{"id":474646,"date":"2025-04-15T10:15:38","date_gmt":"2025-04-15T09:15:38","guid":{"rendered":"https:\/\/cryptoslate.com\/?p=474646"},"modified":"2025-04-15T10:42:22","modified_gmt":"2025-04-15T09:42:22","slug":"openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api","status":"publish","type":"post","link":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/","title":{"rendered":"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API"},"content":{"rendered":"

OpenAI has released<\/a> GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano to its API suite, phasing out GPT-4.5 Preview while advancing code generation, instruction following, and long-context processing capabilities.<\/p>\n

Essentially signaling the failure of GPT-4.5, the new\u00a0 4.1 models introduce context windows of up to one million tokens, enabling native handling of full repositories, extensive documents, and complex multi-turn agent workflows within a single call.<\/p>\n

While researching this article, I was able to use GPT-4.1 ‘vibe code,' a simple Python-based dungeon crawler, in 5 minutes and 5 prompts. The model made no errors in its code, with the only issues related to identifying relevant sprites in the asset atlas I imported.<\/p>\n

\"Dungeon
Dungeon crawler demo built with GPT-4.1<\/figcaption><\/figure>\n

Due to its large context window, it was also able to successfully identify the functionality of a large code repo within a few prompts.<\/p>\n

Model Capabilities and Transition Path<\/h2>\n

Per OpenAI, GPT-4.1 achieves<\/a> a 54.6% score on SWE-bench Verified, reflecting the improved ability to produce runnable code patches that resolve real-world repository issues. This outpaces GPT-4o\u2019s 33.2% and GPT-4.5\u2019s 38% under the same benchmark. The model also executes code diffs more precisely, with 53% accuracy on Aider\u2019s polyglot benchmark in diff format, more than doubling GPT-4o\u2019s 18%.<\/p>\n

Instruction-following fidelity is also refined. On Scale\u2019s MultiChallenge, GPT-4.1 reaches 38.3% accuracy, compared to 27.8% for GPT-4o. These improvements include adhering to strict output formats, complying with constraints, and following nested or contradictory instructions.<\/p>\n

According to the AI coding platform Windsurf, internal evaluations show that GPT-4.1 produces cleaner diffs and is more aligned with structured developer workflows.<\/p>\n

The models\u2019 ability to process long contexts includes 1 million token support, surpassing the previous 128K token window.<\/p>\n

To validate this, OpenAI released MRCR, an open-source evaluation that tests a model's ability to retrieve specific details from within dense, distractor-heavy context blocks. GPT-4.1 scored 72% on the long-video, no-subtitles category of the Video-MME benchmark, setting a new high.<\/p>\n

Efficiency gains across the series and agent use<\/h2>\n

The GPT-4.1 mini model provides latency and cost reductions while maintaining comparable performance. OpenAI stated that GPT-4.1 mini reduces inference latency by nearly 50% and cost by 83% relative to GPT-4o, with equal or superior scores on multiple intelligence evaluations.<\/p>\n

Meanwhile, GPT-4.1 nano, optimized for low-latency tasks, achieves 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider\u2019s polyglot coding. These gains exceed GPT-4o mini in critical areas and position nano for use in classification, autocomplete, and reactive agentic systems.<\/p>\n

There is no added cost for long-context use across the GPT-4.1 series. Token usage follows standard API pricing, allowing developers to scale applications involving large document retrieval, repository comprehension, or complete project editing without premium pricing tiers.<\/p>\n

Improvements in instruction fidelity and context retention bolster the model family\u2019s viability for agentic applications. With OpenAI\u2019s Responses API, developers can deploy GPT-4.1-based systems to autonomously execute chained operations such as resolving customer tickets, mining documents for insights, or operating across multi-step task environments.<\/p>\n

GPT-4.5 Preview, launched as a research-focused offering, will be sunset on July 14. According to OpenAI, feedback from 4.5\u2019s testing phase informed fine-tuning and deployment configurations, which are now embodied in GPT-4.1. As such, GPT-4.1 is positioned as a replacement path for developers using 4.5 in the API.<\/p>\n

ChatGPT users will continue interacting with GPT-4o, where OpenAI is incrementally integrating instruction-following improvements. GPT-4.1 models, however, are API-exclusive.<\/p>\n

