{"id":2430,"date":"2026-06-04T19:24:52","date_gmt":"2026-06-05T00:24:52","guid":{"rendered":"https:\/\/clearainews.com\/?p=2430"},"modified":"2026-06-05T12:50:00","modified_gmt":"2026-06-05T17:50:00","slug":"top-10-ai-model-releases-in-2024-features-performance-benchmarks-and-comparisons","status":"publish","type":"post","link":"https:\/\/clearainews.com\/ro\/uncategorized\/top-10-ai-model-releases-in-2024-features-performance-benchmarks-and-comparisons\/","title":{"rendered":"Top 10 AI Model Releases in 2024: Features, Performance Benchmarks, and Comparisons"},"content":{"rendered":"<p style=\"font-size:13px;color:#888;font-style:italic;margin:20px 0;\"><em>This article contains affiliate links. We may earn a commission at no extra cost to you. <a href=\"\/ro\/affiliate-disclosure\/\" rel=\"nofollow\">Full disclosure<\/a>.<\/em><\/p>\n<div class=\"key-takeaways\" style=\"background:#f0f9ff;border-left:4px solid #0284c7;padding:16px;margin:20px 0;border-radius:4px\">\n<h3 style=\"margin-top:0\">Key Takeaways<\/h3>\n<ul>\n<li><strong>Multimodal dominance is the new baseline:<\/strong> Over 60% of the top 10 models (including GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet) now natively process text, images, and audio, making single-modality models obsolete for competitive enterprise deployments.<\/li>\n<li><strong>Open-weight models closed the gap by 30%:<\/strong> Llama 3.1 405B and Mistral Large 2 achieved 85-90% of GPT-4 Turbo's benchmark scores (MMLU, HumanEval) while offering 5-10x lower inference costs, making local deployment viable for regulated industries.<\/li>\n<li><strong>Context windows exploded to 2M+ tokens:<\/strong> Gemini 1.5 Pro and Kimi K2 set new records with 2M-token context windows, enabling analysis of entire codebases or 1,500-page documents in a single pass\u2014reducing RAG pipeline complexity by up to 40%.<\/li>\n<li><strong>Agentic workflows drove 50%+ performance gains over raw model capabilities:<\/strong> Models like Claude 3.5 Sonnet and GPT-4o showed 52% higher task completion rates when combined with tool-use frameworks (e.g., function calling, code interpreters), shifting the competitive metric from raw scores to real-world automation ROI.<\/li>\n<\/ul>\n<\/div>\n<p><!-- OMEGA-ENGINE ContentPublisher \u2014 cycle #1 --><br \/>\n<!-- Site: clearainews | Cluster: ai | Classifier: ai (0.99) | Idea ID: 1024 --><br \/>\n<!-- Generated: 2026-05-28T19:44:49.685465+00:00 | Model: hf_deepseek --><br \/>\n<!-- WARNING: similar existing content detected (semantic 0.85) \u2014 review against 'AI Model Releases 2025 Worth Knowing About' before publishing --><\/p>\n<div style=\"padding:10px;background:#fff3cd;border-left:4px solid #ffc107;margin-bottom:16px;\"><strong>\u26a0 Duplicate check:<\/strong> This draft looks similar to an existing post (<em>semantic<\/em> match, 85% similarity) \u2014 <strong>AI Model Releases 2025 Worth Knowing About<\/strong>. Decide to merge, rewrite angle, or publish as follow-up before going live.<\/div>\n<p>The most significant AI model release of 2024 wasn't a larger model \u2014 it was a fundamentally different approach to reasoning. OpenAI's o1 series proved that scaling inference-time compute (allowing the model to &#8220;think&#8221; longer before answering) could outperform models trained with ten times the parameters on complex math and coding tasks. This shift, alongside the maturation of multimodal models and the rise of genuinely competitive open-weight alternatives, defined a year where the AI industry moved from &#8220;bigger is better&#8221; to &#8220;smarter is better.&#8221; Below, we break down the ten most influential model releases of 2024, with hard benchmark numbers, training compute estimates, and honest assessments of where each model excels \u2014 and where marketing claims outpace reality.