Microsoft

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 ↗ · 2026-11-12T02:17:04.301031227Z

669 indexed models

669 matching models

gpt-oss-20b-cuda-gpu · azureml v1

azureFoundry/azureml/gpt-oss-20b-cuda-gpu@1

This model is an optimized version of gpt-oss-20b to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** Apache-2.0 - **License Description:** Use of this model is subject to th

Maximum output
2,048
Input modalities
text
Output modalities
text

gpt-oss-20b-generic-cpu · azureml v1

azureFoundry/azureml/gpt-oss-20b-generic-cpu@1

This model is an optimized version of gpt-oss-20b to enable local inference on CPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** Apache-2.0 - **License Description:** Use of this model is subject to th

Maximum output
2,048
Input modalities
text
Output modalities
text

gpt-oss-20b-generic-gpu · azureml v1

azureFoundry/azureml/gpt-oss-20b-generic-gpu@1

This model is an optimized version of gpt-oss-20b to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** Apache-2.0 - **License Description:** Use of this model is subject to th

Maximum output
2,048
Input modalities
text
Output modalities
text

MagenticBrain 14B · azureml-cua-ai-frontiers-p v1

azureFoundry/azureml-cua-ai-frontiers-p/MagenticBrain-14B@1

An 14-B orchestrator model for MagenticLite

Context window
32,768
Maximum output
4,096
Input modalities
text
Output modalities
text
Capabilities
toolCalling

MAI-Code-1.1-Flash · azure-mai v2026-09-15

azureFoundry/azure-mai/mai-code-1.1-flash@2026-09-15

MAI-Code-1.1-Flash offers Quality coding assistance, optimized for efficiency. Tackle everyday engineering tasks faster and more affordably.

Context window
256,000
Maximum output
64,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, visionInput

MAI Code 1.1 Flash · azureml v1

azureFoundry/azureml/MAI-Code-1.1-Flash-On-Device@1

MAI Code 1.1 Flash

Context window
256,000
Maximum input
128,000
Maximum output
128,000
Input modalities
text
Output modalities
text
Capabilities
toolCalling

MAI Code 1.1 Flash · azureml v2

azureFoundry/azureml/MAI-Code-1.1-Flash-On-Device@2

# MAI Code 1.1 Flash, optimized for on-device inference ## Overview MAI Code 1.1 Flash is a coding-optimized mixture-of-experts model from Microsoft AI, designed for agentic software development workflows. The model is optimized for efficient local inference while supporting l

Context window
256,000
Maximum input
128,000
Maximum output
128,000
Input modalities
text
Output modalities
text
Capabilities
toolCalling

MAI-Code-2-Flash · azure-mai v2026-11-17

azureFoundry/azure-mai/mai-code-2-flash@2026-11-17

MAI-Code-2-Flash is Microsoft AI's fast coding model with a 1M-token context window, built for long-running agentic coding in real repositories.

Context window
1,000,000
Maximum output
128,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, toolCalling, visionInput

MAI-Image-2.5 · azure-mai v2026-06-02

azureFoundry/azure-mai/MAI-Image-2.5@2026-06-02

Built for creatives, delivering enhanced photorealism at scale.

Context window
131,072
Maximum output
4,096
Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

MAI-Image-2.5-Flash · azure-mai v2026-06-02

azureFoundry/azure-mai/MAI-Image-2.5-Flash@2026-06-02

Built for creatives, delivering enhanced photorealism at scale.

Context window
131,072
Maximum output
4,096
Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

MAI-Image-2.5-Pro · azure-mai v2026-06-19

azureFoundry/azure-mai/MAI-Image-2.5-Pro@2026-06-19

Built for creatives, delivering enhanced photorealism at scale.

Context window
131,072
Maximum output
4,096
Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

mai-image-2.6

cheaperInference/mai-image-2.6

Context window
128,000
Maximum output
65,536
Output modalities
image
Capabilities
imageOutput

MAI-Image-2.6

vercelAIGatewayCatalog/microsoft/mai-image-2.6

MAI-Image-2.6 is a diffusion-based generative model designed for both high-quality text-to-image synthesis and precise, controllable image-to-image editing. It progressively transforms random noise into a coherent image aligned with a given text prompt, leveraging a flow-matching

Input modalities
text
Output modalities
image
Capabilities
imageOutput

Inference prices

MAI-Image-2.6 · azure-mai v2026-07-31

azureFoundry/azure-mai/MAI-Image-2.6@2026-07-31

Built for creatives, delivering enhanced photorealism at scale.

Context window
32,000
Maximum output
4,096
Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

mai-image-2.6-flash

cheaperInference/mai-image-2.6-flash

Context window
128,000
Maximum output
65,536
Output modalities
image
Capabilities
imageOutput

MAI-Image-2.6-Flash

vercelAIGatewayCatalog/microsoft/mai-image-2.6-flash

MAI-Image-2.6 is a diffusion-based generative model designed for both high-quality text-to-image synthesis and precise, controllable image-to-image editing. It progressively transforms random noise into a coherent image aligned with a given text prompt, leveraging a flow-matching

Input modalities
text
Output modalities
image
Capabilities
imageOutput

Inference prices

MAI-Image-2.6-Flash · azure-mai v2026-07-31

azureFoundry/azure-mai/MAI-Image-2.6-Flash@2026-07-31

Built for creatives, delivering enhanced photorealism at scale.

Context window
32,000
Maximum output
4,096
Input modalities
text, image
Output modalities
image
Capabilities
imageOutput, multimodal, visionInput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace