OpenAI Python SDK

This release introduces support for the 'phase' field in the API and includes fixes related to its enum definition and documentation.

Version 2.23.0 introduces new model options for realtime API interactions, specifically gpt-realtime-1.5 and gpt-audio-1.5.

This release introduces websocket support for the responses API and includes various documentation enhancements across several API endpoints.

This release introduces new API capabilities for container network policy and skills, alongside fixes for a memory leak in structured output parsing and webhook compatibility.

Version 2.20.0 introduces support for images within the batch API operations.

This release introduces new API capabilities for skills and hosted shell functionality. It also includes internal dependency bumps.

This release introduces the addition of the context_management field to API responses.

Release 2.17.0 introduces new API fields for shell calls and image generation actions, alongside client improvements for JSON encoding. Several minor client-side bug fixes related to web search actions were also addressed.

This release introduces support for binary request streaming and includes general API updates. Notably, the Assistants API endpoints have been marked as deprecated.

This release introduces support for new audio model slugs and standardizes model parameters to accept strings, alongside a fix for asynchronous file handling in patch requests.

This release introduces support for the gpt-image-1.5 model and includes internal client updates and CI improvements for the Agents SDK.

Release 2.12.0 introduces general API updates, including support for sora-2 dated slugs and modifications to the grader input list.

This release introduces support for the gpt 5.2 API model.

Release 2.10.0 introduces a breaking change making the 'model' parameter mandatory for the responses/compact endpoint and improves type inference for pyright users.

Release 2.9.0 introduces support for the gpt-5.1-codex-max model and includes critical bug fixes for stream management and client configuration handling.

A patch release focused on aligning input and output item types for TypeScript compatibility.

Release 2.8.0 introduces support for the gpt 5.1 model and provides bug fixes for Pydantic v1 method signatures.

This release drops support for Python 3.8 and introduces compatibility fixes for Python 3.14.

This patch release fixes a bug regarding the nullability of logprobs in the API response.

Release 2.7.0 introduces Realtime API token limits and hybrid search ranking options, while fixing resource leaks in uploads and stream handling.

This is a patch release focused on documentation updates and internal code cleanup for custom translations.

This release introduces a new input token count field to API responses and includes internal updates to the OpenAPI specification.

Minor release featuring an API update and a version bump for the httpx-aiohttp dependency.

This release introduces support for the gpt-4o-transcribe-diarize model on the audio transcriptions endpoint.

Release 2.3.0 introduces new comparison filters for the API and updates the jiter dependency to support Python 3.14.

This release introduces new API features for Dev Day 2025 and includes a bug fix to include chatkit in the beta resource.

This release introduces support for Realtime API calls to the OpenAI Python SDK.

This patch release includes a bug fix for MCP tool calls, adding missing status and approval request ID fields.

This major release introduces support for multi-modal function call outputs (images and files) and BatchUsage, while changing the output type of tool call response items from string to a union type.

This patch release addresses a compatibility bug with older versions of Pydantic when handling additional fields.

This release introduces support for the gpt-5-codex model to the OpenAI Python SDK.

This patch release focuses on fixing MCP tool naming and updating OpenAPI definitions for conversations, alongside minor internal script improvements.

This release introduces the reasoning_text field to the API and updates internal type handling for optional parameters from NotGiven to Omit.

This release introduces type updates for conversations and reasoning effort in evaluations, alongside internal Pydantic dependency maintenance.

This is a maintenance release focused on internal API documentation refactoring, specification updates, and test simplification.

This patch release includes minor documentation and type updates for the realtime API, along with internal test simplifications.

This patch release focuses on correcting type definitions for the Realtime API following its General Availability.

This release introduces the API shape for RealtimeGA and includes internal codegen updates.

This patch release focuses on internal maintenance by moving mypy configurations to the pyproject.toml file.

This release introduces support for dynamic API keys via callables and enhances forward compatibility with Pydantic v3.

This release introduces support for the new gpt-realtime models in the OpenAI API.

Version 1.104.2 is a maintenance patch that restores type aliases for web search tools to fix potential type-checking regressions.

This patch release includes manual updates to the ResponseInputAudio API components.

This release focuses on internal type safety improvements by replacing List[str] with SequenceNotStr in various parameter definitions.

This release introduces updates to the Realtime API and fixes a bug where parameters were missing from the stream() method.

This release introduces web search filters to the API and fixes a bug related to modern type syntax usage.

This release introduces support for the /v1/conversations endpoint and adds connector support for MCP tools.

