Microsoft logo

Microsoft models

Microsoft develops the Phi family of small open-weight language models and, through its Microsoft AI division, the in-house MAI models for text, code, images, voice and transcription.

Redmond, United StatesFounded 1975microsoft.com

Releases
42
Open weights
20
Latest
Oct 27, 2026

October 2026

4 releases
  1. ImageProprietary

    MAI-Image-2.7

    MAI-Image-2.7 is Microsoft AI's latest image editing model, launched in preview. It improves on MAI-Image-2.6 for restyling, relighting, text and symbol edits, and restoring or enhancing existing images.

    Modalities
    text, image → image
    At launch
    Consumer app
    • Launched in preview on Arena, Artificial Analysis and MAI Playground
    • Starts with image editing; text-to-image generation is listed as coming soon
    • Succeeds MAI-Image-2.6 with an editing-first launch
    Source: MAI Image 2.7 debuts above GPT Image 2.5 Flare on Artificial Analysis and #3 on Arena
  2. SpeechProprietary

    MAI-Transcribe-2-Streaming

    MAI-Transcribe-2-Streaming is Microsoft AI's first streaming speech-to-text model, delivering low-latency, real-time transcripts for conversational voice agents in 60 languages with automatic, continuous language detection.

    Modalities
    audio → text
    At launch
    API, Consumer app, Cloud platforms
    • Real-time transcription in 60 languages
    • Automatic, continuous language detection
    • Available through Microsoft Foundry, MAI Playground, Vercel and Azure Voice Live
    Source: Our first streaming transcription model debuts at no. 1 on Artificial Analysis
  3. SpeechProprietary

    MAI-Voice-2.1

    MAI-Voice-2.1 is Microsoft AI's text-to-speech model announced alongside MAI-Transcribe-2-Streaming for conversational voice agents. Microsoft calls it its strongest multilingual text-to-speech model, now covering 23 languages and 26 locales.

    Modalities
    text → audio
    At launch
    API, Consumer app, Cloud platforms
    • Supports 23 languages and 26 locales
    • Available through Microsoft Foundry, MAI Playground, OpenRouter, Vercel and Azure Voice Live
    • Released with a faster MAI-Voice-2.1-Flash variant
    Source: Our first streaming transcription model debuts at no. 1 on Artificial Analysis
  4. SpeechProprietary

    MAI-Voice-2.1-Flash

    MAI-Voice-2.1-Flash is a faster, high-volume variant of Microsoft AI's MAI-Voice-2.1 text-to-speech model, built for latency-sensitive voice agent workloads while supporting the same languages and cross-language speakers.

    Modalities
    text → audio
    At launch
    API, Consumer app, Cloud platforms
    • Supports the same 23 languages as MAI-Voice-2.1
    • Available through Microsoft Foundry, MAI Playground, OpenRouter, Vercel and Azure Voice Live
    • Announced alongside MAI-Transcribe-2-Streaming
    Source: Our first streaming transcription model debuts at no. 1 on Artificial Analysis

September 2026

2 releases
  1. ImageProprietary

    MAI-Image-2.6-Flash

    MAI-Image-2.6-Flash is a faster variant of Microsoft AI's MAI-Image-2.6, built for latency-sensitive, high-throughput image generation and editing workloads. It launched in Microsoft Foundry alongside developer access to MAI-Image-2.6.

    Modalities
    text, image → image
    At launch
    API
    • Supports multi-image reference editing, web grounding and dynamic aspect ratios
    • Available to developers in Microsoft Foundry
    • Generally available in Foundry per an October 27, 2026 update
    Source: Pushing the quality-cost frontier with MAI-Image-2.6
  2. SpeechProprietary

    MAI-Transcribe-2

    MAI-Transcribe-2 is Microsoft AI's batch speech-to-text model, adding speaker diarization, word-level timestamps and configurable transcription styles, with accuracy across 60 languages, up from 43 in MAI-Transcribe-1.5.