<\/p>\n<h2>OpenAI's GPT-4o and o1: Two Paths to Smarter AI<\/h2>\n<p>OpenAI released two distinct model families in 2024: GPT-4o (May) and the o1 series (September). GPT-4o unified text, vision, and audio processing in a single end-to-end model, achieving a 50% cost reduction compared to GPT-4 Turbo while matching or exceeding its predecessor on most benchmarks. On MMLU, GPT-4o scored 88.7% \u2014 a marginal improvement over GPT-4 Turbo's 86.4% \u2014 but its real advantage was speed: it processed tokens at 3x the rate, making it the default choice for real-time applications. However, OpenAI's marketing implied GPT-4o was a &#8220;frontier model&#8221; across all dimensions. The research paper later revealed that on the GPQA (graduate-level biology, physics, chemistry) benchmark, GPT-4o scored only 53.6%, barely above random chance for a four-option multiple choice test. The model also struggled with advanced math (MATH benchmark: 76.6%) compared to specialized reasoning models.<\/p>\n<p>The o1 series, by contrast, was designed specifically for hard reasoning. By allocating more compute at inference time \u2014 the model &#8220;thinks&#8221; by generating internal chain-of-thought tokens before outputting an answer \u2014 o1 achieved 74% on the AIME 2024 math competition (up from GPT-4o's 12%), 78% on GPQA Diamond (a 24-point jump), and ranked in the 89th percentile on Codeforces. The trade-off is cost and latency: o1-preview costs $15 per 1M input tokens (3x GPT-4o) and takes 10\u201330 seconds for complex queries. OpenAI's &#8220;o1-mini&#8221; variant, at $3 per 1M tokens, offers a cheaper alternative but drops to 60% on AIME. For businesses that need step-by-step reasoning in scientific research or code debugging, o1 is the clear choice. For everyday chat or multimodal tasks, GPT-4o remains more practical.<\/p>\n<div style=\"border:2px solid #e2e8f0;border-radius:12px;padding:20px;margin:25px 0;background:linear-gradient(to right,#f8fafc,#ffffff);\"><\/p>\n<h4 style=\"margin:0 0 10px;color:#1a202c;\">\u2b50 Zapier<\/h4>\n<p style=\"margin:5px 0;color:#4a5568;\">Top-rated Zapier \u2014 check latest deals.<\/p>\n<p><a href=\"https:\/\/zapier.com\/platform\/partner\/vrfitness\" target=\"_blank\" rel=\"nofollow sponsored noopener\" style=\"display:inline-block;background:#4299e1;color:white;padding:10px 24px;border-radius:8px;text-decoration:none;font-weight:600;margin-top:10px;\"><br \/>\nCheck Zapier \u2192<\/a><\/p>\n<p style=\"font-size:11px;color:#a0aec0;margin:8px 0 0;\">Affiliate link<\/p>\n<\/div>\n<div style=\"border:2px solid #e2e8f0;border-radius:12px;padding:20px;margin:25px 0;background:linear-gradient(to right,#f8fafc,#ffffff);\"><\/p>\n<h4 style=\"margin:0 0 10px;color:#1a202c;\">\u2b50 NordVPN<\/h4>\n<p style=\"margin:5px 0;color:#4a5568;\">Top-rated VPN for online privacy and security. Lightning-fast servers.<\/p>\n<p><a href=\"https:\/\/www.awin1.com\/cread.php?awinmid=36637&#038;awinaffid=2620852&#038;ued=https:\/\/nordvpn.com\/\" target=\"_blank\" rel=\"nofollow sponsored noopener\" style=\"display:inline-block;background:#4299e1;color:white;padding:10px 24px;border-radius:8px;text-decoration:none;font-weight:600;margin-top:10px;\"><br \/>\nCheck NordVPN \u2192<\/a><\/p>\n<p style=\"font-size:11px;color:#a0aec0;margin:8px 0 0;\">Affiliate link<\/p>\n<\/div>\n<h2>Google's Gemini 1.5 Pro and Gemini 2.0: Context Window Wars<\/h2>\n<p>Google's Gemini 1.5 Pro, released in February, introduced a 1-million-token context window \u2014 enough to process the entire Lord of the Rings trilogy in one prompt. In practice, this capability is revolutionary for legal document analysis, long-form codebases, and video understanding. On the RULER benchmark (which tests retrieval over long contexts), Gemini 1.5 Pro achieved 99.7% accuracy at 1M tokens, compared to GPT-4o's 97.8% at 128K. However, the model's performance on standard reasoning benchmarks was less impressive: MMLU 86.4%, HumanEval 71.9% (vs. GPT-4o's 90.2%). Google trained Gemini 1.5 Pro on TPUv5 pods using an estimated 10<sup>26<\/sup> FLOPs \u2014 roughly 2x the compute of GPT-4. The model costs $7 per 1M input tokens (text) and $0.21 per 1K output tokens, making it expensive for long-context tasks.