Azure OpenAI

OpenAI releases GPT-image-1.5 model with enhanced editing capabilities

GPT-image-1.5 is OpenAI's latest cutting-edge image generation model. It features improved performance, quality, editing controls, and face preservation. In editing mode, the model supports high input_fidelity and adding/removing one aspect of the input image while retaining others. Request access: limited access model application Key model capabilities: Includes all capabilities of GPT-image-1: Text to image generation Image to image generation (editing) Inpainting High quality image generations, up to 1024x1536 and 1536x1024 pixels Face preservation Follow the image generation how-to guide to get started with this model. Automatic speech recognition (ASR) model update gpt-4o-mini-transcribe-2025-12-15 Improved transcription accuracy and robustness for real-time scenarios. ~50% lower word error rate (WER) than previous gpt-4o-transcribe-mini on English benchmarks Improves multilingual performance across Japanese, Indic, and other languages. Reduced hallucinations on silence by up to 4×, making it a more reliable choice for noisy environments and real-world audio streams. Input remains audio, with text as output, and deployment is API-only. Realtime-mini (speech-to-speech) model update gpt-realtime-mini-2025-12-15 Feature parity with full gpt-realtime model in instruction-following and function-calling. Input and output are both audio, and is be API-only. Text to speech model update gpt-4o-mini-tts-2025-12-15 New benchmark for multilingual speech synthesis, More natural, human-like speech with fewer artifacts and improved speaker similarity. Input is text, output is audio, and deployment is API-only. October 2025 Realtime API support for SIP The Realtime API now supports SIP, enabling telephony connections to realtimeapi. For more information, see the Realtime SIP documentation . GPT-4o audio model released The gpt-4o-transcribe-diarize speech to text model is released. This is an Automatic Speech Recognition (ASR) model that converts spoken language into text in re

Date not specified

OpenAI releases gpt-4o 2024-11-20 with data zone deployments

gpt-4o-2024-11-20 is now available for global standard deployment in: East US East US 2 North Central US South Central US West US West US 3 Sweden Central NEW data zone provisioned deployment type Data zone provisioned deployments are available in the same Azure OpenAI resource as all other Azure OpenAI deployment types but allow you to use Azure global infrastructure to dynamically route traffic to the data center within the Microsoft defined data zone with the best availability for each request. Data zone provisioned deployments provide reserved model processing capacity for high and predictable throughput using Azure infrastructure within Microsoft specified data zones. Data zone provisioned deployments are supported on gpt-4o-2024-08-06 , gpt-4o-2024-05-13 , and gpt-4o-mini-2024-07-18 models. For more information, see the deployment types guide . Next steps Learn more about the underlying models that power Azure OpenAI .

Date not specified

OpenAI GPT Realtime API 2024-12-17: New Features & Model Release

The gpt-4o-realtime-preview model version 2024-12-17 is available for global deployments in East US 2 and Sweden Central regions . Use the gpt-4o-realtime-preview version 2024-12-17 model instead of the gpt-4o-realtime-preview version 2024-10-01-preview model for real-time audio interactions. Added support for prompt caching with the gpt-4o-realtime-preview model. Added support for new voices. The gpt-4o-realtime-preview models now support the following voices: alloy , ash , ballad , coral , echo , sage , shimmer , verse . Rate limits are no longer based on connections per minute. Rate limiting is now based on RPM (requests per minute) and TPM (tokens per minute) for the gpt-4o-realtime-preview model. The rate limits for each gpt-4o-realtime-preview model deployment are 100 K TPM and 1 K RPM. During the preview, Azure AI Foundry portal and APIs might inaccurately show different rate limits. Even if you try to set a different rate limit, the actual rate limit is 100 K TPM and 1 K RPM. For more information, see the GPT real-time audio quickstart and the how-to guide . December 2024 o1 reasoning model released for limited access The latest o1 model is now available for API access and model deployment. Registration is required, and access will be granted based on Microsoft's eligibility criteria . Customers who previously applied and received access to o1-preview , don't need to reapply as they're automatically on the wait-list for the latest model. Request access: limited access model application To learn more about the advanced o1 series models see, getting started with o1 series reasoning models . Region availability Model Region o1 (Version: 2024-12-17) East US2 (Global Standard) Sweden Central (Global Standard) Preference fine-tuning (preview) Direct preference optimization (DPO) is a new alignment technique for large language models, designed to adjust model weights based on human preferences. Unlike reinforcement learning from human feedback (RLHF), DPO doesn't r

Date not specified

OpenAI Releases GPT-4.5 Preview and Expands GPT-4o Model Capabilities

The latest GPT model that excels at diverse text and image tasks is now available on Azure OpenAI. For more information on model capabilities, and region availability see the models documentation . Stored completions API Stored completions allow you to capture the conversation history from chat completions sessions to use as datasets for evaluations and fine-tuning. o3-mini data zone standard deployments o3-mini is now available for global standard, and data zone standard deployments for registered limited access customers. For more information, see our reasoning model guide . gpt-4o mini audio released The gpt-4o-mini-audio-preview ( 2024-12-17 ) model is the latest audio completions model. For more information, see the audio generation quickstart . The gpt-4o-mini-realtime-preview ( 2024-12-17 ) model is the latest real-time audio model. The real-time models use the same underlying GPT-4o audio model as the completions API, but is optimized for low-latency, real-time audio interactions. For more information, see the real-time audio quickstart . For more information about available models, see the models and versions documentation . January 2025 o3-mini released o3-mini ( 2025-01-31 ) is the latest reasoning model, offering enhanced reasoning abilities. For more information, see our reasoning model guide . GPT-4o audio completions The gpt-4o-audio-preview model is now available for global deployments in East US 2 and Sweden Central regions . Use the gpt-4o-audio-preview model for audio generation. The gpt-4o-audio-preview model introduces the audio modality into the existing /chat/completions API. The audio model expands the potential for AI applications in text and voice-based interactions and audio analysis. Modalities supported in gpt-4o-audio-preview model include: text, audio, and text + audio. For more information, see the audio generation quickstart . Note The Realtime API uses the same underlying GPT-4o audio model as the completions API, but is optimized

