← ChatGPT & Codex changelog

OpenAI API — October, 2026

This release brings the Decisions API to general availability, offering 10x faster structured data output with expanded capabilities like image input and 400 questions per request. New Ultrafast modes for Agents and Responses APIs deliver significant speed improvements by reducing token generation time, complemented by prompt-to-voice creation and nine new natural voices for GPT-Live. API users gain more control with 12-hour prompt caching for cost savings and improved Agent sandbox performance with pre-warming and active-turn billing. Additionally, simplified usage tiers and new in-product HIPAA compliance support broaden enterprise appeal.

Source: official ChatGPT & Codex release notes. Summaries are written from the official notes; see how we work.

Added

  • Released prompt-to-voice for all API customers. Create a custom voice from a text description through the API or voice Playground, then reuse it in GPT-Live sessions. Creating a prompt-generated voice is free; speech generation uses regular GPT-Live session billing.
  • Added nine natural voices for GPT-Live: Nuri, Juni, and Flitz (German); Brise and Sillage (French); Nira (Hindi); Harema and Shida (Japanese); and Noeul (Korean).
  • Added Ultrafast mode to the Agents API. Set agent.service_tier to ultrafast with a supported model to reduce the time between generated tokens.
  • Added native Decisions integration in GPT-Live. Your app can act while your user is speaking or react to what Live says. Let Live call Decisions directly through native delegation, or trigger decisions as input or output transcript deltas arrive.
  • Added Ultrafast mode for GPT-6.1 Sol in the Responses API. Use gpt-6.1-sol with service_tier: "ultrafast" to reduce the time between generated output tokens. It is available to all API users, subject to rate limits, with global processing and US and EU data residency. See Ultrafast pricing.
  • Released the Decisions API in beta with gpt-6-luna. Turn text and images into typed answers 10x faster than the Responses API.
  • Added an in-product flow for HIPAA compliance support in API Organization settings > General. Admins of eligible organizations can now accept the standard Business Associate Agreement (BAA) and enable HIPAA compliance support for their organization. See the Help Center for eligibility, covered services, and configuration requirements.

Changed

  • The Decisions API is now generally available with gpt-6-luna. Cache shared input across requests for prompt-cache discounts, include images in individual question instructions, and pass structured data directly with input_json. Each request now supports up to 400 questions, increased from 200 in public beta. Review the changes since public beta.
  • You can now choose which service tiers projects can use in Platform settings. Organization settings can restrict service tiers for all projects. See service tier errors.
  • You can now choose 12-hour prompt caching in the API. 12-hour prompt caching keeps shared instructions, tools, and context cached longer to benefit from lower cached-input pricing, even when requests are hours apart. 12-hour cache writes cost 2.5x the input token price. Read more here.
  • OpenAI-hosted sandboxes in the Agents API now include the Artifact SDK and skills for creating and editing spreadsheets, presentations, and Word documents.
  • You can now pre-warm an OpenAI-hosted sandbox before attaching it to an Agents API session. Prewarming improves latency by creating and configuring the sandbox before a user finishes sending their message. This means the user doesn't have to wait for all this work to complete.
  • OpenAI-hosted sandbox compute is now billed during active turns. You no longer pay for idle time between turns.
  • Updated the chat-latest snapshot, which points to the latest model available in ChatGPT for Plus, Pro, Business and Enterprise users. We recommend leveraging the GPT-6 model family for production API usage, but feel free to use this model to test the latest improvements for chat use cases. The underlying model snapshot will be regularly updated. Read more here.
  • Simplified API usage tiers from five to three: Build, Launch, and Grow. Organizations automatically upgrade as total credit purchases reach tier minimums. See usage tiers for monthly usage limits and how to view rate limits for each model.

Get notified the minute the next ChatGPT & Codex release ships

AI Drops sends a push with a plain-English summary of every release.

Get AI Drops on the App Store