{"id":257,"date":"2026-09-07T08:04:55","date_gmt":"2026-09-07T08:04:55","guid":{"rendered":"https:\/\/llmfly.ai\/blog\/?p=257"},"modified":"2026-09-07T08:04:57","modified_gmt":"2026-09-07T08:04:57","slug":"openai-api-deprecations-2026","status":"publish","type":"post","link":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/","title":{"rendered":"OpenAI API Deprecations in 2026: Migration Deadlines"},"content":{"rendered":"<p><em>Last reviewed: September 7, 2026.<\/em><\/p>\n<h2>Quick answer: Which OpenAI APIs and models are shutting down in 2026?<\/h2>\n<p>OpenAI has multiple shutdowns remaining in 2026. The most urgent is the <strong>Videos API and Sora 2 models on September 24<\/strong>, followed by legacy completions and GPT-3.5 models on September 28. A larger group of GPT-4, GPT-4o, o1, o3-mini, and fine-tuned snapshots shuts down October 23. Reusable prompts, the Evals platform, and Agent Builder end November 30. Older GPT Image models end December 1, and older GPT-5 and o3 snapshots end December 11.<\/p>\n<p>Do not treat every migration as a model-ID replacement. Sora 2 currently has no listed replacement; reusable prompts must move into application code; Evals needs an external evaluation system; Agent Builder moves to the Agents SDK or ChatGPT Workspace Agents. Inventory model IDs and product endpoints now, add contract tests, and deploy replacements behind configuration flags before each deadline.<\/p>\n<h2>What is the OpenAI API deprecation calendar for the rest of 2026?<\/h2>\n<figure class=\"wp-block-table\">\n<table>\n<thead>\n<tr>\n<th>Shutdown date<\/th>\n<th>Models or product<\/th>\n<th>Recommended action<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Sep 24<\/td>\n<td>Videos API, <code>sora-2<\/code>, <code>sora-2-pro<\/code>, listed snapshots<\/td>\n<td>No replacement listed; remove dependency or redesign video flow<\/td>\n<\/tr>\n<tr>\n<td>Sep 28<\/td>\n<td><code>gpt-3.5-turbo-instruct<\/code>, <code>babbage-002<\/code>, <code>davinci-002<\/code>, <code>gpt-3.5-turbo-1106<\/code><\/td>\n<td>Move to <code>gpt-5.6-terra<\/code><\/td>\n<\/tr>\n<tr>\n<td>Oct 23<\/td>\n<td>Selected GPT-3.5, GPT-4, GPT-4o, o1, o3-mini, GPT Image, and fine-tuned snapshots<\/td>\n<td>Use the official per-model replacements and re-evaluate outputs<\/td>\n<\/tr>\n<tr>\n<td>Oct 31<\/td>\n<td>OpenAI Evals<\/td>\n<td>Existing evals become read-only<\/td>\n<\/tr>\n<tr>\n<td>Nov 30<\/td>\n<td><code>\/v1\/prompts<\/code>, reusable prompts, Evals dashboard\/API, Agent Builder<\/td>\n<td>Move prompts to code; move evals; use Agents SDK or Workspace Agents<\/td>\n<\/tr>\n<tr>\n<td>Dec 1<\/td>\n<td><code>gpt-image-1-mini<\/code>, <code>gpt-image-1.5<\/code>, <code>chatgpt-image-latest<\/code><\/td>\n<td>Move to <code>gpt-image-2<\/code><\/td>\n<\/tr>\n<tr>\n<td>Dec 11<\/td>\n<td>Older GPT-5 and o3 snapshots<\/td>\n<td>Move to GPT-5.6 Sol, Terra, or Luna as specified<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/figure>\n<p>This table is a planning summary, not a substitute for OpenAI&#8217;s live deprecations page. OpenAI can add notices, so check the official source during every release cycle.<\/p>\n<h2>What should Sora 2 and Videos API developers do before September 24?<\/h2>\n<p>OpenAI lists the Videos API, <code>sora-2<\/code>, <code>sora-2-pro<\/code>, and multiple dated snapshots for shutdown on September 24, 2026. The official table does not provide a replacement.<\/p>\n<p>That changes the migration plan. Do not silently point production to an assumed successor. Identify every video-generation endpoint, stop selling commitments that extend past the shutdown, export any metadata your application needs, and design a provider-neutral job interface:<\/p>\n<pre><code>interface VideoJob {\n  prompt: string;\n  aspectRatio: \"16:9\" | \"9:16\" | \"1:1\";\n  durationSeconds: number;\n  idempotencyKey: string;\n}\n<\/code><\/pre>\n<p>Put provider-specific fields behind adapters and return an explicit \u201ctemporarily unavailable\u201d state if no approved replacement exists. A model abstraction can make later integration easier, but it cannot manufacture a supported Sora replacement.