{"id":"src_lUUecdtTa2GdtjHTQGpjm","slug":"openai-api-changelog","name":"API Changelog","type":"scrape","url":"https://developers.openai.com/api/docs/changelog","orgId":"org_XCtsUSrelarAybkAnBD3g","productId":"prod_620id5eCzPlmwV1xRa-Q9","productSlug":"api","org":{"id":"org_XCtsUSrelarAybkAnBD3g","slug":"openai","name":"OpenAI"},"isPrimary":false,"isHidden":false,"discovery":"curated","metadata":"{\"noFeedFound\":true,\"sourceActor\":{\"nextAlarmAt\":\"2026-10-17T21:47:44.661Z\",\"lastAlarmAt\":\"2026-10-17T17:47:45.595Z\",\"managed\":true},\"markdownUrl\":\"https://developers.openai.com/api/docs/changelog.md\",\"evaluatedMethod\":\"markdown\",\"evaluatedAt\":\"2026-08-11T18:23:27.708Z\",\"parseInstructions\":\"Parse ## Month, YYYY / ### Mon D sections from the markdown changelog. One release per day heading. version=null. Prefer the Feature/Update line as title; keep full markdown body. Synthesize url as https://developers.openai.com/api/docs/changelog#YYYY-MM-DD.\\r\\n\"}","notice":null,"kind":"platform","stars":null,"starsFetchedAt":null,"releaseCount":191,"releasesLast30Days":10,"avgReleasesPerWeek":2.7,"latestVersion":null,"latestDate":"2026-10-15T00:00:00.000Z","changelogUrl":null,"hasChangelogFile":false,"lastFetchedAt":"2026-10-16T12:50:21.412Z","lastPolledAt":"2026-10-17T17:52:29.550Z","changeDetectedAt":null,"trackingSince":"2024-01-25T00:00:00.000Z","releases":[{"id":"rel_lKOA1y5LFlsjn6L-hm8AF","version":null,"type":"feature","title":"Decisions integration in GPT-Live","summary":"GPT-Live (gpt-live-1 and gpt-6-luna) now has native Decisions integration, letting apps act while the user is speaking or react to Live output. Live can invoke Decisions through native delegation, or decisions can be triggered from input/output transcript deltas.","titleGenerated":"OpenAI API adds native Decisions integration in GPT-Live","titleShort":"GPT-Live gains native Decisions integration","breaking":"none","importance":3,"content":"Added native Decisions integration in GPT-Live (`gpt-live-1`, `gpt-6-luna`). Apps can act while the user is speaking or react to Live output. Live can call Decisions via native delegation, or decisions can be triggered from input/output transcript deltas.","publishedAt":"2026-10-15T00:00:00.000Z","fetchedAt":"2026-10-16T12:50:20.446Z","url":"https://developers.openai.com/api/docs/changelog#2026-10-15","media":[],"coverageCount":0},{"id":"rel_FxmC4WGI4BARLimZ0ZS8p","version":null,"type":"feature","title":"Ultrafast mode for GPT-6.1 Sol","summary":"Responses API users can set service_tier: \"ultrafast\" on gpt-6.1-sol to reduce time between generated output tokens. Available to all API users subject to rate limits, with global processing and US and EU data residency.","titleGenerated":"OpenAI API adds Ultrafast mode for GPT-6.1 Sol in Responses API","titleShort":"GPT-6.1 Sol gains Ultrafast mode","breaking":"none","importance":4,"content":"Added **Ultrafast mode** for **GPT-6.1 Sol** in the Responses API. Use `gpt-6.1-sol` with `service_tier: \"ultrafast\"` to reduce the time between generated output tokens. Available to all API users, subject to rate limits, with global processing and US and EU data residency. See Ultrafast pricing.","publishedAt":"2026-10-08T00:00:00.000Z","fetchedAt":"2026-10-09T13:09:45.338Z","url":"https://developers.openai.com/api/docs/changelog#ultrafast-mode-for-gpt-6-1-sol","media":[],"coverageCount":0},{"id":"rel__qUg-fvafiNjSjIbUaBa0","version":null,"type":"feature","title":"Update · Model: chat-latest","summary":"The chat-latest snapshot now points to the latest model available in ChatGPT for Plus, Pro, Business, and Enterprise users, with the underlying snapshot updated regularly. Production API usage should use the GPT-6 model family; chat-latest is for testing the latest chat improvements.","titleGenerated":"OpenAI API update: chat-latest snapshot refreshed for ChatGPT paid tiers","titleShort":"chat-latest snapshot refreshed","breaking":"none","importance":2,"content":"Updated the **chat-latest** snapshot, which points to the latest model available in ChatGPT for Plus, Pro, Business and Enterprise users. Recommended to leverage the GPT-6 model family for production API usage, but can use