Technical implications for code-first developers<\/h2>\n

The decision to scale the token context to one million is likely a response to Google's Gemini 2.1 Pro model. It impacts developers managing large monorepos, documentation-heavy domains, or multi-file dependency chains.<\/p>\n

In addition to traditional inference, GPT-4.1\u2019s upgraded token output limit, now up to 32,768 tokens, enables single-call full file rewrites, removing the need for post-processing or fragment merging.<\/p>\n

Adherence to structured formats allows developers to optimize workflows around minimal output generation for code diffs, cutting token costs and increasing system responsiveness.<\/p>\n

According to OpenAI\u2019s internal tests, GPT-4.1 has already demonstrated improved production results across frontend development, legal parsing, and backend automation.<\/p>\n

In comparative evaluations, paid graders preferred GPT-4.1-generated websites over GPT-4o results in 80% of test cases, citing superior functionality and clarity in HTML, CSS, and JavaScript output.<\/p>\n

GPT-4.1 mini and nano models extend these benefits to low-resource environments and latency-critical settings. The introduction of nano provides a fast-reacting, low-cost LLM capable of replacing larger models in rapid iteration pipelines, chat interfaces, or embedded dev tools.<\/p>\n

Developers using GPT-4.5 or GPT-4o mini are advised to evaluate migration paths now, as GPT-4.1\u2019s performance and token economics favor its adoption in most deployment configurations. Model access, prompting guides, and updated benchmarks are available through the OpenAI developer platform.<\/p>\n

Per OpenAI, GPT-4o and GPT-4o mini will continue to be supported in the API for the foreseeable future, but emphasis is being placed on the GPT-4.1 line as the preferred upgrade path.<\/p>\n","protected":false},"excerpt":{"rendered":"

