Skip to main content
OpenAI

The fastest and most powerful platform for building AI products

Build transformative AI experiences powered by industry-leading models and tools.

Flagship Models

Our GPT models

Powerful general purpose models for a variety of real-world tasks with a refreshed knowledge cutoff of June 2024.

GPT-4.1

Smartest model for complex tasks

  • Text and vision

  • 1M context length

  • Input: $2 | Output: $8
per 1M tokens

GPT-4.1 mini

Affordable model balancing speed and intelligence

  • Text and vision

  • 1M context length

  • Input: $0.40 | Output: $1.60 per 1M tokens

GPT-4.1 nano

Fastest, most cost-effective model for low-latency tasks

  • Text and vision

  • 1M context length

  • Input: $0.10 | Output: $0.40 per 1M tokens

Our reasoning models

These models spend more time thinking before producing a response, making them ideal for complex, multi-step problems.

OpenAI o3

Our most powerful reasoning model with leading performance on coding, math, science, and vision

  • Text and vision

  • Structured outputs

  • Function calling

  • 200k context length

  • Input $ 10 | Output $40 per 1M tokens

OpenAI o4-mini

Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision

  • Text and vision

  • Structured outputs

  • Function calling

  • 200k context length

  • Input $ 1.10 | Output $4.40 per 1M tokens

Access the power of our models with APIs

Responses API

A new API primitive for agents, combining the simplicity of Chat Completions with the ability to use built-in tools like the Assistants API.

API > Tabs > Responses API > Two Up > media item > asset

Extend model capabilities with built-in tools

Web Search

Enhance model responses with up-to-date and clearly cited answers from the web using the same capabilities as ChatGPT search.

API > Section > Extend model capabilities with built-in tools > two up (Web search) > media item > asset

File search

Build fast, accurate semantic search to augment model responses in just a few lines of code.

API > Section > Extend model capabilities with built-in tools > two up (File search) > media item > asset PLACEHOLDER

Computer use

Build computer-using agents powered by the same model behind Operator, currently in Research Preview.

API > Section > Extend model capabilities with built-in tools > two up (Computer use) > media item > asset PLACEHOLDER

Code interpreter

Get models to run code iteratively to solve challenging code and math problems, and generate charts.

API Test > Code interpreter > Media > Asset

Customize models for your needs

Fine-tuning

Customize a model’s existing knowledge and behavior for a specific task using text and images via supervised fine-tuning. Plus, use our Model Distillation tools to fine-tune smaller models on the outputs of more capable models.

API > Tabs 2 > Fine-Tuning API > Two Up > Media > Asset > Light

Build useful and reliable agents

The Agents SDK is a robust and lightweight orchestration framework for designing, building, and deploying agents with built-in observability to track and optimize performance.

API > Section > Build useful and reliable Agents GROUP > two-up (Agents SDK) > media item > asset

See what you can build in Playground

Explore our models and APIs in Playground without writing a single line of code.

API > Playground> Media > Asset

Enterprise-grade features for operating at scale

Security and data privacy

Administrative controls
  • Scope user roles and API keys to individual projects

  • Role-based access controls

  • Limit access to specific models within each project

  • Set billing and usage restrictions to avoid overages

  • View granular usage activity by project

Access to OpenAI expertise
  • Dedicated account team and prioritized support

  • Guidance on AI deployment and best practices from solutions architects

  • Opportunity to collaborate with researchers on building custom AI models