"title":"NIMLLMChatCompletionMessage"},"NIMLLMChatCompletionRequest":{"properties":{"messages":{"items":{"$ref":"#/components/schemas/NIMLLMChatCompletionMessage"},"type":"array","minItems":1,"title":"Messages","description":"A list of messages comprising the conversation so far."},"model":{"type":"string","title":"Model","description":"The model to use.","default":"nvidia/nemotron-parse-2.0"},"frequency_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Frequency Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.","default":0},"max_tokens":{"anyOf":[{"type":"integer","maximum":8192,"minimum":1},{"type":"null"}],"title":"Max Tokens","description":"The maximum number of tokens that can be generated.","default":3500},"presence_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Presence Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.","default":0},"seed":{"anyOf":[{"type":"integer","maximum":9223372036854776000,"minimum":-9223372036854776000},{"type":"null"}],"title":"Seed","description":"Changing the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant."},"stop":{"anyOf":[{"type":"string"},{"items":{"type":"string"},"type":"array"},{"type":"null"}],"title":"Stop","description":"Sequences where the API will stop generating further tokens."},"stream":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Stream","description":"If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`","default":false},"temperature":{"anyOf":[{"type":"number","maximum":2,"minimum":0},{"type":"null"}],"title":"Temperature","description":"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.","default":0},"top_p":{"anyOf":[{"type":"number","maximum":1,"exclusiveMinimum":0},{"type":"null"}],"title":"Top P","description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.","default":1}},"additionalProperties":false,"type":"object","required":["messages","model"],"title":"NIMLLMChatCompletionRequest"},"NIMVLMChatCompletionContentPartImage":{"properties":{"image_url":{"$ref":"#/components/schemas/ImageURL"},"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type"}},"type":"object","required":["image_url","type"],"title":"NIMVLMChatCompletionContentPartImage"},"NIMVLMChatCompletionContentPartText":{"properties":{"text":{"type":"string","title":"Text"},"type":{"type":"string","enum":["text"],"const":"text","title":"Type"}},"type":"object","required":["text","type"],"title":"NIMVLMChatCompletionContentPartText"},"Role":{"type":"string","enum":["assistant","user"],"title":"Role"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","default":0}},"additionalProperties":false,"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","nvcfFunctionId":"7a0655e9-0b6e-4741-a2a5-b6c2eeb96cca","createdDate":"2026-09-11T21:29:41.519Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-parse-2.0","termsOfUse":"GOVERNING TERMS: Use of this trial service is governed by the NVIDIA API Trial Terms of Service. Use of the model is governed by the OpenMDW License Agreement, version 1.1.\n","showUnavailableBanner":false,"cta":"$39:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","playground":{"type":"hidden"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$4a"}],"modelCapability":{"functionCalling":true,"structuredOutput":false,"reasoning":true}},"artifactName":"nemotron-parse-2.0"},"isLoginRequired":true,"playgroundElement":"$4b","publisherName":"nvidia","searchParams":{},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/nemotron-parse-2.0","aliases":["/nvidia/nemotron-parse-2.0/experience"]},{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/nvidia/nemotron-parse-2.0/modelcard","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/nvidia/nemotron-parse-2.0/deploy","aliases":"$undefined"}]}]}]}]]}]] 3a:["$","$L4c",null,{"spec":"$39:0:props:children:1:props:children:props:children:props:endpointSpec"}]