<\/p>\n<h2>Which legacy text models shut down on September 28?<\/h2>\n<p><code>gpt-3.5-turbo-instruct<\/code>, <code>babbage-002<\/code>, <code>davinci-002<\/code>, and <code>gpt-3.5-turbo-1106<\/code> are scheduled to shut down on September 28. OpenAI recommends <code>gpt-5.6-terra<\/code>.<\/p>\n<p>This is not always a drop-in replacement. Instruct-style completions, older chat payloads, token usage, and output behavior can differ. Create golden test cases for classification, extraction, rewriting, and refusal behavior. Compare structured-output validity and latency before switching all traffic.<\/p>\n<h2>What changes on October 23?<\/h2>\n<p>The October 23 wave affects a broad set of older snapshots, including <code>gpt-4-0613<\/code>, <code>gpt-4-turbo<\/code>, <code>gpt-4o-2024-05-13<\/code>, <code>o1-2024-12-17<\/code>, <code>o3-mini-2025-01-31<\/code>, and <code>gpt-image-1<\/code>. It also removes multiple fine-tuned model families.<\/p>\n<p>OpenAI&#8217;s replacements vary by model: GPT-5.6 Sol for many high-capability models, GPT-5.6 Terra or Luna for smaller models, <code>gpt-image-2<\/code> for image generation, and Sol with <code>reasoning.mode: pro<\/code> for selected pro models.<\/p>\n<p>Search application code, environment variables, database configuration, prompt-management systems, background workers, and CI fixtures. A model ID can survive in a rarely used queue long after the main application has migrated.<\/p>\n<h2>How do you migrate away from OpenAI reusable prompts?<\/h2>\n<p>The <code>\/v1\/prompts<\/code> API and reusable prompt objects shut down November 30. OpenAI recommends moving prompt content into application code.<\/p>\n<p>Store prompts as versioned application assets rather than inline strings scattered across handlers:<\/p>\n<pre><code>prompts\/\n  support_reply\/\n    v3.system.md\n    v3.schema.json\n    evals.jsonl\n<\/code><\/pre>\n<p>Record the prompt version with every response. Deploy prompt changes through code review, run a fixed evaluation set, and keep rollback capability. Never put secrets into source-controlled prompt files; inject them from the runtime secret store.<\/p>\n<h2>What replaces the OpenAI Evals platform?<\/h2>\n<p>Existing OpenAI evals become read-only on October 31, and the dashboard and API shut down November 30. Export definitions, datasets, grader logic, score history, and release thresholds before read-only mode. OpenAI links to Promptfoo as one migration path, but teams can use any system that preserves reproducibility and CI integration.<\/p>\n<p>The critical artifact is not the dashboard. It is the contract connecting a task dataset, prompt version, model version, scoring rule, and release decision. Keep these in a repository or controlled evaluation store so a provider migration does not erase your quality history.<\/p>\n<h2>What replaces Agent Builder?<\/h2>\n<p>Agent Builder shuts down November 30. OpenAI recommends the Agents SDK or ChatGPT Workspace Agents; ChatKit remains available.<\/p>\n<p>Before moving, document every tool, permission, state transition, approval point, and external side effect. Add idempotency keys to write operations and human approval to destructive actions. A visual workflow can hide important defaults, so migrate behavior\u2014not only boxes on a canvas.<\/p>\n<h2>Which GPT Image models end on December 1?<\/h2>\n<p><code>gpt-image-1-mini<\/code>, <code>gpt-image-1.5<\/code>, and <code>chatgpt-image-latest<\/code> shut down December 1. OpenAI recommends <code>gpt-image-2<\/code>. A separate October 23 deadline applies to <code>gpt-image-1<\/code>.