this model to test the latest improvements for chat use cases. The underlying model snapshot will be regularly updated.","publishedAt":"2026-10-07T00:00:00.000Z","fetchedAt":"2026-10-08T12:50:01.515Z","url":"https://developers.openai.com/api/docs/changelog#update-model-chat-latest","media":[],"coverageCount":0},{"id":"rel_IJ7TVooYlBWrUrEh4A9vz","version":null,"type":"feature","title":"Simplified API Usage Tiers","summary":"API usage tiers are simplified from five to three: Build, Launch, and Grow. Organizations automatically upgrade as total credit purchases reach tier minimums.","titleGenerated":"OpenAI API simplifies usage tiers from five to three","titleShort":"API usage tiers cut from five to three","breaking":"major","importance":3,"content":"Simplified API usage tiers from five to three: Build, Launch, and Grow. Organizations automatically upgrade as total credit purchases reach tier minimums. See usage tiers for monthly usage limits and how to view rate limits for each model.","publishedAt":"2026-10-06T00:00:00.000Z","fetchedAt":"2026-10-07T00:56:49.166Z","url":"https://developers.openai.com/api/docs/changelog#simplified-api-usage-tiers","media":[],"coverageCount":0},{"id":"rel_G_L7VZ4knwRRhDXLx4mnQ","version":"gpt-6-luna","type":"feature","title":"Decisions API Beta Release","summary":"Released the Decisions API in beta with gpt-6-luna, turning text and images into typed answers 10x faster than the Responses API.","titleGenerated":"OpenAI API launches Decisions API beta with gpt-6-luna","titleShort":"Decisions API beta turns text and images into typed answers","breaking":"none","importance":4,"content":"Released the Decisions API in beta with `gpt-6-luna`. Turn text and images into typed answers 10x faster than the Responses API.","publishedAt":"2026-10-06T00:00:00.000Z","fetchedAt":"2026-10-07T00:56:49.166Z","url":"https://developers.openai.com/api/docs/changelog#gpt-6-luna","media":[],"coverageCount":0},{"id":"rel_Hjr3aDV1EKqKAnyiJ-VGr","version":null,"type":"feature","title":"Added an in-product flow for HIPAA compliance support in API Organization settings","summary":"Admins of eligible organizations can now accept the standard Business Associate Agreement and enable HIPAA compliance support directly from Organization settings > General.","titleGenerated":"OpenAI API adds in-product HIPAA BAA flow for organization admins","titleShort":"Admins can accept BAA, enable HIPAA support in-product","breaking":"none","importance":3,"content":"Added an in-product flow for HIPAA compliance support in API [Organization settings > General](https://platform.openai.com/settings/organization/general). Admins of eligible organizations can now accept the standard Business Associate Agreement (BAA) and enable HIPAA compliance support for their organization. See the [Help Center](https://help.openai.com/en/articles/8660679-getting-a-business-associate-agreement-for-the-openai-api) for eligibility, covered services, and configuration requirements.","publishedAt":"2026-10-05T00:00:00.000Z","fetchedAt":"2026-10-06T13:02:57.133Z","url":"https://developers.openai.com/api/docs/changelog#added-an-in-product-flow-for-hipaa-compliance-support-in-api","media":[],"coverageCount":0},{"id":"rel_ZBsDTyvvLZSeFXlkDvfXw","version":null,"type":"feature","title":"Added Ultrafast mode for GPT-6 Astra","summary":"Ultrafast mode for GPT-6 Astra is available in the Responses API via service_tier: \"ultrafast\", reducing the time between generated output tokens. It is subject to rate limits, restricted to global processing and US data residency, and EU and other regional inference residency aren't supported.","titleGenerated":"OpenAI API adds Ultrafast mode for GPT-6 Astra","titleShort":"GPT-6 Astra gains Ultrafast service tier","breaking":"none","importance":4,"content":"Added [Ultrafast mode](https://developers.openai.com/api/docs/guides/ultrafast-mode) for GPT-6 Astra in the Responses API. Use `gpt-6-astra` with `service_tier: \"ultrafast\"` to reduce the time between generated output tokens. 