    Modalities
    audio → text
    At launch
    API, Consumer app, Cloud platforms
    • Covers 60 languages
    • Adds speaker diarization, word-level timestamps, keyword biasing and automatic language identification
    • Available through Microsoft Foundry, MAI Playground and OpenRouter
    Source: MAI-Transcribe-2 is the fastest, most accurate and cheapest speech recognition model in the world

August 2026

2 releases
  1. CodingProprietary

    MAI-Code-1.1-Flash

    MAI-Code-1.1-Flash is Microsoft AI's updated small coding model for GitHub Copilot, focused on CLI and .NET tasks and using fewer tokens per task than MAI-Code-1-Flash. A quantized on-device version followed in October 2026.

    Modalities
    text → text
    Context
    250K context
    At launch
    Consumer app
    • In production in GitHub Copilot at launch
    • October 7, 2026 update added a 3-bit quantized version that runs locally with a full 256K context window
    • Local use recommended on devices with more than 120GB of RAM
    Source: MAI-Code-1.1-Flash: Better, faster, at a quarter of the cost
  2. ImageProprietary

    MAI-Image-2.6

    MAI-Image-2.6 is Microsoft AI's text-to-image and image editing model succeeding MAI-Image-2.5, with stronger text rendering, portraits, 3D imagery and commercial photorealistic output. Developer access in Microsoft Foundry followed on September 4, 2026.

    Modalities
    text, image → image
    At launch
    API
    • Brought to developers in Microsoft Foundry on September 4, 2026
    • Generally available in Foundry per an October 27, 2026 update
    • Supports multiple image references, web grounding and control over format and resolution
    Source: MAI Image 2.6 launches at No. 2 on Arena ahead of Google, Meta and xAI

July 2026

2 releases
  1. ImageProprietary

    MAI-Image-2.5-Pro

    MAI-Image-2.5-Pro is Microsoft AI's highest-fidelity image model at launch, released in public preview for hero imagery, detailed editing and precise in-image text rendering, alongside the existing MAI-Image-2.5 and 2.5-Flash models.

    Modalities
    text, image → image
    At launch
    API
    • Released in public preview
    • Targets hero imagery, detailed editing and precise in-image text rendering
    • Sits above MAI-Image-2.5 and MAI-Image-2.5-Flash as the highest-fidelity option
    Source: Introducing MAI-Image-2.5-Pro and MAI-Voice-2-Flash
  2. SpeechProprietary

    MAI-Voice-2-Flash

    MAI-Voice-2-Flash is a faster, lower-cost variant of Microsoft AI's MAI-Voice-2 text-to-speech model for high-volume voice experiences. First previewed at Microsoft Build in June 2026, it entered public preview in July 2026.

    Modalities
    text → audio
    At launch
    API
    • Released in public preview on July 23, 2026
    • Microsoft says it is 2x faster than MAI-Voice-2
    • Announced as coming soon on June 2, 2026
    Source: Introducing MAI-Image-2.5-Pro and MAI-Voice-2-Flash

June 2026

6 releases
  1. CodingProprietary

    MAI-Code-1-Flash

    MAI-Code-1-Flash is Microsoft AI's inference-efficient agentic coding model, trained inside the agent tooling GitHub Copilot uses and rolled out to GitHub Copilot users in Visual Studio Code. It uses adaptive thinking to scale reasoning to task difficulty.

    Modalities
    text → text
    Parameters
    5B active
    At launch
    Consumer app
    • Rolled out to GitHub Copilot individual users in VS Code
    • Has 5 billion active parameters
    • Trained without distillation from third-party models
    Source: Introducing MAI-Code-1-Flash
  2. ImageProprietary

    MAI-Image-2.5

    MAI-Image-2.5 is Microsoft AI's image model for high-quality text-to-image generation and precise, localized image editing, with face and identity consistency across edits. It launched in Foundry and in PowerPoint.