<\/p>\n<p>Re-run quality, aspect ratio, edit-mask, transparency, content-policy, and latency tests. Image migrations can change output dimensions and file handling even when the prompt is unchanged.<\/p>\n<h2>Which GPT-5 and o3 snapshots end on December 11?<\/h2>\n<p>The December 11 shutdown includes:<\/p>\n<ul>\n<li><code>gpt-5-2025-08-07<\/code> \u2192 <code>gpt-5.6-sol<\/code><\/li>\n<li><code>gpt-5-mini-2025-08-07<\/code> \u2192 <code>gpt-5.6-terra<\/code><\/li>\n<li><code>gpt-5-nano-2025-08-07<\/code> \u2192 <code>gpt-5.6-luna<\/code><\/li>\n<li><code>gpt-5-pro-2025-10-06<\/code> \u2192 <code>gpt-5.6-sol<\/code> with pro reasoning<\/li>\n<li><code>o3-2025-04-16<\/code> \u2192 <code>gpt-5.6-sol<\/code><\/li>\n<li><code>o3-pro-2025-06-10<\/code> \u2192 <code>gpt-5.6-sol<\/code> with pro reasoning<\/li>\n<\/ul>\n<p>Reasoning settings, output volume, and token prices can change the bill. Use our <a href=\"https:\/\/llmfly.ai\/blog\/2026\/09\/05\/gpt-6-astra-vs-gpt-5-6-sol-ai-agents\/\">Astra vs GPT-5.6 Sol agent comparison<\/a> if the migration is also an opportunity to decide whether Astra is worth its higher per-token price.<\/p>\n<h2>Can an OpenAI-compatible API reduce deprecation risk?<\/h2>\n<p>It can reduce integration work, but it cannot eliminate model retirement. <a href=\"https:\/\/llmfly.ai\/\">LLMFly AI<\/a> is a multi-model AI API platform with an OpenAI-compatible endpoint for selected GPT, Claude, Gemini, and Grok models. Keeping the base URL and model ID in configuration can make a tested model switch faster, and current routes may be priced below official API rates.<\/p>\n<p>Use the live <a href=\"https:\/\/app.llmfly.ai\/model-plaza\">LLMFly AI Model Plaza<\/a> to verify supported model IDs, pricing, and availability. Do not assume a listed text model replaces provider-specific products such as Sora, Agent Builder, or OpenAI Evals. An API compatibility layer standardizes portable calls; it does not reproduce every hosted tool or product.<\/p>\n<p>For portable text workloads, keep a small abstraction:<\/p>\n<pre><code>const MODEL = process.env.LLM_MODEL;\nconst BASE_URL = process.env.LLM_BASE_URL;\n\n\/\/ Change configuration only after the candidate model passes evals.\nconst client = new OpenAI({\n  apiKey: process.env.LLM_API_KEY,\n  baseURL: BASE_URL,\n});<\/code><\/pre>\n<p>Our <a href=\"https:\/\/llmfly.ai\/blog\/2026\/08\/31\/openai-responses-api-migration\/\">OpenAI Responses API migration guide<\/a> covers the broader transition from legacy request patterns.<\/p>\n<h2>What is a safe 30-day OpenAI migration plan?<\/h2>\n<ol>\n<li><strong>Days 1\u20133:<\/strong> inventory models, endpoints, stored prompts, evals, tools, and fine-tuned assets.<\/li>\n<li><strong>Days 4\u20137:<\/strong> export configurations and define acceptance tests.<\/li>\n<li><strong>Days 8\u201314:<\/strong> implement replacements behind feature flags and provider adapters.<\/li>\n<li><strong>Days 15\u201321:<\/strong> shadow traffic, compare cost per accepted result, and inspect failures.<\/li>\n<li><strong>Days 22\u201326:<\/strong> canary production traffic with rollback.<\/li>\n<li><strong>Days 27\u201330:<\/strong> complete cutover, remove dead credentials, and monitor error rates.<\/li>\n<\/ol>\n<p>Do not schedule the first production test on the shutdown date. Rate-limit changes, unavailable regions, schema differences, and prompt regressions need time to surface.<\/p>\n<h2>Frequently asked questions<\/h2>\n<h3>Is the OpenAI Assistants API still available?<\/h3>\n<p>No. The Assistants API was removed on August 26, 2026. OpenAI recommends the Responses API and Conversations API.<\/p>\n<h3>Will GPT-5 stop working in 2026?