What changed in the OpenAI API

OpenAI-hosted sandbox compute is now billed during active turns. You no longer pay for idle time between turns.

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 
 in the Agents API now include the Artifact SDK and skills for creating and editing spreadsheets, presentations, and Word documents.
 with a supported model to reduce the time between generated tokens.
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.

Create a custom voice from a text description through the API or voice Playground, then reuse it in GPT-Live sessions.

 Windows app and CLI deployment 
 Designing failover across OpenAI model providers 
 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.
natural voices for GPT-Live
: Nuri, Juni, and Flitz (German); Brise and Sillage (French); Nira (Hindi); Harema and Shida (Japanese); and Noeul (Korean).

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.

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.

Maintaining software with the GPT-6 family

 Maintaining software with the GPT-6 family 

It is available to all API users, subject to rate limits, with global processing and US and EU data residency.

 in the Responses API. Use 
 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 

snapshot, which points to the latest model available in ChatGPT for Plus, Pro, Business and Enterprise users.

 Use API/provider credentials 
 snapshot, which points to the latest model available in ChatGPT for Plus, Pro, Business and Enterprise users. We recommend leveraging the 

Simplified API usage tiers from five to three: Build, Launch, and Grow. Organizations automatically upgrade as total credit purchases reach tier minimums.

 Connect voice to Decisions 
. Turn text and images into typed answers 10x faster than the Responses API.
Simplified API usage tiers from five to three: Build, Launch, and Grow. Organizations automatically upgrade as total credit purchases reach tier minimums. See 
 for monthly usage limits and how to view rate limits for each model.

Added an in-product flow for HIPAA compliance support in 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 
 for eligibility, covered services, and configuration requirements.

It is available to API customers, subject to rate limits, with global processing and US data residency. EU and other regional inference residency aren't supported.

 Get started with the OpenAI API 
 Explore models and compare capabilities 
 Build persistent agents on hosted infrastructure 
 Connect models to tools and data 
 Build speech and realtime voice experiences 
 Deploy and scale your API integrations 
 Explore endpoints, parameters, and responses 
 Apps powered by your user's ChatGPT plan 
 ChatGPT + Codex user docs 
 Guides and product docs for ChatGPT and Codex 
 ChatGPT + Codex user docs 
ChatGPT + Codex user docs
 Add events to your MCP server (optional) 
 Annotations Extensibility 
 ChatGPT in Slack and Teams 
 Local computer access for Work Cloud and dots 
 Deployment and configuration 
 Collaboration and sharing 
 to the Agents API. Agents can complete tasks in an OpenAI-hosted browser, with website access approvals and sign-in handled by your application.
) for complex coding and professional work at a lower cost than GPT-6 Astra.
Standard pricing per 1M tokens for prompts with up to 272K input tokens is $2 input, $0.10 cached input, $2.50 cache write, and $10 output.
GPT-6.1 Sol also supports 
 in beta. Let the model delegate work to subagents in a Responses API request.
Use the Responses API for tool calling. See 
 for reaso

If your use cases involve image inputs, we recommend rerunning your evaluations and retrying workflows affected by the issue.

Fixed a bug in image encoding that degraded image understanding in 
. This update improves results on visual tasks in the API and Codex, including computer use.
If your use cases involve image inputs, we recommend rerunning your evaluations and retrying workflows affected by the issue.

Bringing my LED display to life with GPT-Live-1 and Codex

 Bringing my LED display to life with GPT-Live-1 and Codex 

These reasoning models accept text and image inputs and generate text through the Responses and Chat Completions APIs.

 Private Safety Processing 
These reasoning models accept text and image inputs and generate text through the Responses and Chat Completions APIs.
Standard pricing per 1M tokens for prompts with up to 272K input tokens:
GPT-6 Sol: $2 input, $0.20 cached input, and $10 output.
GPT-6 Luna: $0.10 input, $0.01 cached input, and $0.50 output.
Compare capabilities in the 
 for cache writes, longer prompts, and other processing tiers.

support in the Responses API to accept more document, presentation, spreadsheet, code, and text file types.

Upcoming deprecations can be found on the 
 support in the Responses API to accept more document, presentation, spreadsheet, code, and text file types. Learn more 

Added API key creation governance controls at the organization and project levels. Administrators can allow only service-account keys, allow only user-owned project keys, or disable all new API key…

Added API key creation governance controls at the organization and project levels. Administrators can allow only service-account keys, allow only user-owned project keys, or disable all new API key creation. Organization restrictions take precedence over project settings, and existing API keys are unaffected. See 

Standard pricing is $5 per 1M input tokens, $0.50 per 1M cached input tokens, and $25 per 1M output tokens. Billing begins on October 5, 2026.

 Rethinking skills and prompts for GPT-6 Astra 
) is now generally available through the 
 for approved internal life sciences research.
Standard pricing is $5 per 1M input tokens, $0.50 per 1M cached input tokens, and $25 per 1M output tokens. Billing begins on October 5, 2026. See 

You can now set expiration dates when creating project API keys. Administrators can also enforce a maximum key lifetime at the organization or project level in Platform settings, requiring newly…

 Run and continue sessions 
Environments and sandboxes
 Audio in Chat Completions 
You can now set expiration dates when creating project API keys. Administrators can also enforce a maximum key lifetime at the organization or project level in Platform settings, requiring newly created keys to expire within the configured limit. See 
production best practices
 for guidance on key expiration and rotation.
 in public beta. Build agents with a managed Codex harness while OpenAI handles session orchestration, context compaction, and recovery.
Use durable sessions to continue work across turns, stream progress, and connect your own tools and MCP servers. Run agents in OpenAI-hosted sandboxes or connect a sandbox from your own infrastructure or a supported provider.
 is now generally available in the API. Build full-duplex voice conversations that can continue while a backend model or agent handles reasoning and tools.
Use Responses delegation with an OpenAI model, or client delegation to connect your own backend. Voice sessions cost $0.05 per minute, billed per second; backend model and tool usage is charged separately.

Compare cache reuse against a previous response, identify reasons for cache misses, and follow troubleshooting guidance to improve cache reuse.

 is now generally available in the Responses API for GPT-5.6 and later supported models.
Compare cache reuse against a previous response, identify reasons for cache misses, and follow troubleshooting guidance to improve cache reuse.
 for image generation and editing through the Image API and the Responses API image generation tool.
Use Sunburst for workflows where editing precision matters most, or Flare for fast, high-quality everyday image generation. Both models support the new 
 quality settings and use GPT Image 2 token rates. See the