    Modalities
    text, image → image
    At launch
    API, Enterprise
    • Available to developers in Microsoft Foundry
    • Live in PowerPoint and rolling out to OneDrive for photo editing
    • Launched with a faster MAI-Image-2.5-Flash variant
    Source: MAI-Image-2.5 launches at No. 2 for image editing on Arena
  3. ImageProprietary

    MAI-Image-2.5-Flash

    MAI-Image-2.5-Flash is a faster, lower-cost variant of Microsoft AI's MAI-Image-2.5 for scalable production image generation and editing workloads, launched in Microsoft Foundry on the same day as MAI-Image-2.5.

    Modalities
    text, image → image
    At launch
    API
    • Supports both text-to-image generation and image editing
    • Available in Microsoft Foundry
    • Part of the seven-model MAI launch at Microsoft Build 2026
    Source: MAI-Image-2.5 launches at No. 2 for image editing on Arena
  4. ReasoningProprietary

    MAI-Thinking-1

    MAI-Thinking-1 is Microsoft AI's flagship reasoning model, a medium-sized sparse mixture-of-experts model trained from scratch without distillation from third-party models, aimed at software engineering, math and enterprise tasks.

    Modalities
    text → text
    Parameters
    MoE: about 1T total, 35B active
    At launch
    API
    • One of seven in-house models Microsoft AI announced on June 2, 2026
    • Public preview in Microsoft Foundry from August 12, 2026
    • Sparse mixture-of-experts with about 1T total and 35B active parameters
    Source: Building a hill-climbing machine: Launching seven new MAI models
  5. SpeechProprietary

    MAI-Transcribe-1.5

    MAI-Transcribe-1.5 is Microsoft AI's multilingual speech-to-text model, expanding language coverage from 25 to 43 languages and adding keyword biasing for domain-specific terminology, and is being integrated into Copilot, Teams, GitHub and Dynamics 365.

    Modalities
    audio → text
    At launch
    API, Enterprise
    • Covers 43 languages, up from 25 in MAI-Transcribe-1
    • Adds keyword biasing for user-supplied domain terms
    • Available in Microsoft Foundry
    Source: Introducing MAI-Transcribe-1.5
  6. SpeechProprietary

    MAI-Voice-2

    MAI-Voice-2 is Microsoft AI's text-to-speech model, expanding from English-only to 15 languages with emotion tags and zero-shot voice prompting from short reference audio, protected by consent guardrails.

    Modalities
    text, audio → audio
    At launch
    API
    • Supports 15 languages
    • Zero-shot voice prompting from 5 to 60 seconds of reference audio
    • Available in Microsoft Foundry and being integrated into VS Code and Dynamics 365 Contact Center
    Source: Introducing MAI-Voice-2

May 2026

1 release
  1. MultimodalOpen weights

    Fara1.5

    Fara1.5 is Microsoft's second generation of open computer use agent models, released in 4B, 9B and 27B sizes and fine-tuned from Qwen3.5 on synthetic web-task trajectories generated by the FaraGen1.5 pipeline.

    Modalities
    text, image → text
    Context
    256K context
    Parameters
    4B, 9B, 27B
    License
    MIT
    At launch
    Open weights, API
    • Released in 4B, 9B and 27B sizes with a 262,144-token context length
    • Supervised fine-tuned from Qwen3.5 base models
    • 27B version also offered on Microsoft Foundry
    Source: microsoft/Fara1.5-27B on Hugging Face

April 2026

2 releases
  1. ImageProprietary

    MAI-Image-2-Efficient

    MAI-Image-2-Efficient is a faster, lower-cost version of Microsoft AI's MAI-Image-2 text-to-image model, aimed at high-volume production work such as product shots, marketing creatives and batch pipelines.

