openai/openai-python

The official Python library for the OpenAI API

What it solves

This library provides a streamlined, type-safe way for Python developers to interact with the OpenAI REST API, eliminating the need to manually handle raw HTTP requests to access OpenAI's models and services.

How it works

It acts as a Python wrapper around the OpenAI REST API, generated from an OpenAPI specification. It uses HTTPX2 for synchronous and asynchronous communication and provides Pydantic models for response fields and TypedDicts for request parameters to ensure type safety and and autocomplete in editors.

Who it’s for

Python developers building applications that integrate OpenAI's AI models, including those requiring high-concurrency asynchronous requests or secure enterprise-grade authentication.

Highlights

  • Multi-modal Support: Access to text generation, vision (image input), and a Realtime API for low-latency audio and text conversations via WebSockets.
  • Flexible Authentication: Supports standard API keys, workload identity authentication for cloud providers (Kubernetes, Azure, GCP), and X.509 mutual TLS.
  • Developer Experience: Includes auto-paginating iterators for list methods and built-in webhook verification tools.
  • Async Capabilities: Full support for asynchronous requests using AsyncOpenAI, with an optional aiohttp transport for improved performance.
  • Streaming: Support for Server-Sent Events (SSE) to stream model responses in real time.

Related

  • Project
    openai/openai-node

    Official OpenAI Node/TS SDK for calling OpenAI’s REST API – supports text, vision, streaming, realtime, Azure/Bedrock adapters, workload‑identity auth, and webhook verification.

  • Project
    openai/openai-java

    Official Java client library for OpenAI’s REST API, offering sync/async, streaming, workload‑identity auth, and optional Bedrock support.

  • Project
    openai/openai-go

    Official Go SDK for OpenAI’s API, offering typed helpers for chat/completions, streaming, tool calls, structured outputs, and WebSocket‑based real‑time interactions.

  • Dispatch
    OpenAI Python SDK Migration to HTTPX2

    The OpenAI Python SDK has transitioned from httpx to HTTPX2 to ensure API stability and shift TLS certificate verification to the operating system trust store.

  • Project
    openai/openai-cli

    The official OpenAI command-line interface for interacting with the OpenAI REST API, enabling developers to manage models, generate content, and handle admin tasks directly from the terminal.