--- title: OpenAI promised developers six months’ notice. GPT-4o... description: OpenAI is retiring GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini from its API on January 14, 2027, giving developers only three months' notice despite a... canonical: https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenAI promised developers six months’ notice. GPT-4o users got three. | daily.dev og:description: OpenAI is retiring GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini from its API on January 14, 2027, giving developers only three months' notice despite a... og:url: https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw og:image: https://api.daily.dev/og/posts/sRBz67kXw.png og:image:alt: OpenAI promised developers six months’ notice. GPT-4o users got three. og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI promised developers six months’ notice. GPT-4o users got three. **[The New Stack](https://daily.dev/sources/newstack)** · 4 min read · 1 upvotes · 0 comments ## Summary OpenAI is retiring GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini from its API on January 14, 2027, giving developers only three months' notice despite a stated policy of at least six months for generally available models. The recommended replacement, GPT-6 Luna, differs significantly in reasoning and tool-call handling, complicating migration beyond a simple model ID swap. Luna offers a 1.05 million-token context window at $0.10/$0.50 per million input/output tokens, but pricing doubles past 272,000 input tokens, and combining reasoning with function calling requires switching to the Responses API. Self-serve fine-tuning ends January 6, 2027, and other model families (GPT-3.5, GPT-4, o-series, GPT-5 variants) have their own staggered retirement dates on OpenAI's deprecation schedule. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### When is OpenAI shutting down the GPT-4o and GPT-4.1 API models? OpenAI is retiring GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini from its API on January 14, 2027, along with their dated snapshots and any fine-tuned models built on them. The deprecation notice went out to developers on a Wednesday, giving only about three months to migrate production traffic, despite OpenAI's own policy promising at least six months' notice for generally available models. _Teams planning an API migration timeline can track OpenAI model deprecation news as it develops on daily.dev._ ### What changes when migrating from GPT-4.1 to GPT-6 Luna in the OpenAI API? GPT-6 Luna defaults to medium reasoning effort and only supports function calling through Chat Completions when reasoning_effort is set to none; combining reasoning with tool calls requires switching to the Responses API. Enabling reasoning also disables temperature, top_p, top_logprobs, and logprobs parameters, all of which were supported under GPT-4.1, so a simple model ID swap won't preserve existing behavior. _Developers weighing a GPT-6 Luna migration can compare model behavior changes like these before shipping on daily.dev._ ### How does GPT-6 Luna pricing work for long prompts? GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens, cheaper than GPT-5.6 Luna's $0.20 input and $1.20 output rates. However, once a prompt exceeds 272,000 input tokens, the input rate doubles and the output rate rises 50% for the entire request, which can erode savings for RAG pipelines and coding agents working across large codebases. _Anyone budgeting token costs for long-context coding agents can watch for pricing shifts like this on daily.dev._ ## Similar posts on daily.dev - [OpenAI axes ChatGPT models with just two weeks' warning](https://daily.dev/posts/openai-axes-chatgpt-models-with-just-two-weeks-warning-jr3z1jag0) · The Register · 1 upvotes · 0 comments - [OpenAI removes access to sycophancy-prone GPT-4o model](https://daily.dev/posts/openai-removes-access-to-sycophancy-prone-gpt-4o-model-ynmpphlzk) · TechCrunch · 1 upvotes · 0 comments - [Advancing the price-performance frontier with GPT‑5.6](https://daily.dev/posts/advancing-the-price-performance-frontier-with-gpt-5-6-kn3eddfk3) · OpenAI · 2 upvotes · 1 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#openai](https://daily.dev/tags/openai), [#gpt](https://daily.dev/tags/gpt) [View this post on daily.dev](https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI promised developers six months’ notice. GPT-4o users got three.","url":"https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw"},"datePublished":"2026-10-15T17:55:42.162Z","dateModified":"2026-10-15T18:05:42.053Z","description":"OpenAI is retiring GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini from its API on January 14, 2027, giving developers only three months' notice despite a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6360e8b5ddea2205fd804ceac607ff47?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/6360e8b5ddea2205fd804ceac607ff47?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,openai,gpt","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"OpenAI promised developers six months’ notice. GPT-4o users got three."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/openai-promised-developers-six-months-notice-gpt-4o-users-got-three--srbz67kxw#faq","mainEntity":[{"@type":"Question","name":"When is OpenAI shutting down the GPT-4o and GPT-4.1 API models?","acceptedAnswer":{"@type":"Answer","text":"OpenAI is retiring GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini from its API on January 14, 2027, along with their dated snapshots and any fine-tuned models built on them. The deprecation notice went out to developers on a Wednesday, giving only about three months to migrate production traffic, despite OpenAI's own policy promising at least six months' notice for generally available models. Teams planning an API migration timeline can track OpenAI model deprecation news as it develops on daily.dev."}},{"@type":"Question","name":"What changes when migrating from GPT-4.1 to GPT-6 Luna in the OpenAI API?","acceptedAnswer":{"@type":"Answer","text":"GPT-6 Luna defaults to medium reasoning effort and only supports function calling through Chat Completions when reasoning_effort is set to none; combining reasoning with tool calls requires switching to the Responses API. Enabling reasoning also disables temperature, top_p, top_logprobs, and logprobs parameters, all of which were supported under GPT-4.1, so a simple model ID swap won't preserve existing behavior. Developers weighing a GPT-6 Luna migration can compare model behavior changes like these before shipping on daily.dev."}},{"@type":"Question","name":"How does GPT-6 Luna pricing work for long prompts?","acceptedAnswer":{"@type":"Answer","text":"GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens, cheaper than GPT-5.6 Luna's $0.20 input and $1.20 output rates. However, once a prompt exceeds 272,000 input tokens, the input rate doubles and the output rate rises 50% for the entire request, which can erode savings for RAG pipelines and coding agents working across large codebases. Anyone budgeting token costs for long-context coding agents can watch for pricing shifts like this on daily.dev."}}]} ```