What changed in the OpenAI API

Added new controls for long-running work with GPT-6 Astra in the Responses API:

, our most capable model, built for the hardest end-to-end work.
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 
GPT-6 Astra does not support custom 
 values or log probabilities (
Tool calling requires the Responses API. If you use tools with Chat Completions, follow the 
Responses migration guide
 asynchronously checks for potential issues during agent work in supported Responses API requests. Checks can trigger safety alerts or stop a conversation for review.
 for capabilities, prompting, and migration guidance. Explore 
 for browser and desktop workflows, and see 
 for available inference tiers.
Added new controls for long-running work with GPT-6 Astra in the Responses API:
: Let the model continue working while your application runs function or custom tools, then return results as they become available.
: Send additional instructions while a response is in progress over WebSockets, so the model can incorporate corrections or cha

Updated API errors so applications can distinguish traffic that increases too quickly from temporary model overload.

Updated API errors so applications can distinguish traffic that increases too quickly from temporary model overload.
Traffic that increases too quickly can return a 
 code. Temporary model overload returns a 
 code. Both responses may include 
. When the header is present, wait at least as long as it specifies before retrying. If it's missing, use exponential backoff. See the 

with access controlled by your organization's roles and permissions.

 User lifecycle management 
X.509 workload identity federation
 are now generally available for the OpenAI API. Configure certificates and X.509 identity providers directly in the 
, with access controlled by your organization's roles and permissions.

The Assistants API shut down on August 26, 2026. Migrate to the Responses API and Conversations API using the

gpt-4o-transcribe-diarize
Announced the deprecation of 
gpt-4o-transcribe-diarize
. These models will shut down on February 26, 2027. Migrate to 
The Assistants API shut down on August 26, 2026. Migrate to the Responses API and Conversations API using the 

Meet Rosalind Workbench: Empowering every scientist to be their own research team

 ChatGPT Work local security 
 ChatGPT Work: usage and cost 
 Meet Rosalind Workbench: Empowering every scientist to be their own research team 

Automating repetitive work at OpenAI with Codex

 Automating repetitive work at OpenAI with Codex 
 Meet the winners of OpenAI Build Week 

API customers can now select regional processing for an individual request by using a prefixed domain with an API key from a project having Global geography. Existing eligibility, data retention contr

 Scaling cyber defenders with Daybreak 
API customers can now select regional processing for an individual request by using a prefixed domain with an API key from a project having Global geography. Existing eligibility, data retention control, endpoint, and model support requirements continue to apply. Learn more in the 
GPT-5.6 Sol now costs $4 per million input tokens and $20 per million output tokens, representing 20% lower input pricing and 33% lower output pricing. GPT-5.6 Sol’s promotional pricing is available at least through November 21, 2026. See 

Transparent backgrounds are now available in preview for

 on the OpenAI API platform. Track your cache hit rate over time, cache reads per write, and the breakdown of cache-read, cache-write, and uncached tokens to understand your caching efficiency and identify opportunities to improve. Filter metrics by model and service tier.
Transparent backgrounds are now available in preview for 
 in the Images API and the Responses API image generation tool. Set 
 does not support transparent backgrounds. Learn more in the 

Codex as a platform: build on the open agent harness

 Codex as a platform: build on the open agent harness 

Announced Ultrafast mode, a new API service tier for GPT-5.6 Sol that runs up to 14x faster than Standard processing. Available in limited preview to select customers. Sign up to receive updates on Ul

Announced Ultrafast mode, a new API service tier for GPT-5.6 Sol that runs up to 14x faster than Standard processing. Available in limited preview to select customers. Sign up to receive updates on Ultrafast mode 

Daybreak now offers two access tiers for approved defenders: Daybreak Blue and Daybreak Red. Use them to move from security findings to validated fixes in explicitly authorized engagements.

Daybreak now offers two access tiers for approved defenders: Daybreak Blue and Daybreak Red. Use them to move from security findings to validated fixes in explicitly authorized engagements.
Start with Daybreak Blue for most defensive security work. It provides access to general-purpose models such as GPT-5.6 Sol for vulnerability discovery, secure code review, detection engineering, incident response, malware analysis, and patch validation. Read more 
Daybreak Red provides separately approved access to purpose-trained models such as 
 for authorized vulnerability reproduction, exploit validation, penetration testing, red teaming, and complex system analysis.
These models require separate approval and provisioning. You can apply to join the Daybreak program 
. More details on pricing 
 snapshot, which points to the latest model available in ChatGPT for Plus and Pro users. We recommend leveraging 

What's new in 5.2 is a new xhigh reasoning effort level, concise reasoning summaries, and new context management using compaction.

 X.509 certificates (beta) 
controlling when memories are created and where they're stored.
What's new in 5.2 is a new xhigh reasoning effort level, concise reasoning summaries, and new context management using compaction.
Steerability and faster responses when less thinking's required
 reasoning setting for faster responses when less thinking's required—different from the previous 
—our largest and most capable chat model yet. GPT-4.5's high "EQ" and understanding of user intent make it better at creative tasks and agentic planning.

Fast mode now supports long-context requests for GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna. As of today, long-context prompts exceeding 272K tokens can run in

 Multiple Pixels (Advanced) 
 Conversion-Optimized Campaigns 
Fast mode now supports long-context requests for GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna. As of today, long-context prompts exceeding 272K tokens can run in 
, delivering speeds up to 2.5× faster than the Standard tier. See 
Customers can now filter and group data by API key in the 
Usage and Costs dashboards
 also support the API key dimension for programmatic reporting and analysis.