OpenAI has released GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano to its API suite, phasing out GPT-4.5 Preview while advancing code generation, instruction following, and long-context processing capabilities. Essentially signaling the failure of GPT-4.5, the new\u00a0 4.1 models introduce context windows of up to one million tokens, enabling native handling of full repositories, extensive documents, and […]<\/p>\n","protected":false},"author":1264,"featured_media":474647,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[78326,77968],"tags":[],"post_folder":[],"acf":[],"yoast_head":"\nOpenAI releases 1 million token coding model GPT 4.1, available immediately via API<\/title>\n<meta name=\"description\" content=\"OpenAI's newest model phases out GPT-4.5, adding GPT-4.1 mini and nano for lower cost coding inference.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API\" \/>\n<meta property=\"og:description\" content=\"OpenAI's newest model phases out GPT-4.5, adding GPT-4.1 mini and nano for lower cost coding inference.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\" \/>\n<meta property=\"og:site_name\" content=\"CryptoSlate\" \/>\n<meta property=\"article:published_time\" content=\"2025-04-15T09:15:38+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-04-15T09:42:22+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/04\/openai-gpt41.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"630\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Liam 'Akiba' Wright\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@akibablade\" \/>\n<meta name=\"twitter:site\" content=\"@cryptoslate\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Liam 'Akiba' Wright\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\"},\"author\":{\"@type\":\"Person\",\"@id\":\"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/#person\",\"name\":\"Liam 'Akiba' Wright\",\"url\":\"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/\"},\"image\":{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/#authorimage\",\"url\":\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam.jpg\",\"contentUrl\":\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam.jpg\",\"caption\":\"Liam 'Akiba' Wright\"},\"jobTitle\":\"Editor-in-Chief\",\"description\":\"Liam \u201cAkiba\u201d Wright is CryptoSlate\u2019s Editor-in-Chief, reporter and podcast producer, focused on decentralized tech\u2019s positive impact.\",\"worksFor\":{\"@id\":\"https:\/\/cryptoslate.com\/#organization\"},\"sameAs\":[\"https:\/\/www.akiba.gg\",\"https:\/\/x.com\/akibablade\",\"https:\/\/www.linkedin.com\/in\/liamandrewwright\",\"https:\/\/muckrack.com\/liam-wright\/articles\"]},\"headline\":\"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API\",\"datePublished\":\"2025-04-15T09:15:38+00:00\",\"dateModified\":\"2025-04-15T09:42:22+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\"},\"wordCount\":819,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/cryptoslate.com\/#organization\"},\"articleSection\":[\"AI\",\"Featured\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#respond\"]}],\"copyrightYear\":\"2025\",\"copyrightHolder\":{\"@id\":\"https:\/\/cryptoslate.com\/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\",\"url\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\",\"name\":\"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API\",\"isPartOf\":{\"@id\":\"https:\/\/cryptoslate.com\/#website\"},\"datePublished\":\"2025-04-15T09:15:38+00:00\",\"dateModified\":\"2025-04-15T09:42:22+00:00\",\"description\":\"OpenAI's newest model phases out GPT-4.5, adding GPT-4.1 mini and nano for lower cost coding inference.\",\"breadcrumb\":{\"@id\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/cryptoslate.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/cryptoslate.com\/#website\",\"url\":\"https:\/\/cryptoslate.com\/\",\"name\":\"CryptoSlate\",\"description\":\"Cryptocurrency News and Real-time Coin Data\",\"publisher\":{\"@id\":\"https:\/\/cryptoslate.com\/#organization\"},\"inLanguage\":\"en-US\"},{\"@type\":\"NewsMediaOrganization\",\"@id\":\"https:\/\/cryptoslate.com\/#organization\",\"name\":\"CryptoSlate\",\"url\":\"https:\/\/cryptoslate.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/cryptoslate.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2018\/05\/c-logo.jpg\",\"contentUrl\":\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2018\/05\/c-logo.jpg\",\"width\":1000,\"height\":1000,\"caption\":\"CryptoSlate\"},\"image\":{\"@id\":\"https:\/\/cryptoslate.