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. See [Ultrafast pricing](https://developers.openai.com/api/docs/pricing?latest-pricing=ultrafast).","publishedAt":"2026-09-29T00:00:00.000Z","fetchedAt":"2026-10-02T11:30:53.466Z","url":"https://developers.openai.com/api/docs/changelog#added-ultrafast-mode-for-gpt-6-astra","media":[],"coverageCount":0},{"id":"rel_KP9-qFthx7cgPsloHmPWx","version":null,"type":"feature","title":"Added computer use to the Agents API","summary":"Computer use is now available in the Agents API, letting agents complete tasks in an OpenAI-hosted browser, with website access approvals and sign-in handled by the calling application.","titleGenerated":"OpenAI API adds computer use to the Agents API","titleShort":"Agents API gains computer use in hosted browser","breaking":"none","importance":3,"content":"Added [computer use](https://developers.openai.com/api/docs/guides/agents-api/tools/computer-use) to the Agents API. Agents can complete tasks in an OpenAI-hosted browser, with website access approvals and sign-in handled by your application.","publishedAt":"2026-09-29T00:00:00.000Z","fetchedAt":"2026-10-02T11:30:53.466Z","url":"https://developers.openai.com/api/docs/changelog#added-computer-use-to-the-agents-api","media":[],"coverageCount":0},{"id":"rel_BqQ2tmd3wx1yFMmN2SQWJ","version":"gpt-6.1-sol","type":"feature","title":"Released GPT-6.1 Sol","summary":"GPT-6.1 Sol (gpt-6.1-sol) is available for complex coding and professional work at a lower cost than GPT-6 Astra, priced at $2 input, $0.10 cached input, $2.50 cache write, and $10 output per 1M tokens for prompts up to 272K input tokens. It also supports Multi-agent in beta, letting the model delegate work to subagents in a Responses API request.","titleGenerated":"OpenAI API releases GPT-6.1 Sol model for complex coding at lower cost","titleShort":"GPT-6.1 Sol launches cheaper; multi-agent beta","breaking":"none","importance":4,"content":"Released [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol) (`gpt-6.1-sol`) for complex coding and professional work at a lower cost than GPT-6 Astra.\n\nStandard 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.\n\nGPT-6.1 Sol also supports [Multi-agent](https://developers.openai.com/api/docs/guides/responses-multi-agent) in beta. Let the model delegate work to subagents in a Responses API request.\n\nUse the Responses API for tool calling. See [GPT-6 model guidance](https://developers.openai.com/api/docs/guides/latest-model?model=gpt-6-astra#gpt-61-sol) for reasoning settings and [pricing](https://developers.openai.com/api/docs/pricing) for available processing tiers.","publishedAt":"2026-09-29T00:00:00.000Z","fetchedAt":"2026-10-02T11:30:53.466Z","url":"https://developers.openai.com/api/docs/changelog#gpt-6-1-sol","media":[],"coverageCount":0},{"id":"rel_2Moc2INu6jPeZ6JH5kja8","version":null,"type":"feature","title":"Fixed image encoding bug in GPT-6 Sol and GPT-6 Luna","summary":"An image encoding bug that degraded image understanding in GPT-6 Sol and GPT-6 Luna is fixed, improving results on visual tasks in the API and Codex, including computer use. OpenAI recommends rerunning evaluations and retrying workflows that use image inputs.","titleGenerated":"OpenAI fixes image encoding bug degrading image understanding in GPT-6 Sol and Luna","titleShort":"Image encoding bug in GPT-6 Sol and Luna fixed","breaking":"none","importance":3,"content":"Fixed a bug in image encoding that degraded image understanding in GPT-6 Sol and GPT-6 Luna. This update improves results on visual tasks in the API and Codex, including computer use.\n\nIf your use cases involve image inputs, we recommend rerunning your evaluations and retrying workflows affected by the issue.","publishedAt":"2026-09-25T00:00:00.000Z","fetchedAt":"2026-09-29T17:28:45.130Z","url":"https://developers.openai.com/api/docs/changelog#fixed-image-encoding-bug-in-gpt-6-sol-and-gpt-6-luna","media":[],"coverageCount":0},{"id":"rel_2RdaijHKYSgFvkatcPzBI","version":null,"type":"feature","title":"API key creation governance controls","summary":"Administrators can now restrict API key creation at the organization and project levels to service-account keys only, user-owned project keys only, or disable new key creation entirely, with organization restrictions taking precedence over project settings. Existing API keys are