Releasesby GlyphOpenAI 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.
Also shipped Sep 3, 2026OpenAI in September 2026 →
Conversational analytics now supports questions about market basket analysis
Conversational analytics now supports questions about market basket analysis . This feature is generally available (GA).
External lineage (General availability)
External lineage is now generally available and is no longer in Preview .
Restricted Session Scope for agents (General availability)
With this release, Restricted Session Scope (RSS) is generally available. An RSS is a privilege ceiling that limits what an agent can do on behalf of a user. It intersects with RBAC and never grants privileges the user doesn't already have through their roles.
Share metric views with OpenSharing (Beta)
You can now share metric views with Databricks users in other metastores or accounts using OpenSharing. See Add metric views to a share and Read shared metric views .
Genie One enhancements
- Ask Genie button hidden when unsupported : In embedded dashboards, the Ask Genie button is now hidden when it isn't supported. See Ask Genie in embedded dashboards . Push notifications for scheduled tasks (Public Preview) : The Genie mobile app can now send push notifications for scheduled tasks to iOS devices. See Push notifications .
Web search in Genie One (Beta)
Genie One can now search the public web to answer questions that need current information, such as recent releases, third-party documentation, or news. Genie One decides when to search and cites the sources it uses, showing each as a link you can open. See Search the web .
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 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.
OpenAI API supports IPv6 connections to api.openai.com
Connections to api.openai.com can now use IPv6.
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 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 project API keys support expiration dates
Project API keys can now be created with an expiration date, and admins can enforce a maximum key lifetime at the organization or project level.