o3-deep-research
o3-deep-research
Version: 2025-06-26
OpenAI•Last updated July 2025
The o3 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.
Reasoning
Multilingual
Agents

o3-deep-research model: Powering agentic capability to create comprehensive reports like a research analyst.

The o3-deep-research model is specifically designed to perform automated detailed analysis of knowledge sources and create detailed research reports. Available in the agents platform, developers can build agents that deeply plan, analyze, and synthesize information from across the web—automate complex research tasks, generate transparent, auditable outputs, and seamlessly compose multi-step workflows with other tools and agents in Azure AI Foundry.

Key Capabilities

  • Handles text, images and PDFs as part of its web-based research tasks
  • 200K context length and 100K completion tokens
  • Outputs its thinking as reasoning summary as it searches and synthesizes information
  • Delivers a detailed research report at the end of the request session

Benefits

  • Automate web-scale research using a best-in-class research model grounded with Bing Search, with every insight traceable and source-backed.
  • Programmatically build agents that can be invoked by apps, workflows, or other agents—turning deep research into a reusable, production-ready service.
  • Orchestrate complex workflows: Compose Deep Research agents with other Foundry Agent Service connectors to automate reporting, notifications, and more.
  • Ensure enterprise governance: With Azure AI Foundry, customers get full control and transparency over how research is run and used.

Limitations

o3-deep-research model does not include all the features available in other models.

Model provider

This model is provided through the Azure OpenAI Service.

Relevant documents

The following documents are applicable:

Content Filtering

Prompts and completions are passed through a default configuration of Azure AI Content Safety classification models to detect and prevent the output of harmful content. Learn more about Azure AI Content Safety . Additional classification models and configuration options are available when you deploy an Azure OpenAI model in production; learn more .
Model Specifications
Context Length200000
LicenseCustom
Training DataMay 2024
Last UpdatedJuly 2025
Input TypeText,Image
Output TypeText
PublisherOpenAI
Languages27 Languages
Quick Start
Sign in to get startedView DocumentationAzure Support