unaffected.","titleGenerated":"OpenAI API adds org and project API key creation governance controls","titleShort":"API key creation governance at org and project levels","breaking":"none","importance":3,"content":"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 [production best practices](https://developers.openai.com/api/docs/guides/production-best-practices#api-keys) for details.","publishedAt":"2026-09-15T00:00:00.000Z","fetchedAt":"2026-09-17T11:45:08.495Z","url":"https://developers.openai.com/api/docs/changelog#api-key-creation-governance-controls","media":[],"coverageCount":0},{"id":"rel_d-7Hq64zOIK5vWRJYEREu","version":null,"type":"feature","title":"Released the Agents API in public beta","summary":"The Agents API is available in public beta for building agents on a managed Codex harness, with OpenAI handling session orchestration, context compaction, and recovery. It supports durable sessions, streaming progress, custom tools and MCP servers, and OpenAI-hosted or self-provided sandboxes.","titleGenerated":"OpenAI Agents API enters public beta with managed Codex harness","titleShort":"Agents API beta: managed Codex harness, durable sessions","breaking":"none","importance":5,"content":"Build agents with a managed Codex harness while OpenAI handles session orchestration, context compaction, and recovery. Durable sessions, streaming progress, custom tools and MCP servers, and OpenAI-hosted or self-provided sandboxes.","publishedAt":"2026-09-10T00:00:00.000Z","fetchedAt":"2026-10-15T16:56:15.202Z","url":"https://developers.openai.com/api/docs/changelog#released-the-agents-api-in-public-beta","media":[],"coverageCount":0},{"id":"rel_qiAoNlEJzT5H_6IEhAQkI","version":null,"type":"feature","title":"API key expiration dates now configurable","summary":"Project API keys can now be created with expiration dates, and administrators can enforce a maximum key lifetime at the organization or project level in Platform settings so newly created keys expire within the configured limit.","titleGenerated":"OpenAI API keys get configurable expiration dates and org-level max lifetime","titleShort":"API keys now expire; admins can cap key lifetime","breaking":"none","importance":3,"content":"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](https://developers.openai.com/api/docs/guides/production-best-practices#api-keys) for guidance on key expiration and rotation.","publishedAt":"2026-09-10T00:00:00.000Z","fetchedAt":"2026-09-11T08:53:04.764Z","url":"https://developers.openai.com/api/docs/changelog#api-key-expiration-dates-now-configurable","media":[],"coverageCount":0},{"id":"rel_i6nl6MtECye6dgf0F3Xya","version":null,"type":"feature","title":"GPT-Rosalind now generally available for life sciences research","summary":"GPT-Rosalind (gpt-rosalind-research) is now generally available through the trusted-access program 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, with billing beginning October 5, 2026.","titleGenerated":"OpenAI API makes GPT-Rosalind generally available for life sciences research","titleShort":"GPT-Rosalind now GA for life sciences research","breaking":"none","importance":4,"content":"GPT-Rosalind (`gpt-rosalind-research`) is now generally available through the [trusted-access program](https://help.openai.com/en/articles/20001193-gpt-rosalind-for-life-sciences-research) for approved internal life sciences research.\n\nStandard 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 [pricing](https://developers.openai.com/api/docs/pricing) for details.","publishedAt":"2026-09-08T00:00:00.000Z","fetchedAt":"2026-09-14T10:19:04.423Z","url":"https://developers.openai.com/api/docs/changelog#gpt-rosalind-now-generally-available-for-life-sciences-resea","media":[],"coverageCount":0},{"id":"rel_O8tPqbcLroBS1QCl1YlQP","version":null,"type":"feature","title":"GPT Image 2.5 Sunburst and Flare released","summary":"GPT Image 2.5 Sunburst and GPT Image 2.5 Flare are available for image generation and editing through the Image API and the Responses API image generation tool. Both support new xhigh and max quality settings and use GPT Image 2 token rates.","titleGenerated":"OpenAI API launches GPT Image 2.5 Sunburst and Flare","titleShort":"GPT Image 2.5 Sunburst and Flare launch","breaking":"none","importance":4,"content":"Released [GPT Image 2.5 Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst) and [GPT Image 2.5 Flare](https://developers.openai.com/api/docs/models/gpt-image-2.5-flare) for image generation and editing through the Image API and the Responses API image generation tool.