Releasesby GlyphOpenAI API separates slow_down 429s from server_is_overloaded 503s
Traffic ramping too quickly now returns 429 slow_down, while temporary model overload returns 503 server_is_overloaded. Honor Retry-After when present, otherwise use exponential backoff.
Also shipped Sep 2, 2026OpenAI in September 2026 →
Openflow Connector for Jira Cloud: Core flow (General availability)
The Atlassian Jira Cloud (Core) flow is now generally available. The flow ingests Jira Cloud issues, projects, users, and related data into dedicated Snowflake tables with explicit schemas. It supports optional deletion tracking and parallel ingestion across projects. The Atlassian Jira Cloud (Agile) flow remains in Public Preview .
Git Folder Serverless is in Beta
You can now use Git Folder Serverless to share serverless compute and a pyproject.toml -managed environment across notebooks and files in a Git folder. See Git Folder Serverless .
AlloyDB real-time BigQuery access adds limit pushdown and runtime projects
The preview feature pushes some LIMIT and OFFSET clauses down to BigQuery to cut network transfer, and optional runtime projects let queries run and bill compute separately from the owning project.
OpenJDK 11 will no longer be supported as of January 14, 2027
OpenJDK 11 will no longer be supported as of January 14, 2027 . Customer-hosted instances must upgrade to OpenJDK 21 .
Gemini Enterprise: Gemini 3.8 Flash available in Global, US, and EU regions
Gemini 3.8 Flash is generally available (GA) in the global , us , and eu regions. For more information, see: Manage features on the web app Data residency for Gemini Enterprise Standard and Plus Editions and Gemini Notebook Enterprise
Gemini 3.8 Flash is generally available
Gemini 3.8 Flash is now generally available (GA) and available for production use. For more information on 3.8 Flash, see the model page .
More from OpenAI APIEvery OpenAI API release →
OpenAI releases GPT-6 Astra for complex end-to-end work
GPT-6 Astra targets reasoning, coding, computer use, research and document creation. When migrating, note it lacks the none reasoning effort, custom temperature, top_p and logprobs.
OpenAI Responses API adds async tool calling and mid-turn steering for GPT-6 Astra
New long-running work controls let GPT-6 Astra keep working while tools run, accept extra instructions mid-response over WebSockets, and change reasoning effort mid-conversation while preserving the cached prompt.
OpenAI API supports IPv6 connections to api.openai.com
Connections to api.openai.com can now use IPv6.
OpenAI API mTLS and X.509 workload identity federation are GA
Mutual TLS and X.509 workload identity federation can be configured in the Platform console, with access governed by organization roles and permissions, enabling keyless authentication.
OpenAI Prompt Cache Diagnostics is generally available in the Responses API
For GPT-5.6 and later, developers can compare cache reuse against a previous response, see reasons for cache misses and follow guidance to improve cache hit rates.
OpenAI releases GPT Image 2.5 Sunburst and GPT Image 2.5 Flare
Sunburst targets precise image editing and Flare fast everyday generation, both via the Image API and Responses image tool. They support new xhigh and max quality settings at GPT Image 2 token rates.
OpenAI GPT-Rosalind is GA for approved life sciences research
gpt-rosalind-research is available through the trusted-access program at $5 input, $0.50 cached input and $25 output per 1M tokens. Billing begins October 5, 2026.
OpenAI deprecates whisper-1 and gpt-4o transcribe models, shutdown February 26, 2027
whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize shut down February 26, 2027; migrate to gpt-live-transcribe or gpt-transcribe. The Assistants API shut down August 26, 2026.