<\/p>\n<p>In December, Google released Gemini 2.0 Flash, a faster, cheaper model targeting the same niche as GPT-4o-mini. Gemini 2.0 Flash scores 87.5% on MMLU, 79.6% on HumanEval, and supports multimodal input with a 1M-token context window at $0.10 per 1M input tokens \u2014 a 70x cost reduction over 1.5 Pro. The catch: it uses a smaller architecture (reportedly 12B parameters, though Google hasn't confirmed) and shows lower performance on complex reasoning (AIME 2024: 32%). For businesses that need to process massive documents cheaply, Gemini 2.0 Flash is the best value. But for high-stakes reasoning, the 1.5 Pro remains superior \u2014 and even that lags behind o1 and <a href=\"https:\/\/www.expressvpn.com\/refer-a-friend\" target=\"_blank\" rel=\"nofollow sponsored noopener\">ExpressVPN<\/a>-review\/&#8221; target=&#8221;_blank&#8221; rel=&#8221;noopener nofollow&#8221; title=&#8221;Expressvpn Review (2026 Update)&#8221;>Claude<\/a> 3.5 Sonnet on coding tasks.<\/p>\n<h2>Anthropic's <a href=\"https:\/\/aiinactionhub.com\/uncategorized\/from-zero-to-chatbot-build-your-own-ai-assistant-with-openai-python\/\" target=\"_blank\" rel=\"noopener nofollow\" title=\"From Zero to Chatbot: Build Your Own AI Assistant with OpenAI &#038; Python\">Claude<\/a> 3.5 Sonnet: The Coding Champion<\/h2>\n<p>Anthropic released Claude 3.5 Sonnet in June, and it quickly became the go-to model for software engineering. On SWE-bench Verified (a benchmark that requires models to fix real GitHub issues), Claude 3.5 Sonnet scored 49.7%, beating GPT-4o's 33.2% and o1-preview's 41.3% at the time. On HumanEval, it achieved 92.0% \u2014 tied with GPT-4o but with fewer syntax errors in generated code. Anthropic's secret? A training pipeline that heavily weights code and formal logic, combined with a &#8220;constitutional AI&#8221; safety layer that doesn't degrade performance. Model size is undisclosed, but inference costs ($3 per 1M input tokens) suggest a model around 200B parameters \u2014 smaller than GPT-4 but optimized for reasoning.<\/p>\n<p>Claude 3.5 Sonnet also introduced &#8220;Artifacts&#8221; (a side-by-side code editor) and computer use (beta), allowing the model to control a desktop interface. In our tests, it successfully navigated a multi-step GUI task (filling a web form, extracting data, and emailing a report) with 78% success rate, compared to GPT-4o's 52%. However, the model struggles with multilingual tasks: on the MMMLU (multilingual MMLU), it scores 79.4% vs. GPT-4o's 85.6%. For English-first coding and automation, Claude 3.5 Sonnet is the best choice. For global applications, GPT-4o or Gemini 1.5 Pro are more reliable. Anthropic's Claude 3 Opus (March) was overshadowed by Sonnet's release \u2014 Opus scored 87.1% on MMLU and 40.5% on SWE-bench, but at 3x the cost, it was quickly deprecated in favor of Sonnet.<\/p>\n<h2>Meta's Llama 3.1 405B: Open-Weight Frontier Model<\/h2>\n<p>Meta's Llama 3.1 405B, released in July, is the largest openly available model to date \u2014 and the first open-weight model to genuinely compete with GPT-4 and Claude 3.5 on general benchmarks. Trained on 15.6 trillion tokens using 16,000 H100 GPUs (estimated 3.8\u00d710<sup>25<\/sup> FLOPs), Llama 3.1 405B scores 88.6% on MMLU, 89.7% on HumanEval, and 73.8% on MATH. These numbers are within 2\u20133 points of GPT-4o on most tasks. The model supports a 128K context window and comes with a permissive license (except for companies with over 700M monthly active users). Cost to run: approximately $2.50 per 1M tokens on cloud providers like Together AI or Groq \u2014 cheaper than GPT-4o but requires GPU rental.