About Microsoft
Explore research at Microsoft, a site featuring the impact of research along with publications, products, downloads, and research careers.
Microsoft Research conducts fundamental science and technology research across a spectrum of research areas. With labs around the globe we pursue breakthroughs across the computing and AI stack to accelerate discovery across sciences and advance the frontiers of computing and AI to create new foundations for others to build upon.
Artificial intelligence | Search & information retrieval | Human language technologies | Human-computer interaction | Computer vision | Graphics & multimedia | Audio & acoustics
Medical, health & genomics | Economics | Social sciences | Technology for emerging markets | Ecology & environment
Website ↗Documentation ↗
Source ↗ · 2026-11-12T02:17:04.301031227ZazureFoundry/azureml-ai-frontiers/CxrReportGen@1
Grounded chest X-ray report generation model that produces radiology findings with bounding box annotations
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
azureFoundry/azureml-ai-frontiers-p/CxrReportGen-Premium@1
The CXRReportGen Premium model is built on Qwen2.5-VL-7B-Instruct and is designed to help applications interpret complex chest X-ray imaging studies and generate radiology-style findings and impression.
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
azureFoundry/azureml-ai-frontiers-p/CxrReportGen-Premium@2
The CXRReportGen Premium model is designed to help applications interpret complex chest X-ray imaging studies and generate radiology-style findings and impression.
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
vercelAIGatewayCatalog/microsoft/microsoft-decision-1
Microsoft Decision-1 is a text decision model from Microsoft AI for classification, routing, and evaluation. It answers yes/no questions, selects among predefined options, and scores inputs against custom criteria, returning calibrated probabilities and confidence values. With su
- Context window
- 32,768
- Input modalities
- text
- Output modalities
- text
- Capabilities
- decision
Inference prices
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@1
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@2
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@3
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@4
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@5
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@6
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@7
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@8
*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning
azureFoundry/azureml/deepseek-r1-distill-llama-8b-cuda-gpu@4
This model is an optimized version of DeepSeek-R1-Distill-Llama-8B to enable local inference on CUDA GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/deepseek-r1-distill-llama-8b-generic-cpu@4
This model is an optimized version of DeepSeek-R1-Distill-Llama-8B to enable local inference on CPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of th
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/deepseek-r1-distill-llama-8b-generic-gpu@4
This model is an optimized version of DeepSeek-R1-Distill-Llama-8B to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of th
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/deepseek-r1-distill-qwen-14b-cuda-gpu@4
This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on CUDA GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/deepseek-r1-distill-qwen-14b-generic-cpu@4
This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on CPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of th
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/deepseek-r1-distill-qwen-14b-generic-gpu@4
This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of th
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text