OpenAI o3-mini

Version: 2025-01-31

OpenAI•Last updated November 2025

o3-mini includes the o1 features with significant cost-efficiencies for scenarios requiring high performance.

Reasoning

Multilingual

Coding

Azure Direct Models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all as part of one Azure AI Foundry platform.
Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Azure AI Foundry; reducing integration effort.
Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

Key capabilities

About this model

This model is provided through the Azure OpenAI Service.

Key model capabilities

o1 added advanced image analysis capabilities with the new version. Enhance your prompts and context with images for additional insights.
o3-mini follows o1 mini but adds the features supported by o1 like function calling and tools.
Complex Code Generation: Capable of generating algorithms and handling advanced coding tasks to support developers.
Advanced Problem Solving: Ideal for comprehensive brainstorming sessions and addressing multifaceted challenges.
Complex Document Comparison: Perfect for analyzing contracts, case files, or legal documents to identify subtle differences.
Instruction Following and Workflow Management: Particularly effective for managing workflows requiring shorter contexts.
o4-mini: The most efficient reasoning model in the o model series, well suited for agentic solutions. Now generally available.
o3: The most capable reasoning model in the o model series, and the first one to offer full tools support for agentic solutions. Now generally available.
o3-mini: A faster and more cost-efficient option in the o3 series, ideal for coding tasks requiring speed and lower resource consumption.
o1: The most capable model in the o1 series, offering enhanced reasoning abilities. Now generally available.
o1-mini: A faster and more cost-efficient option in the o1 series, ideal for coding tasks requiring speed and lower resource consumption.
Supports both System message and the new Developer message to improve upgrade experience.
Reasoning effort as in high, medium, and low. It controls whether the model thinks "less" or "more" in terms of applying cognitive reasoning.
Structured outputs and functions/tools.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

For example, o1 can be used by healthcare researchers to annotate cell sequencing data, by physicists to generate complicated mathematical formulas needed for quantum optics, and by developers in all fields to build and execute multi-step workflows.

Out of scope use cases

o1 model does not include all the features available in other models.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

o1 added advanced image analysis capabilities with the new version. Enhance your prompts and context with images for additional insights.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

Context window: 200K, Max Completion Tokens: 100K

Optimizing model performance

The provider has not supplied this information.

Additional assets

The following documents are applicable:

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

OpenAI has incorporated additional safety measures into the o1 models, including new techniques to help the models refuse unsafe requests. These advancements make the o1 series some of the most robust models available. OpenAI measures safety is by testing how well models continue to follow its safety rules if a user tries to bypass them (known as "jailbreaking"). In OpenAI's internal tests, GPT-4o scored 22 (on a scale of 0-100) while o1-preview model scored 84. You can read more about this in the OpenAI's system card and research post .

Responsible AI considerations

Safety techniques

Safety evaluations

OpenAI measures safety is by testing how well models continue to follow its safety rules if a user tries to bypass them (known as "jailbreaking"). In OpenAI's internal tests, GPT-4o scored 22 (on a scale of 0-100) while o1-preview model scored 84. You can read more about this in the OpenAI's system card and research post .

Known limitations

o1 model does not include all the features available in other models.

Acceptable use

Acceptable use policy

The provider has not supplied this information.

Quality and performance evaluations

Source: OpenAI In OpenAI's internal tests, GPT-4o scored 22 (on a scale of 0-100) while o1-preview model scored 84.

Benchmarking methodology

Source: OpenAI OpenAI measures safety is by testing how well models continue to follow its safety rules if a user tries to bypass them (known as "jailbreaking").