← ChatGPT & Codex changelog

OpenAI API — March, 2026

This release brings a suite of new models to the API, including the GPT-5.4 frontier model for professional work, GPT-5.4 Pro for complex problems, and the efficient GPT-5.4 mini and nano for high-volume, cost-sensitive applications. Model capabilities are enhanced with tool search, built-in computer use, and a 1M token context window with native compaction for advanced agent workflows. The Sora API sees major upgrades, adding reusable character references, extended generations up to 20 seconds, 1080p output for sora-2-pro, and a new dedicated video editing API. An image encoder fix also provides improved quality for specific GPT-5.4 image understanding use cases.

Added

  • Released GPT-5.4 mini and GPT-5.4 nano to the Chat Completions and Responses API. GPT-5.4 mini brings GPT-5.4-class capabilities to a faster, more efficient model for high-volume workloads, while GPT-5.4 nano is optimized for simple high-volume tasks where speed and cost matter most.
  • Added POST /v1/videos/edits for editing existing videos. This will replace POST /v1/videos/{video_id}/remix, which will be deprecated in 6 months. Learn more here.
  • Released GPT-5.4, our newest frontier model for professional work, to the Chat Completions and Responses API, and released GPT-5.4 Pro to the Responses API for tougher problems that benefit from more compute.
  • Released gpt-5.3-chat-latest to the Chat Completions and Responses API. This model points to the GPT-5.3 Instant snapshot currently used in ChatGPT. Read more here.

Changed

  • GPT-5.4 mini supports tool search, built-in computer use, and compaction. GPT-5.4 nano supports compaction, but does not support tool search or computer use.
  • Updated the gpt-5.3-chat-latest slug to point to the latest model currently used in ChatGPT.
  • Expanded the Sora API with reusable character references, longer generations up to 20 seconds, 1080p output for sora-2-pro, video extensions, and Batch API support for POST /v1/videos. 1080p generations on sora-2-pro are billed at $0.70 per second. Learn more here.
  • Also released:
  • Tool search in the Responses API, which lets models defer large tool surfaces until runtime to reduce token usage, preserve cache performance, and improve latency.
  • Built-in Computer use support in GPT-5.4 through the Responses API computer tool for screenshot-based UI interaction.
  • A 1M token context window and native Compaction support for longer-running agent workflows.

Fixed

  • Updated our image encoder to fix a small bug with input_image inputs in GPT-5.4. Some image understanding use cases may now see improved quality. No action is required.