This is a maintenance release focused on internal CI improvements, specifically setting up breaking change detection.

This patch release updates the internal API representation for the verbosity parameter in Chat Completions to ensure accurate data shaping.

This patch release reverts an accidental deletion of response text configuration types to ensure type consistency.

This release introduces new text parameters and expiration options to the API.

This patch release specifically addresses a typing issue within the ChatCompletionMessageToolCall class.

Release 1.99.8 focuses on internal test improvements and reverts a breaking change to the ChatCompletionMessageToolCallUnion type.

Release 1.99.7 focuses on fixing type definitions by reverting ChatCompletionMessageToolCallParam to a TypedDict.

This release focuses on improving type exports for tool calls and internal maintenance updates.

This patch release fixes a bug regarding the location of the verbosity parameter within the Responses class.

This patch release focuses on type definition fixes, specifically reverting ChatCompletionToolParam to a TypedDict and renaming internal chat completion tool types.

This patch release restores the missing 'output_text' field to response objects.

This release introduces support for GPT-5 and associated API features, alongside a fix for tool-related type definitions.

This patch release addresses a bug regarding internal event imports.

This release introduces support for file upload requests and adds missing prompt cache parameters to the client.

This release includes manual updates to the API.

This patch release includes internal refactoring of the streaming client for future-proofing and adds VS Code project settings.

This patch release focuses on improving parsing logic for metadata and extra field types, alongside internal API event shape refinements.

This release includes manual updates to the API definitions.

This patch release updates the internal Realtime API specifications.

This release focuses on internal maintenance, including environment call-out cleanup and updates to the Realtime API specifications.

This patch release fixes a bug in the client where Content-Type headers were incorrectly being sent during GET requests.

This release introduces file_url support to the API and includes minor fixes for event IDs and README rendering on PyPI.

Release 1.94.0 improves API error messaging specifically for missing embeddings.

This patch release addresses a bug in the parsing logic to correctly handle nested discriminated unions.

This maintenance release adds official support for Python 3.13 and updates the internal h11 dependency constraint.

This patch release focuses on fixing missing arguments in vector store file polling methods and response parsing, alongside CI improvements.

This release introduces CLI support for managing fine-tuning jobs.

This patch release fixes an encoding error triggered by empty API keys and updates documentation regarding macOS requirements for realtime examples.

This maintenance release removes an unsupported 'api' property from the library.

This patch release focuses on internal client synchronization for streaming and parsing methods, alongside documentation updates for Webhooks.

This release introduces support for webhooks and deep research, while promoting the 'stream' and 'parse' client methods from beta to stable.

This release updates the API shapes for usage tracking and the code interpreter tool.

Version 1.90.0 updates the API to make the 'model' and 'inputs' parameters optional during response creation.

This release introduces support for the aiohttp library within the client and includes minor bug fixes for the test suite.

This release includes manual API updates and internal CI improvements.

This release introduces support for reusable prompt IDs and fixes an issue with service_tier updates in the beta chat completions client.

This release adds support for the o3-pro model IDs to the OpenAI API.

This release introduces support for tools and structured outputs in evaluations and fixes an issue to allow raw responses within the parse() method.

This release introduces support for new Realtime and Audio models along with expanded session options and internal type name updates.

This release introduces a new follow_redirects option and binary content support for container files, while deprecating the Assistants API and fixing code interpreter interfaces.

This patch release fixes a bug in response re-serialization and updates internal release workflows.

This release introduces new streaming helpers for background API responses and fixes an issue where Azure image edit endpoints were not correctly identified as deployment endpoints.

This release introduces support for a new container endpoint in the OpenAI API.

Version 1.80.0 introduces new API tools and includes minor documentation grammar improvements.

This release focuses on expanding the Evals and Assistants API schemas and includes a fix for the audio transcription endpoint.

This patch release focuses on internal maintenance, fixing linting errors and enabling support for direct resource imports.

This release introduces support for the reinforcement fine-tuning API and optimizes performance through lazy imports for resources and module-level clients.

Version 1.77.0 introduces support for reasoning encryption and new image sizes, alongside bug fixes for whitespace parsing.

This patch release includes internal API specification cleanup and maintenance chores.

This patch release improves the handling of JSON-related content-type headers and includes internal CI updates for the repository.

This release introduces support for new image models and improves compatibility with Pydantic v1 by making ModelField annotation checks more robust.

This release adds support for the new o3 and o4-mini model identifiers to the API.