    Modalities
    text → image
    At launch
    API, Consumer app
    • Available in Microsoft Foundry and MAI Playground at launch
    • Rolling out across Copilot and Bing
    • Handles short-form in-image text such as headlines and labels
    Source: MAI-Image-2-Efficient: Flagship Quality, 41% Lower Cost
  2. SpeechProprietary

    MAI-Transcribe-1

    MAI-Transcribe-1 is Microsoft AI's first speech-to-text model, a multilingual transcription model supporting 25 languages and built for noisy, real-world audio such as meetings, call centers and voice agents.

    Modalities
    audio → text
    At launch
    API, Consumer app
    • Supports 25 languages
    • Available in Microsoft Foundry and MAI Playground
    • Launched alongside Foundry availability for MAI-Voice-1 and MAI-Image-2
    Source: State of the Art Speech Recognition with MAI-Transcribe-1

March 2026

2 releases
  1. ImageProprietary

    MAI-Image-2

    MAI-Image-2 is Microsoft AI's second in-house text-to-image model, focused on photorealism, reliable in-image text and detailed scene generation. It launched in MAI Playground and began rolling out to Copilot and Bing Image Creator.

    Modalities
    text → image
    At launch
    API, Consumer app
    • Available in MAI Playground at launch
    • API access first for select customers, then in Microsoft Foundry from April 2, 2026
    • Rolling out to Copilot and Bing Image Creator
    Source: Introducing MAI-Image-2: for limitless creativity
  2. MultimodalOpen weights

    Phi-4-reasoning-vision-15B

    Phi-4-reasoning-vision-15B is Microsoft's open-weight multimodal reasoning model, pairing a SigLIP-2 vision encoder with the Phi-4-Reasoning backbone. It reasons step by step for math and science and answers perception tasks directly.

    Modalities
    text, image → text
    Context
    16K context
    Parameters
    15B
    License
    MIT
    At launch
    Open weights, API
    • 15B parameters with a 16,384-token context length
    • Built on the Phi-4-Reasoning backbone with a SigLIP-2 vision encoder
    • Available on Microsoft Foundry, Hugging Face and GitHub
    Source: Phi-4-reasoning-vision and the lessons of training a multimodal reasoning model

November 2025

1 release
  1. MultimodalOpen weights

    Fara-7B

    Fara-7B is Microsoft's first agentic small language model for computer use, taking screenshots and text context as input and directly predicting thoughts and grounded actions to complete web tasks.

    Modalities
    text, image → text
    Context
    125K context
    Parameters
    7B
    License
    MIT
    At launch
    Open weights, API
    • 7B parameters with a 128K context length
    • Builds on Qwen 2.5 VL
    • Available on Hugging Face and Microsoft Foundry
    Source: microsoft/Fara-7B on Hugging Face

October 2025

1 release
  1. ImageProprietary

    MAI-Image-1

    MAI-Image-1 is Microsoft AI's first image generation model developed entirely in-house. It later became available in Bing Image Creator and in Copilot Audio Expressions Story Mode.

    Modalities
    text → image
    At launch
    Consumer app
    • Microsoft's first in-house text-to-image model
    • Added to Bing Image Creator and Copilot on November 4, 2025
    • Available in countries that can access Bing Image Creator and Copilot Labs
    Source: Introducing MAI-Image-1, debuting in the top 10 on LMArena

August 2025

2 releases
  1. LLMProprietary

    MAI-1-preview

    MAI-1-preview is Microsoft AI's first in-house foundation language model, a mixture-of-experts model released for public testing on LMArena and rolled out for certain text use cases in Copilot.

    Modalities
    text → text
    At launch
    Consumer app
    • Mixture-of-experts model pre-trained and post-trained on about 15,000 NVIDIA H100 GPUs
    • Public testing on LMArena, with API access for trusted testers
    • Rolled out to certain Copilot text use cases
    Source: Two in-house models in support of our mission
  2. SpeechProprietary

    MAI-Voice-1

    MAI-Voice-1 is Microsoft AI's first in-house speech generation model, producing expressive audio for single and multi-speaker scenarios. It launched in Copilot Daily and Podcasts and later reached Microsoft Foundry.