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/twitter.com\/cryptoslate\",\"https:\/\/www.instagram.com\/cryptoslate\",\"https:\/\/www.linkedin.com\/company\/cryptoslate\",\"https:\/\/www.youtube.com\/c\/cryptoslate\",\"https:\/\/cryptoslate.substack.com\",\"https:\/\/t.me\/cryptoslatenews\",\"https:\/\/www.crunchbase.com\/organization\/cryptoslate\",\"https:\/\/iq.wiki\/wiki\/cryptoslate\",\"https:\/\/news.google.com\/publications\/CAAqKggKIiRDQklTRlFnTWFoRUtEMk55ZVhCMGIzTnNZWFJsTG1OdmJTZ0FQAQ\",\"https:\/\/muckrack.com\/media-outlet\/cryptoslate\",\"https:\/\/www.tiktok.com\/@cryptoslatenews\"],\"publishingPrinciples\":\"https:\/\/cryptoslate.com\/editorial-policy\/#editorial-principles\",\"ownershipFundingInfo\":\"https:\/\/cryptoslate.com\/disclaimers\/how-cryptoslate-makes-and-spends-money\/\",\"correctionsPolicy\":\"https:\/\/cryptoslate.com\/editorial-policy\/#corrections-feedback\",\"ethicsPolicy\":\"https:\/\/cryptoslate.com\/editorial-policy\/#editorial-principles\",\"foundingDate\":\"2017-08-04\",\"founder\":[{\"@type\":\"Person\",\"name\":\"Nate Whitehill\"},{\"@type\":\"Person\",\"name\":\"Matthew Blancarte\"}],\"contactPoint\":[{\"@type\":\"ContactPoint\",\"contactType\":\"customer support\",\"url\":\"https:\/\/cryptoslate.com\/contact\/\",\"availableLanguage\":\"en-US\"},{\"@type\":\"ContactPoint\",\"contactType\":\"sales\",\"url\":\"https:\/\/cryptoslate.com\/advertising\/\",\"availableLanguage\":\"en-US\"},{\"@type\":\"ContactPoint\",\"contactType\":\"newsroom\",\"url\":\"https:\/\/cryptoslate.com\/editorial-policy\/#corrections-feedback\",\"email\":\"tips@cryptoslate.com\",\"availableLanguage\":\"en-US\"}],\"masthead\":\"https:\/\/cryptoslate.com\/about\/#masthead\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/cryptoslate.com\/#\/schema\/person\/ea2b02b41a7478e18d903ca8eec4979e\",\"name\":\"Liam 'Akiba' Wright\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/cryptoslate.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam-150x150.jpg\",\"contentUrl\":\"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam-150x150.jpg\",\"caption\":\"Liam 'Akiba' Wright\"},\"description\":\"Also known as \\\"Akiba,\\\" Liam Wright is the Editor-in-Chief at CryptoSlate and host of the SlateCast. He believes that together decentralized blockchain and AI technology have the potential to make widespread positive change.\",\"sameAs\":[\"https:\/\/www.akiba.gg\",\"https:\/\/www.instagram.com\/akibablade\",\"https:\/\/twitter.com\/akibablade\"],\"award\":[\"Most improved footballer - 1992\"],\"knowsAbout\":[\"Python\",\"Javascript\",\"PHP\",\"HTML\",\"Agentic Software\",\"Machine Learning\",\"2000s emo music\",\"Manchester United\"],\"knowsLanguage\":[\"English\",\"Spanish\"],\"url\":\"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API","description":"OpenAI's newest model phases out GPT-4.5, adding GPT-4.1 mini and nano for lower cost coding inference.","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:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/","og_locale":"en_US","og_type":"article","og_title":"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API","og_description":"OpenAI's newest model phases out GPT-4.5, adding GPT-4.1 mini and nano for lower cost coding inference.","og_url":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/","og_site_name":"CryptoSlate","article_published_time":"2025-04-15T09:15:38+00:00","article_modified_time":"2025-04-15T09:42:22+00:00","og_image":[{"width":1200,"height":630,"url":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/04\/openai-gpt41.jpg","type":"image\/jpeg"}],"author":"Liam 'Akiba' Wright","twitter_card":"summary_large_image","twitter_creator":"@akibablade","twitter_site":"@cryptoslate","twitter_misc":{"Written by":"Liam 'Akiba' Wright","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#article","isPartOf":{"@id":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/"},"author":{"@type":"Person","@id":"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/#person","name":"Liam 'Akiba' Wright","url":"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/","mainEntityOfPage":{"@id":"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/"},"image":{"@type":"ImageObject","@id":"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/#authorimage","url":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam.jpg","contentUrl":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam.jpg","caption":"Liam 'Akiba' Wright"},"jobTitle":"Editor-in-Chief","description":"Liam \u201cAkiba\u201d Wright is CryptoSlate\u2019s Editor-in-Chief, reporter and podcast producer, focused on decentralized tech\u2019s positive impact.","worksFor":{"@id":"https:\/\/cryptoslate.com\/#organization"},"sameAs":["https:\/\/www.akiba.gg","https:\/\/x.com\/akibablade","https:\/\/www.linkedin.com\/in\/liamandrewwright","https:\/\/muckrack.com\/liam-wright\/articles"]},"headline":"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API","datePublished":"2025-04-15T09:15:38+00:00","dateModified":"2025-04-15T09:42:22+00:00","mainEntityOfPage":{"@id":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/"},"wordCount":819,"commentCount":0,"publisher":{"@id":"https:\/\/cryptoslate.com\/#organization"},"articleSection":["AI","Featured"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#respond"]}],"copyrightYear":"2025","copyrightHolder":{"@id":"https:\/\/cryptoslate.com\/#organization"}},{"@type":"WebPage","@id":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/","url":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/","name":"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API","isPartOf":{"@id":"https:\/\/cryptoslate.com\/#website"},"datePublished":"2025-04-15T09:15:38+00:00","dateModified":"2025-04-15T09:42:22+00:00","description":"OpenAI's