<\/h3>\n<p>Specific older GPT-5 snapshots listed by OpenAI shut down December 11, 2026. This does not mean every current GPT model disappears. Check the exact model ID in logs and configuration.<\/p>\n<h3>Does changing a model ID complete an API migration?<\/h3>\n<p>Usually not. Reasoning controls, tool calling, output schemas, pricing, latency, and safety behavior can differ. Run regression tests and compare cost per accepted result.<\/p>\n<h3>How can I find deprecated model IDs in a codebase?<\/h3>\n<p>Search source, environment templates, infrastructure configuration, database records, workflow builders, queues, notebooks, and CI fixtures. Also inspect API usage logs because dynamically stored IDs may not exist in source control.<\/p>\n<h2>Bottom line<\/h2>\n<p>The 2026 OpenAI deprecation schedule is not one migration. It is a series of product, model, prompt, evaluation, image, and agent deadlines. Start with Sora and September legacy models, then prepare for the October and November waves. A multi-model platform such as LLMFly AI can make portable model switches and price comparisons easier, but provider-specific products still require explicit migration work.<\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/developers.openai.com\/api\/docs\/deprecations\">OpenAI API deprecations<\/a><\/li>\n<li><a href=\"https:\/\/developers.openai.com\/api\/docs\/models\/gpt-6-astra\">OpenAI GPT-6 Astra model documentation<\/a><\/li>\n<li><a href=\"https:\/\/app.llmfly.ai\/model-plaza\">LLMFly AI Model Plaza<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>A developer migration calendar for every major OpenAI API shutdown remaining in 2026, with replacement models, checklists, and production rollout guidance.<\/p>\n","protected":false},"author":2,"featured_media":258,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[125,127],"tags":[152,149,46,151,134,25,73,150],"class_list":["post-257","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-api-integration","category-reliability-debugging","tag-agent-builder","tag-api-deprecation","tag-api-migration","tag-gpt-image","tag-gpt-5-6-sol","tag-openai-api","tag-responses-api","tag-sora-2"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>OpenAI API Deprecations 2026: Migration Deadlines<\/title>\n<meta name=\"description\" content=\"Track OpenAI API shutdown dates in 2026 for Sora 2, legacy GPT models, reusable prompts, Evals, Agent Builder, GPT Image, GPT-5, and o3.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"OpenAI API Deprecations 2026: Migration Deadlines\" \/>\n<meta property=\"og:description\" content=\"Track OpenAI API shutdown dates in 2026 for Sora 2, legacy GPT models, reusable prompts, Evals, Agent Builder, GPT Image, GPT-5, and o3.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/\" \/>\n<meta property=\"og:site_name\" content=\"LLM Fly Blog\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-07T08:04:55+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-09-07T08:04:57+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/09\/openai-api-deprecations-2026.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1536\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"mora\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"mora\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/\"},\"author\":{\"name\":\"mora\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#\\\/schema\\\/person\\\/9084f68fb2457e0fcdb27c8cd59f1d62\"},\"headline\":\"OpenAI API Deprecations in 2026: Migration Deadlines\",\"datePublished\":\"2026-09-07T08:04:55+00:00\",\"dateModified\":\"2026-09-07T08:04:57+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/\"},\"wordCount\":1278,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/openai-api-deprecations-2026.png\",\"keywords\":[\"Agent Builder\",\"API Deprecation\",\"API Migration\",\"GPT Image\",\"GPT-5.6 Sol\",\"OpenAI