    Modalities
    text → audio
    At launch
    Consumer app, API
    • Generates a minute of audio in under a second on a single GPU, per Microsoft
    • Launched in Copilot Daily, Copilot Podcasts and Copilot Labs
    • Added to Microsoft Foundry with custom voice creation on April 2, 2026
    Source: Two in-house models in support of our mission

July 2025

1 release
  1. ReasoningOpen weights

    Phi-4-mini-flash-reasoning

    Phi-4-mini-flash-reasoning is a 3.8B open Microsoft model for math reasoning on edge and mobile devices, built on the new SambaY decoder-hybrid-decoder architecture that combines Mamba, sliding window attention and gated memory units.

    Modalities
    text → text
    Context
    64K context
    Parameters
    3.8B
    License
    MIT
    At launch
    Open weights, API, Cloud platforms
    • Uses the SambaY architecture with a Gated Memory Unit
    • Supports a 64K token context length
    • Available on Azure AI Foundry, NVIDIA API Catalog and Hugging Face
    Source: Reasoning reimagined: Introducing Phi-4-mini-flash-reasoning

April 2025

3 releases
  1. ReasoningOpen weights

    Phi-4-mini-reasoning

    Phi-4-mini-reasoning is a 3.8B open Microsoft model for math reasoning, fine-tuned from Phi-4-mini with synthetic data generated by DeepSeek-R1, and aimed at edge, mobile and educational applications.

    Modalities
    text → text
    Context
    125K context
    Parameters
    3.8B
    License
    MIT
    At launch
    Open weights, API
    • 3.8B parameters with a 128K token context length
    • Fine-tuned on synthetic data generated by DeepSeek-R1
    • ONNX version for Copilot+ PCs made available May 15, 2025
    Source: One year of Phi: Small language models making big leaps in AI
  2. ReasoningOpen weights

    Phi-4-reasoning and Phi-4-reasoning-plus

    Phi-4-reasoning is a 14B open-weight reasoning model fine-tuned from Phi-4 on reasoning demonstrations, released with Phi-4-reasoning-plus, which adds reinforcement learning to use more inference-time compute.

    Modalities
    text → text
    Context
    32K context
    Parameters
    14B
    License
    MIT
    At launch
    Open weights, API
    • Both models have 14B parameters and a 32K token context length
    • Phi-4-reasoning-plus is further trained with reinforcement learning
    • Available on Azure AI Foundry and Hugging Face under the MIT license
    Source: One year of Phi: Small language models making big leaps in AI
  3. ReasoningOpen weights

    MAI-DS-R1

    MAI-DS-R1 is an open-weights version of DeepSeek R1 post-trained by the Microsoft AI team to respond to more previously blocked topics and reduce risk while keeping the original model's reasoning capabilities.

    Modalities
    text → text
    License
    MIT
    At launch
    Open weights, API
    • Post-trained from DeepSeek-R1
    • Released on Azure AI Foundry and Hugging Face
    • Retired from Microsoft Foundry on February 27, 2026
    Source: Introducing MAI-DS-R1

February 2025

2 releases
  1. Small modelOpen weights

    Phi-4-mini

    Phi-4-mini is a 3.8B dense, decoder-only Microsoft language model with grouped-query attention and a 200,000-token vocabulary, designed for speed and efficiency, with support for function calling and long inputs.

    Modalities
    text → text
    Context
    125K context
    Parameters
    3.8B
    License
    MIT
    At launch
    Open weights, API, Cloud platforms
    • Supports sequences up to 128,000 tokens
    • 200,000-token vocabulary with grouped-query attention
    • Available in Azure AI Foundry, Hugging Face and the NVIDIA API Catalog
    Source: Empowering innovation: The next generation of the Phi family
  2. MultimodalOpen weights

    Phi-4-multimodal

    Phi-4-multimodal is Microsoft's first multimodal Phi language model, a 5.6B model that processes speech, vision and text in a single unified model rather than a pipeline of separate models.