Date not specified

Azure OpenAI releases GPT-4.1, GPT-4o models, and Responses API

GPT 4.1 and GPT 4.1-nano are now available. These are the latest models from Azure OpenAI. GPT 4.1 has a 1 million token context limit. For more information, see the models page . gpt-4o audio models released New audio models powered by GPT-4o are now available. The gpt-4o-transcribe and gpt-4o-mini-transcribe speech to text models are released. Use these models via the /audio and /realtime APIs. The gpt-4o-mini-tts text to speech model is released. Use the gpt-4o-mini-tts model for text to speech generation via the /audio API. For more information about available models, see the models and versions documentation . March 2025 Responses API & computer-use-preview model The Responses API is a new stateful API from Azure OpenAI. It brings together the best capabilities from the chat completions and assistants API in one unified experience. The Responses API also adds support for the new computer-use-preview model, which powers the Computer use capability. For access to computer-use-preview registration is required, and access will be granted based on Microsoft's eligibility criteria . Customers who have access to other limited access models still need to request access for this model. Request access: computer-use-preview limited access model application For more information on model capabilities, and region availability see the models documentation . Playwright integration demo code . Provisioned spillover (preview) Spillover manages traffic fluctuations on provisioned deployments by routing overages to a designated standard deployment. To learn more about how to maximize utilization for your provisioned deployments with spillover, see Manage traffic with spillover for provisioned deployments (preview) . Specify content filtering configurations In addition to the deployment-level content filtering configuration, we now also provide a request header that allows you specify your custom configuration at request time for every API call. For more information, see Use conten

Date not specified

OpenAI releases GPT-image-1.5 model with improved image generation capabilities

Latest image generation model with improved performance, quality, editing controls, and face preservation. Supports high input_fidelity editing, inpainting, and generates images up to 1536x1024 pixels. Requires limited access application.

Date not specified

OpenAI releases gpt-realtime-mini-2025-12-15 speech-to-speech model

Feature parity with full gpt-realtime model in instruction-following and function-calling. API-only deployment with both audio input and output.

Date not specified

OpenAI releases GPT-image-1.5 model with enhanced image generation capabilities

Latest image generation model with improved performance, quality, editing controls, and face preservation. Supports high input_fidelity editing with capability to add/remove aspects while retaining others. Up to 1536x1024 pixel resolution.

Date not specified

OpenAI gpt-realtime-mini model update — feature parity with full gpt-realtime model

gpt-realtime-mini-2025-12-15 now has feature parity with full gpt-realtime model for instruction-following and function-calling. Audio input/output, API-only deployment.

Date not specified

OpenAI releases gpt-4o-mini-transcribe-2025-12-15 ASR model with 50% lower WER

Improved transcription accuracy with ~50% lower word error rate than previous version on English benchmarks. Enhanced multilingual performance (Japanese, Indic) and 4x reduced hallucinations on silence for noisy environments. API-only deployment.

Date not specified

OpenAI releases GPT-image-1.5 model with advanced editing controls

New cutting-edge image generation model featuring improved performance, quality, editing controls, face preservation, high input fidelity, and support for adding/removing image aspects. Supports up to 1024x1536 and 1536x1024 pixel generation. Limited access model.

Date not specified

OpenAI releases GPT-Realtime-1.5 and GPT-Audio-1.5 models

New gpt-realtime-1.5-2026-02-23 and gpt-audio-1.5-2026-02-23 models available with improved instruction following, multi-lingual support, and tool calling while maintaining low-latency real-time interactions for voice-first applications.

Date not specified

OpenAI releases gpt-realtime-1.5 and gpt-audio-1.5 models for voice-first apps

New gpt-realtime-1.5-2026-02-23 and gpt-audio-1.5-2026-02-23 models available with improved instruction following, multi-lingual support, and tool calling for voice-first applications. Available through chat completion APIs in Microsoft Foundry.

Date not specified

OpenAI releases GPT-5-Codex Model for Code Generation

New coding model designed for use with Codex CLI and Visual Studio Code extension. Requires registration.

Date not specified

OpenAI Adds PII Detection Content Filter

New built-in content filter to identify and block sensitive personally identifiable information in LLM outputs.

Date not specified

OpenAI Releases GPT-4o Audio Transcription and Diarization Model

New speech-to-text model with real-time transcription across 100+ languages and speaker diarization capabilities.

Date not specified

Azure OpenAI Releases New Speech Models & Sora Updates

Updates to automatic speech recognition, real-time speech, and text-to-speech models with improved multilingual performance and lower error rates.

Date not specified

Azure Communication Services Incident in Australia East & Southeast Asia

Ongoing investigation of an alert affecting Azure Communication Services in Australia East and Southeast Asia regions. Additional details will be provided as they become available.

Date not specified

Partial Service Degradation in West US Region — Multiple Azure Services Affected

Intermittent service unavailability and delays in monitoring/log data for multiple Azure services. Affected services include Web Apps, Container Registry, IoT Hub, Kubernetes Service, and others. Most services recovering.

Date not specified

Partial Service Degradation in West US Azure Region

Intermittent service unavailability and delays affecting multiple Azure services including Web Apps, Application Insights, Azure Confidential Compute, and others. Restoration efforts mostly complete with some resources requiring manual recovery.

Date not specified