← ChatGPT & Codex changelog

OpenAI API — February, 2026

This release brings a suite of powerful new models, including gpt-5.3-codex, GPT-Realtime-1.5, and gpt-audio-1.5, significantly expanding available capabilities. API users will experience a major performance improvement with GPT-5.2 and GPT-5.2-Codex models now running approximately 40% faster, enhancing application responsiveness. Additional advancements include WebSocket support, Skills integration, and a new Hosted Shell tool for the Responses API, alongside expanded input file type support and Batch API for image models, benefiting all developers seeking more robust and efficient AI interactions.

Added

  • Released phase to the Responses API. It labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer). Read more here.
  • Released gpt-5.3-codex to the Responses API. Read more here.
  • Launched WebSocket mode for the Responses API. Learn more here.
  • Released GPT-Realtime-1.5 to the Realtime API.
  • Released gpt-audio-1.5 to the Chat Completions API. Read more here.
  • Launched server-side compaction in the Responses API.
  • Launched support for Skills in the Responses API. We support Skills across both local execution and hosted container-based execution.
  • Launched a new Hosted Shell tool, as well as support for networking in containers.
  • Added support for application/json requests on /v1/images/edits for GPT image models. JSON requests use images (and optional mask) with image_url or file_id references instead of multipart uploads.

Changed

  • Expanded input_file support to accept more document, presentation, spreadsheet, code, and text file types. Learn more here.
  • Batch API is now supported for GPT Image models: gpt-image-1.5, chatgpt-image-latest, gpt-image-1, and gpt-image-1-mini.
  • Updated the gpt-5.2-chat-latest slug to point to the latest model currently used in ChatGPT.
  • We have optimized our inference stack for API customers and GPT-5.2 and GPT-5.2-Codex now run ~40% faster. Model and model weights are unchanged.