API\",\"Responses API\",\"Sora 2\"],\"articleSection\":[\"API Integration\",\"Reliability &amp; Debugging\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/\",\"url\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/\",\"name\":\"OpenAI API Deprecations 2026: Migration Deadlines\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/openai-api-deprecations-2026.png\",\"datePublished\":\"2026-09-07T08:04:55+00:00\",\"dateModified\":\"2026-09-07T08:04:57+00:00\",\"description\":\"Track OpenAI API shutdown dates in 2026 for Sora 2, legacy GPT models, reusable prompts, Evals, Agent Builder, GPT Image, GPT-5, and o3.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#primaryimage\",\"url\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/openai-api-deprecations-2026.png\",\"contentUrl\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/openai-api-deprecations-2026.png\",\"width\":1536,\"height\":1024,\"caption\":\"OpenAI API deprecation calendar and migration deadlines for 2026\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/2026\\\/09\\\/07\\\/openai-api-deprecations-2026\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"OpenAI API Deprecations in 2026: Migration Deadlines\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/\",\"name\":\"LLM Fly Blog\",\"description\":\"One Affordable AI API\",\"publisher\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#organization\",\"name\":\"LLM Fly Blog\",\"url\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/lofee_icon.jpg\",\"contentUrl\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/lofee_icon.jpg\",\"width\":512,\"height\":512,\"caption\":\"LLM Fly Blog\"},\"image\":{\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/#\\\/schema\\\/person\\\/9084f68fb2457e0fcdb27c8cd59f1d62\",\"name\":\"mora\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/2eba9dc6cfa9ae82cd42f59edb1ef77a0d2ab29849e7ef0c918a0bc58fb8ed43?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/2eba9dc6cfa9ae82cd42f59edb1ef77a0d2ab29849e7ef0c918a0bc58fb8ed43?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/2eba9dc6cfa9ae82cd42f59edb1ef77a0d2ab29849e7ef0c918a0bc58fb8ed43?s=96&d=mm&r=g\",\"caption\":\"mora\"},\"url\":\"https:\\\/\\\/llmfly.ai\\\/blog\\\/author\\\/mora\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"OpenAI API Deprecations 2026: Migration Deadlines","description":"Track OpenAI API shutdown dates in 2026 for Sora 2, legacy GPT models, reusable prompts, Evals, Agent Builder, GPT Image, GPT-5, and o3.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/","og_locale":"en_US","og_type":"article","og_title":"OpenAI API Deprecations 2026: Migration Deadlines","og_description":"Track OpenAI API shutdown dates in 2026 for Sora 2, legacy GPT models, reusable prompts, Evals, Agent Builder, GPT Image, GPT-5, and o3.","og_url":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/","og_site_name":"LLM Fly Blog","article_published_time":"2026-09-07T08:04:55+00:00","article_modified_time":"2026-09-07T08:04:57+00:00","og_image":[{"width":1536,"height":1024,"url":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/09\/openai-api-deprecations-2026.png","type":"image\/png"}],"author":"mora","twitter_card":"summary_large_image","twitter_misc":{"Written by":"mora","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#article","isPartOf":{"@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/"},"author":{"name":"mora","@id":"https:\/\/llmfly.ai\/blog\/#\/schema\/person\/9084f68fb2457e0fcdb27c8cd59f1d62"},"headline":"OpenAI API Deprecations in 2026: Migration Deadlines","datePublished":"2026-09-07T08:04:55+00:00","dateModified":"2026-09-07T08:04:57+00:00","mainEntityOfPage":{"@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/"},"wordCount":1278,"commentCount":0,"publisher":{"@id":"https:\/\/llmfly.ai\/blog\/#organization"},"image":{"@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#primaryimage"},"thumbnailUrl":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/09\/openai-api-deprecations-2026.png","keywords":["Agent