    Modalities
    text, image, audio → text
    Context
    125K context
    Parameters
    5.6B
    License
    MIT
    At launch
    Open weights, API, Cloud platforms
    • 5.6B parameters with a 128K token context length
    • Handles speech, vision and text in one model
    • Available in Azure AI Foundry, Hugging Face and the NVIDIA API Catalog
    Source: Empowering innovation: The next generation of the Phi family

December 2024

1 release
  1. Small modelOpen weights

    Phi-4

    Phi-4 is a 14B Microsoft small language model specializing in complex reasoning, particularly math, with gains attributed to synthetic training data, curated organic data and improved post-training methods.

    Modalities
    text → text
    Context
    16K context
    Parameters
    14B
    License
    MIT
    At launch
    Open weights, API
    • 14B parameter dense decoder-only model with a 16K token context length
    • Announcement updated January 8, 2025, listing availability on Azure AI Foundry and Hugging Face
    • Weights released under the MIT license
    Source: Introducing Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

August 2024

3 releases
  1. Small modelOpen weights

    Phi-3.5-mini

    Phi-3.5-mini is a 3.8B open Microsoft model that updates Phi-3-mini with further multilingual pre-training and post-training, improving multilingual, multi-turn conversation and reasoning quality while supporting a 128K context.

    Modalities
    text → text
    Context
    125K context
    Parameters
    3.8B
    License
    MIT
    At launch
    Open weights, API
    • 3.8B dense model with a 128K token context length
    • Lists support for 23 languages
    • Offered as a serverless endpoint in Azure AI Studio
    Source: Discover the New Multi-Lingual, High-Quality Phi-3.5 SLMs
  2. LLMOpen weights

    Phi-3.5-MoE

    Phi-3.5-MoE is Microsoft's first mixture-of-experts Phi model, activating two of 16 experts per token for 6.6B active parameters, with multilingual support and a 128K context length.

    Modalities
    text → text
    Context
    125K context
    Parameters
    MoE: 16x3.8B experts, 6.6B active
    License
    MIT
    At launch
    Open weights
    • Mixture-of-experts with 16 experts and 6.6B active parameters
    • 128K token context length
    • Supports more than 20 languages
    Source: Discover the New Multi-Lingual, High-Quality Phi-3.5 SLMs
  3. MultimodalOpen weights

    Phi-3.5-vision

    Phi-3.5-vision is a 4.2B open multimodal Microsoft model that adds multi-frame image understanding to the Phi-3 vision line, enabling image comparison, multi-image summarization and video summarization.

    Modalities
    text, image → text
    Context
    125K context
    Parameters
    4.2B
    License
    MIT
    At launch
    Open weights
    • 4.2B parameters with a 128K token context length
    • Adds multi-frame image understanding and reasoning
    • Not optimized for multilingual use cases
    Source: Discover the New Multi-Lingual, High-Quality Phi-3.5 SLMs

May 2024

2 releases
  1. LLMOpen weights

    Phi-3-small and Phi-3-medium

    Phi-3-small (7B) and Phi-3-medium (14B) are larger instruction-tuned members of Microsoft's Phi-3 family, first announced with Phi-3-mini and made available on Azure and Hugging Face in May 2024.

    Modalities
    text → text
    Context
    125K context
    Parameters
    7B, 14B
    License
    MIT
    At launch
    Open weights, API, Cloud platforms
    • Phi-3-small offers 8K and 128K context variants
    • Phi-3-medium offers 4K and 128K context variants
    • First announced as coming soon on April 23, 2024
    Source: New models added to the Phi-3 family, available on Microsoft Azure
  2. MultimodalOpen weights

    Phi-3-vision

    Phi-3-vision is the first multimodal model in Microsoft's Phi-3 family, a 4.2B model that combines language and vision to reason over images, extract text and interpret charts and diagrams.