\n\nUse Sunburst for workflows where editing precision matters most, or Flare for fast, high-quality everyday image generation. Both models support the new `xhigh` and `max` quality settings and use GPT Image 2 token rates. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) and [pricing](https://developers.openai.com/api/docs/pricing#image-generation).","publishedAt":"2026-09-08T00:00:00.000Z","fetchedAt":"2026-09-11T08:53:04.764Z","url":"https://developers.openai.com/api/docs/changelog#gpt-image-2-5-sunburst-and-flare-released","media":[],"coverageCount":0},{"id":"rel_Ka2rXODjx1M4_9rVjFjFP","version":null,"type":"feature","title":"Prompt Cache Diagnostics now generally available","summary":"Prompt Cache Diagnostics is now generally available in the Responses API for GPT-5.6 and later supported models. It lets developers compare cache reuse against a previous response, identify reasons for cache misses, and follow troubleshooting guidance to improve cache reuse.","titleGenerated":"OpenAI API Prompt Cache Diagnostics generally available in Responses API","titleShort":"Prompt Cache Diagnostics reaches GA","breaking":"none","importance":3,"content":"[Prompt Cache Diagnostics](https://developers.openai.com/api/docs/guides/prompt-caching/diagnostics) is now generally available in the Responses API for GPT-5.6 and later supported models.\n\nCompare cache reuse against a previous response, identify reasons for cache misses, and follow troubleshooting guidance to improve cache reuse.","publishedAt":"2026-09-08T00:00:00.000Z","fetchedAt":"2026-09-11T08:53:04.764Z","url":"https://developers.openai.com/api/docs/changelog#prompt-cache-diagnostics-now-generally-available","media":[],"coverageCount":0},{"id":"rel_UVsK9y5LbB_dWpcdqis4I","version":null,"type":"feature","title":"New controls for long-running work with GPT-6 Astra","summary":"New Responses API controls for long-running GPT-6 Astra work let the model keep running while your app executes function or custom tools and return results as available, accept mid-turn steering over WebSockets while a response is in progress, and change reasoning effort mid-conversation while preserving the cached prompt prefix.","titleGenerated":"OpenAI API adds async tool calling and mid-turn steering for GPT-6 Astra","titleShort":"GPT-6 Astra: async tools, mid-turn steering, live reasoning effort","breaking":"none","importance":4,"content":"Added new controls for long-running work with GPT-6 Astra in the Responses API:\n\n- [Async tool calling](https://developers.openai.com/api/docs/guides/async-tool-calling): Let the model continue working while your application runs function or custom tools, then return results as they become available.\n- [Mid-turn steering](https://developers.openai.com/api/docs/guides/steering): Send additional instructions while a response is in progress over WebSockets, so the model can incorporate corrections or changing requirements.\n- [Change reasoning effort mid-conversation](https://developers.openai.com/api/docs/guides/reasoning#change-reasoning-mid-conversation): Increase effort for difficult work or reduce it for routine follow-ups while preserving the cached prompt prefix.","publishedAt":"2026-09-03T00:00:00.000Z","fetchedAt":"2026-10-05T12:10:45.831Z","url":"https://developers.openai.com/api/docs/changelog#new-controls-for-long-running-work-with-gpt-6-astra","media":[],"coverageCount":0},{"id":"rel_6g_8wZM_bw_sOPAYJd5zW","version":null,"type":"feature","title":"Released GPT-6 Astra, most capable model for end-to-end work","summary":"GPT-6 Astra is released for reasoning, coding, computer use, research, and document creation, carrying complex tasks from an initial request to a finished result. It does not support the none reasoning effort level, custom temperature or top_p values, or log probabilities, and tool calling requires the Responses API.","titleGenerated":"OpenAI releases GPT-6 Astra, most capable model for end-to-end work","titleShort":"GPT-6 Astra ships; drops temperature, top_p, none reasoning","breaking":"major","importance":5,"content":"Released [GPT-6 Astra](https://developers.openai.com/api/docs/models/gpt-6-astra), our most capable model, built for the hardest end-to-end work.