Builder","API Deprecation","API Migration","GPT Image","GPT-5.6 Sol","OpenAI API","Responses API","Sora 2"],"articleSection":["API Integration","Reliability &amp; Debugging"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/","url":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/","name":"OpenAI API Deprecations 2026: Migration Deadlines","isPartOf":{"@id":"https:\/\/llmfly.ai\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#primaryimage"},"image":{"@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#primaryimage"},"thumbnailUrl":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/09\/openai-api-deprecations-2026.png","datePublished":"2026-09-07T08:04:55+00:00","dateModified":"2026-09-07T08:04:57+00:00","description":"Track OpenAI API shutdown dates in 2026 for Sora 2, legacy GPT models, reusable prompts, Evals, Agent Builder, GPT Image, GPT-5, and o3.","breadcrumb":{"@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#primaryimage","url":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/09\/openai-api-deprecations-2026.png","contentUrl":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/09\/openai-api-deprecations-2026.png","width":1536,"height":1024,"caption":"OpenAI API deprecation calendar and migration deadlines for 2026"},{"@type":"BreadcrumbList","@id":"https:\/\/llmfly.ai\/blog\/2026\/09\/07\/openai-api-deprecations-2026\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/llmfly.ai\/blog\/"},{"@type":"ListItem","position":2,"name":"OpenAI API Deprecations in 2026: Migration Deadlines"}]},{"@type":"WebSite","@id":"https:\/\/llmfly.ai\/blog\/#website","url":"https:\/\/llmfly.ai\/blog\/","name":"LLM Fly Blog","description":"One Affordable AI API","publisher":{"@id":"https:\/\/llmfly.ai\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/llmfly.ai\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/llmfly.ai\/blog\/#organization","name":"LLM Fly Blog","url":"https:\/\/llmfly.ai\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/llmfly.ai\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/08\/lofee_icon.jpg","contentUrl":"https:\/\/llmfly.ai\/blog\/wp-content\/uploads\/2026\/08\/lofee_icon.jpg","width":512,"height":512,"caption":"LLM Fly Blog"},"image":{"@id":"https:\/\/llmfly.ai\/blog\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/llmfly.ai\/blog\/#\/schema\/person\/9084f68fb2457e0fcdb27c8cd59f1d62","name":"mora","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/2eba9dc6cfa9ae82cd42f59edb1ef77a0d2ab29849e7ef0c918a0bc58fb8ed43?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/2eba9dc6cfa9ae82cd42f59edb1ef77a0d2ab29849e7ef0c918a0bc58fb8ed43?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2eba9dc6cfa9ae82cd42f59edb1ef77a0d2ab29849e7ef0c918a0bc58fb8ed43?s=96&d=mm&r=g","caption":"mora"},"url":"https:\/\/llmfly.ai\/blog\/author\/mora\/"}]}},"_links":{"self":[{"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/posts\/257","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/comments?post=257"}],"version-history":[{"count":1,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/posts\/257\/revisions"}],"predecessor-version":[{"id":259,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/posts\/257\/revisions\/259"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/media\/258"}],"wp:attachment":[{"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/media?parent=257"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/categories?post=257"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/llmfly.ai\/blog\/wp-json\/wp\/v2\/tags?post=257"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}