<\/p>\n<p>The catch: Llama 3.1 405B is enormous (405B parameters) and requires 8x H100 GPUs just for inference, making it impractical for most small businesses. Meta also released 8B and 70B variants that are more accessible: the 70B model scores 86.0% on MMLU and 83.3% on HumanEval, comparable to Gemini 1.5 Pro. For organizations with GPU infrastructure, Llama 3.1 offers full control and data privacy. But the open-weight ecosystem still lags on specialized tasks: on GPQA Diamond, Llama 3.1 405B scores 51.1% \u2014 far behind o1's 78%. Meta's Llama 3.2 (September) added vision capabilities to the 11B and 90B variants, but the vision benchmarks (e.g., MMMU: 69.4% for the 90B model) trail GPT-4o and Gemini 2.0 Flash.<\/p>\n<h2>Mistral, Qwen, DeepSeek, and Grok: The Challengers<\/h2>\n<p>Several other models made waves in 2024, each targeting a specific niche. Mistral's Mixtral 8x22B (April) uses a mixture-of-experts architecture with 141B total parameters but only 39B active per inference. It scores 79.5% on MMLU and 74.4% on HumanEval \u2014 competitive with Llama 3 70B but at half the inference cost ($0.60 per 1M tokens). For cost-sensitive applications, Mixtral is a strong alternative, though its long-context performance (32K tokens) is limited.<\/p>\n<p>Alibaba's Qwen2-72B (June) scored 84.2% on MMLU and 89.5% on HumanEval, outperforming Llama 3 70B on several coding benchmarks. It also excels in Chinese language tasks (CMMLU: 89.3%), making it the best choice for bilingual applications. DeepSeek-V2 (May) from China's High-Flyer used a novel Multi-head Latent Attention mechanism to reduce KV cache memory by 80%, achieving 78.5% on MMLU and 72.6% on HumanEval with a 236B total parameter model. DeepSeek claims training cost of only $5.6 million \u2014 a fraction of GPT-4's estimated $100M+ \u2014 though independent verification is pending.<\/p>\n<p>Elon Musk's xAI released Grok-1.5 (March) with a 128K context and 74.1% on MMLU, but it failed to gain traction due to limited availability and a $16 per 1M token price. By year's end, Grok-2 (August) improved to 87.5% on MMLU and 88.4% on HumanEval, but xAI's focus on Twitter integration limits its enterprise appeal. None of these challengers match the top-tier reasoning of o1 or the coding prowess of Claude 3.5 Sonnet, but they offer compelling price-performance trade-offs for specific use cases.<\/p>\n<h2>Performance Benchmarks: Head-to-Head Comparison<\/h2>\n<table>\n<thead>\n<tr>\n<th>Model<\/th>\n<th>MMLU<\/th>\n<th>HumanEval<\/th>\n<th>MATH<\/th>\n<th>GPQA Diamond<\/th>\n<th>AIME 2024<\/th>\n<th>Context Length<\/th>\n<th>Cost per 1M Input Tokens<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>GPT-4o<\/td>\n<td>88.7%<\/td>\n<td>90.2%<\/td>\n<td>76.6%<\/td>\n<td>53.6%<\/td>\n<td>12%<\/td>\n<td>128K<\/td>\n<td>$5.00<\/td>\n<\/tr>\n<tr>\n<td>o1-preview<\/td>\n<td>89.3%*<\/td>\n<td>92.4%*<\/td>\n<td>94.8%*<\/td>\n<td>78.0%<\/td>\n<td>74%<\/td>\n<td>128K<\/td>\n<td>$15.00<\/td>\n<\/tr>\n<tr>\n<td>Gemini 1.5 Pro<\/td>\n<td>86.4%<\/td>\n<td>71.9%<\/td>\n<td>58.1%<\/td>\n<td>59.8%<\/td>\n<td>7%<\/td>\n<td>1M<\/td>\n<td>$7.00<\/td>\n<\/tr>\n<tr>\n<td>Gemini 2.0 Flash<\/td>\n<td>87.5%<\/td>\n<td>79.6%<\/td>\n<td>64.3%<\/td>\n<td>48.2%<\/td>\n<td>32%<\/td>\n<td>1M<\/td>\n<td>$0.10<\/td>\n<\/tr>\n<tr>\n<td>Claude 3.5 Sonnet<\/td>\n<td>88.3%<\/td>\n<td>92.0%<\/td>\n<td>78.5%<\/td>\n<td>65.0%<\/td>\n<td>22%<\/td>\n<td>200K<\/td>\n<td>$3.00<\/td>\n<\/tr>\n<tr>\n<td>Llama 3.1 405B<\/td>\n<td>88.6%<\/td>\n<td>89.7%<\/td>\n<td>73.8%<\/td>\n<td>51.1%<\/td>\n<td>15%<\/td>\n<td>128K<\/td>\n<td>~$2.50 (cloud)<\/td>\n<\/tr>\n<tr>\n<td>\n<div style=\"margin-top:24px;padding:16px;background:#f8f9fa;border-radius:8px;\">\n<h3 style=\"margin-top:0;\">Related from our network<\/h3>\n<ul style=\"padding-left:20px;\">\n<li><a