\n\nUse 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.\n\nKey changes to consider when migrating:\n\n- GPT-6 Astra does not support the `none` reasoning effort level.\n- GPT-6 Astra does not support custom `temperature` or `top_p` values or log probabilities (`logprobs`).\n- Tool calling requires the Responses API. If you use tools with Chat Completions, follow the [Responses migration guide](https://developers.openai.com/api/docs/guides/migrate-to-responses).\n- [Misalignment monitoring](https://developers.openai.com/api/docs/guides/safety-checks/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.\n\nStart with [Using GPT-6 Astra](https://developers.openai.com/api/docs/guides/latest-model) for capabilities, prompting, and migration guidance. Explore [computer use](https://developers.openai.com/api/docs/guides/tools-computer-use) for browser and desktop workflows, and see [pricing](https://developers.openai.com/api/docs/pricing) for available inference tiers.","publishedAt":"2026-09-03T00:00:00.000Z","fetchedAt":"2026-10-05T12:10:45.831Z","url":"https://developers.openai.com/api/docs/changelog#released-gpt-6-astra-most-capable-model-for-end-to-end-work","media":[],"coverageCount":0},{"id":"rel_51V0O5s8kRm1EKNoKbvPb","version":null,"type":"feature","title":"Updated API error codes to distinguish traffic increases from model overload","summary":"Rapid traffic increases now return a 429 with the slow_down code, while temporary model overload returns a 503 with server_is_overloaded, letting applications tell the two apart. Both responses may include Retry-After; wait at least as long as it specifies, or use exponential backoff when absent.","titleGenerated":"OpenAI API distinguishes traffic spikes from model overload in error codes","titleShort":"Traffic spikes now 429 slow_down; overload 503 server_is_overloaded","breaking":"none","importance":3,"content":"Updated API errors so applications can distinguish traffic that increases too quickly from temporary model overload.\n\nTraffic 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](https://developers.openai.com/api/docs/guides/error-codes) and [rate limits guide](https://developers.openai.com/api/docs/guides/rate-limits).","publishedAt":"2026-09-02T00:00:00.000Z","fetchedAt":"2026-09-29T17:28:45.130Z","url":"https://developers.openai.com/api/docs/changelog#updated-api-error-codes-to-distinguish-traffic-increases-fro","media":[],"coverageCount":0},{"id":"rel_j9UhMAu2s-xGUe6Fq4O3n","version":null,"type":"feature","title":"Connections to api.openai.com can use IPv6","summary":"Connections to api.openai.com can now use IPv6.","titleGenerated":"OpenAI API now accepts IPv6 connections to api.openai.com","titleShort":"api.openai.com now reachable over IPv6","breaking":"none","importance":2,"content":"Connections to `api.openai.com` can now use IPv6.","publishedAt":"2026-09-01T00:00:00.000Z","fetchedAt":"2026-10-15T16:56:15.568Z","url":"https://developers.openai.com/api/docs/changelog#connections-to-api-openai-com-can-use-ipv6","media":[],"coverageCount":0}],"pagination":{"nextCursor":"2026-09-01T00:00:00.000Z|2026-10-15T16:56:15.568Z|rel_j9UhMAu2s-xGUe6Fq4O3n","limit":20},"summaries":{"rolling":{"windowDays":90,"summary":"OpenAI shifted focus toward developer education and tooling around its generative models. The team published prompting guides for both Sora 2 video generation and Codex, positioning Codex as the primary agentic coding model, while also shipping IDE integrations and a dedicated Codex app to lower friction for daily workflows.","releaseCount":4,"generatedAt":"2026-04-07T17:27:07.073Z"},"monthly":[{"year":2026,"month":3,"summary":"The team published a prompting guide for Sora 2, documenting strategies to craft effective video generation requests.","releaseCount":1,"generatedAt":"2026-04-07T17:27:09.134Z"}]}}