newest model phases out GPT-4.5, adding GPT-4.1 mini and nano for lower cost coding inference.","breadcrumb":{"@id":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/cryptoslate.com\/openai-releases-1-million-token-context-coding-model-gpt-4-1-available-immediately-via-api\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/cryptoslate.com\/"},{"@type":"ListItem","position":2,"name":"OpenAI releases 1 million token coding model GPT 4.1, available immediately via API"}]},{"@type":"WebSite","@id":"https:\/\/cryptoslate.com\/#website","url":"https:\/\/cryptoslate.com\/","name":"CryptoSlate","description":"Cryptocurrency News and Real-time Coin Data","publisher":{"@id":"https:\/\/cryptoslate.com\/#organization"},"inLanguage":"en-US"},{"@type":"NewsMediaOrganization","@id":"https:\/\/cryptoslate.com\/#organization","name":"CryptoSlate","url":"https:\/\/cryptoslate.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cryptoslate.com\/#\/schema\/logo\/image\/","url":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2018\/05\/c-logo.jpg","contentUrl":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2018\/05\/c-logo.jpg","width":1000,"height":1000,"caption":"CryptoSlate"},"image":{"@id":"https:\/\/cryptoslate.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/twitter.com\/cryptoslate","https:\/\/www.instagram.com\/cryptoslate","https:\/\/www.linkedin.com\/company\/cryptoslate","https:\/\/www.youtube.com\/c\/cryptoslate","https:\/\/cryptoslate.substack.com","https:\/\/t.me\/cryptoslatenews","https:\/\/www.crunchbase.com\/organization\/cryptoslate","https:\/\/iq.wiki\/wiki\/cryptoslate","https:\/\/news.google.com\/publications\/CAAqKggKIiRDQklTRlFnTWFoRUtEMk55ZVhCMGIzTnNZWFJsTG1OdmJTZ0FQAQ","https:\/\/muckrack.com\/media-outlet\/cryptoslate","https:\/\/www.tiktok.com\/@cryptoslatenews"],"publishingPrinciples":"https:\/\/cryptoslate.com\/editorial-policy\/#editorial-principles","ownershipFundingInfo":"https:\/\/cryptoslate.com\/disclaimers\/how-cryptoslate-makes-and-spends-money\/","correctionsPolicy":"https:\/\/cryptoslate.com\/editorial-policy\/#corrections-feedback","ethicsPolicy":"https:\/\/cryptoslate.com\/editorial-policy\/#editorial-principles","foundingDate":"2017-08-04","founder":[{"@type":"Person","name":"Nate Whitehill"},{"@type":"Person","name":"Matthew Blancarte"}],"contactPoint":[{"@type":"ContactPoint","contactType":"customer support","url":"https:\/\/cryptoslate.com\/contact\/","availableLanguage":"en-US"},{"@type":"ContactPoint","contactType":"sales","url":"https:\/\/cryptoslate.com\/advertising\/","availableLanguage":"en-US"},{"@type":"ContactPoint","contactType":"newsroom","url":"https:\/\/cryptoslate.com\/editorial-policy\/#corrections-feedback","email":"tips@cryptoslate.com","availableLanguage":"en-US"}],"masthead":"https:\/\/cryptoslate.com\/about\/#masthead"},{"@type":"Person","@id":"https:\/\/cryptoslate.com\/#\/schema\/person\/ea2b02b41a7478e18d903ca8eec4979e","name":"Liam 'Akiba' Wright","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/cryptoslate.com\/#\/schema\/person\/image\/","url":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam-150x150.jpg","contentUrl":"https:\/\/cryptoslate.com\/wp-content\/uploads\/2025\/10\/about-liam-150x150.jpg","caption":"Liam 'Akiba' Wright"},"description":"Also known as \"Akiba,\" Liam Wright is the Editor-in-Chief at CryptoSlate and host of the SlateCast. He believes that together decentralized blockchain and AI technology have the potential to make widespread positive change.","sameAs":["https:\/\/www.akiba.gg","https:\/\/www.instagram.com\/akibablade","https:\/\/twitter.com\/akibablade"],"award":["Most improved footballer - 1992"],"knowsAbout":["Python","Javascript","PHP","HTML","Agentic Software","Machine Learning","2000s emo music","Manchester United"],"knowsLanguage":["English","Spanish"],"url":"https:\/\/cryptoslate.com\/author\/liam-akiba-wright\/"}]}},"_links":{"self":[{"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/posts\/474646"}],"collection":[{"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/users\/1264"}],"replies":[{"embeddable":true,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/comments?post=474646"}],"version-history":[{"count":11,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/posts\/474646\/revisions"}],"predecessor-version":[{"id":474665,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/posts\/474646\/revisions\/474665"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/media\/474647"}],"wp:attachment":[{"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/media?parent=474646"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/categories?post=474646"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/tags?post=474646"},{"taxonomy":"post_folder","embeddable":true,"href":"https:\/\/cryptoslate.com\/wp-json\/wp\/v2\/post_folder?post=474646"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}