← ChatGPT & Codex changelog

OpenAI API — September, 2026

This release introduces GPT-6 Astra, our most capable model designed for comprehensive end-to-end work across reasoning, coding, computer use, and research. Significant new controls for long-running agent workflows are now available in the Responses API, including asynchronous tool calling, mid-turn steering, and dynamic reasoning effort adjustments. Migrating to Astra requires using the Responses API for tools and notes changes to supported parameters. Additionally, API error codes for rate limiting and server overload have been updated, alongside new IPv6 support for API connections.

Added

  • Released GPT-6 Astra, our most capable model, built for the hardest end-to-end work.
  • Added new controls for long-running work with GPT-6 Astra in the Responses API:

Changed

  • Use GPT-6 Astra for reasoning, coding, computer use, research, and document creation. It combines these capabilities to carry complex tasks from an initial request to a finished result, using the context and tools you provide.
  • Key changes to consider when migrating:
  • GPT-6 Astra does not support the none reasoning effort level.
  • GPT-6 Astra does not support custom temperature or top_p values or log probabilities (logprobs).
  • Tool calling requires the Responses API. If you use tools with Chat Completions, follow the Responses migration guide.
  • Misalignment monitoring asynchronously checks for potential issues during agent work in supported Responses API requests. Checks can trigger safety alerts or stop a conversation for review.
  • Start with Using GPT-6 Astra for capabilities, prompting, and migration guidance. Explore computer use for browser and desktop workflows, and see pricing for available inference tiers.
  • Async tool calling: Let the model continue working while your application runs function or custom tools, then return results as they become available.
  • Mid-turn steering: Send additional instructions while a response is in progress over WebSockets, so the model can incorporate corrections or changing requirements.
  • Change reasoning effort mid-conversation: Increase effort for difficult work or reduce it for routine follow-ups while preserving the cached prompt prefix.
  • Updated API errors so applications can distinguish traffic that increases too quickly from temporary model overload.
  • Traffic that increases too quickly can return a 429 error with the slow_down code. Temporary model overload returns a 503 error with the server_is_overloaded code. Both responses may include Retry-After. When the header is present, wait at least as long as it specifies before retrying. If it's missing, use exponential backoff. See the error codes guide and rate limits guide.
  • Connections to api.openai.com can now use IPv6.