    Modalities
    text, image → text
    Context
    125K context
    Parameters
    4.2B
    License
    MIT
    At launch
    Open weights, API, Cloud platforms
    • 4.2B parameters with a 128K token context length
    • Weights released May 21, 2024
    • Optimized variants via ONNX Runtime, DirectML and NVIDIA NIM
    Source: New models added to the Phi-3 family, available on Microsoft Azure

April 2024

1 release
  1. Small modelOpen weights

    Phi-3-mini

    Phi-3-mini is a 3.8B instruction-tuned Microsoft small language model and the first of the Phi-3 family, offered in 4K and 128K context variants for on-device, latency-sensitive and cost-constrained uses.

    Modalities
    text → text
    Context
    125K context
    Parameters
    3.8B
    License
    MIT
    At launch
    Open weights, API, Cloud platforms
    • Available in 4K and 128K token context variants
    • Released on Azure AI Studio, Hugging Face and Ollama, and as an NVIDIA NIM microservice
    • Safety post-training included RLHF and red-teaming
    Source: Introducing Phi-3: Redefining what's possible with SLMs

December 2023

1 release
  1. Small modelOpen weights

    Phi-2

    Phi-2 is a 2.7B Microsoft Research base language model trained on 1.4T tokens of synthetic textbook-quality and filtered web data, scaled up from Phi-1.5 and offered as a platform for research.

    Modalities
    text → text
    Context
    2K context
    Parameters
    2.7B
    License
    MIT
    At launch
    Open weights, Cloud platforms
    • Base model without RLHF or instruction tuning
    • Trained for 14 days on 96 A100 GPUs
    • Released in the Azure AI Studio model catalog
    Source: Phi-2: The surprising power of small language models

November 2023

1 release
  1. LLMOpen weights

    Orca 2

    Orca 2 is a pair of Microsoft Research models fine-tuned from Llama 2 on synthetic data to teach smaller models different reasoning strategies, such as step-by-step processing and direct answering.

    Modalities
    text → text
    Parameters
    7B, 13B
    License
    Microsoft Research License
    At launch
    Open weights
    • Released in 7B and 13B sizes
    • Fine-tuned from Llama 2 base models
    • Not trained with RLHF for safety, per Microsoft Research
    Source: Orca 2: Teaching Small Language Models How to Reason

September 2023

1 release
  1. Small modelOpen weights

    phi-1.5

    phi-1.5 is a 1.3B Microsoft Research language model trained on the phi-1 data sources plus synthetic NLP texts, extending the textbook-quality data approach from Python coding to common sense reasoning and general language.

    Modalities
    text → text
    Parameters
    1.3B
    License
    MIT
    At launch
    Open weights
    • 1.3B parameters trained on 150B tokens
    • Excludes generic web-crawl sources such as Common Crawl
    • Released on Hugging Face under the MIT license
    Source: microsoft/phi-1_5 on Hugging Face

June 2023

1 release
  1. CodingOpen weights

    phi-1

    phi-1 is a 1.3B Microsoft Research model for Python code generation, trained on filtered code data and synthetic textbooks and exercises, introduced in the paper Textbooks Are All You Need.

    Modalities
    text → text
    Parameters
    1.3B
    License
    MIT
    At launch
    Open weights
    • 1.3B parameter Transformer specialized in Python
    • Trained on 54B tokens including synthetic textbooks generated with GPT-3.5
    • Weights published on Hugging Face under the MIT license
    Source: microsoft/phi-1 on Hugging Face

Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL.

Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

Citation

The AI Engineering Editors. "Microsoft models: release history and timeline." The AI Engineering, updated Oct 27, 2026. https://theaiengineering.com/releases/microsoft

HTML link

<a href="https://theaiengineering.com/releases/microsoft">Microsoft models: release history and timeline</a> (The AI Engineering)
Full dataset
1,167 releases from 55 labs
Coverage
to
Updated
License
CC BY 4.0
Publisher
The AI Engineering

Other labs