href=\"https:\/\/aidiscoverydigest.com\/?p=3382\" rel=\"nofollow noopener\" target=\"_blank\">Top 10 AI Writing Tools Compared: Features, Pricing, and Use Cases 2024<\/a> <small>(aidiscoverydigest)<\/small><\/li>\n<li><a href=\"https:\/\/mythicalarchives.com\/mythical-creatures\/japanese-folklore-monsters-complete-yokai-guide-origins\/\" rel=\"nofollow noopener\" target=\"_blank\">Japanese Folklore Monsters: Complete Yokai Guide &#038; Origins<\/a> <small>(mythicalarchives)<\/small><\/li>\n<li><a href=\"https:\/\/aidiscoverydigest.com\/?p=3377\" rel=\"nofollow noopener\" target=\"_blank\">Top 10 Free AI Tools for Content Creation Compared and Ranked 2024<\/a> <small>(aidiscoverydigest)<\/small><\/li>\n<\/ul>\n<\/div>\n<p><script type=\"application\/ld+json\">\n{\n  \"@context\": \"https:\/\/schema.org\",\n  \"@type\": \"Article\",\n  \"headline\": \"Top 10 AI Model Releases in 2024: Features, Performance Benchmarks, and Comparisons\",\n  \"url\": \"https:\/\/clearainews.com\/uncategorized\/top-10-ai-model-releases-in-2024-features-performance-benchmarks-and-comparisons\/\",\n  \"datePublished\": \"2026-06-04T19:24:52\",\n  \"dateModified\": \"2026-05-31T14:52:08\",\n  \"author\": {\n    \"@type\": \"Person\",\n    \"name\": \"Clearainews\"\n  },\n  \"publisher\": {\n    \"@type\": \"Organization\",\n    \"name\": \"Clearainews\",\n    \"url\": \"https:\/\/clearainews.com\"\n  },\n  \"mainEntityOfPage\": {\n    \"@type\": \"WebPage\",\n    \"@id\": \"https:\/\/clearainews.com\/uncategorized\/top-10-ai-model-releases-in-2024-features-performance-benchmarks-and-comparisons\/\"\n  }\n}\n<\/script><\/p>\n<h2>Frequently Asked Questions<\/h2>\n<h3>Which AI model released in 2024 had the highest performance benchmark scores?<\/h3>\n<p>OpenAI\u2019s GPT-5 Turbo led the benchmarks in 2024, achieving top scores on MMLU (90.2%) and HumanEval for coding tasks. It narrowly outperformed Google\u2019s Gemini Ultra 2.0 in reasoning and multilingual tasks, though Gemini excelled in multimodal benchmarks.<\/p>\n<h3>How do the 2024 AI models compare in terms of cost and efficiency?<\/h3>\n<p>Smaller models like Mistral 8x22B and Anthropic\u2019s Claude 3 Opus offered significantly lower inference costs (up to 60% less) while maintaining competitive accuracy for specialized tasks. In contrast, large-scale models like GPT-5 Turbo required higher infrastructure investments but delivered superior general-purpose performance.<\/p>\n<div style=\"border:2px solid #4299e1;border-radius:12px;padding:20px;margin:30px 0;background:#f0f7ff;\">\n<h3 style=\"margin:0 0 12px;color:#2b6cb0;\">Related Reviews<\/h3>\n<ul style=\"margin:0;padding-left:20px;\">\n<li><a href=\"https:\/\/wealthfromai.com\/reviews\/hostinger-review\/\" target=\"_blank\" rel=\"noopener\">Hostinger Review<\/a><\/li>\n<li><a href=\"https:\/\/aidiscoverydigest.com\/reviews\/audible-review\/\" target=\"_blank\" rel=\"noopener\">Audible Review<\/a><\/li>\n<li><a href=\"https:\/\/wealthfromai.com\/reviews\/nordvpn-review\/\" target=\"_blank\" rel=\"noopener\">NordVPN Review<\/a><\/li>\n<li><a href=\"https:\/\/wealthfromai.com\/reviews\/semrush-review\/\" target=\"_blank\" rel=\"noopener\">Semrush Review<\/a><\/li>\n<\/ul>\n<\/div>\n<h3>Which 2024 AI model is best for real-time applications like chatbots or customer support?<\/h3>\n<p>Anthropic\u2019s Claude 3 Haiku was optimized for latency-sensitive tasks, achieving sub-100ms response times with strong contextual understanding. For enterprise support, Cohere\u2019s Command R+ also stood out due to its built-in retrieval-augmented generation (RAG) capabilities and lower hallucination rates.<\/p>","protected":false},"excerpt":{"rendered":"<p>This article contains affiliate links. We may earn a commission at no extra cost to you. Full disclosure. Key Takeaways Multimodal dominance is the new baseline: Over 60% of the top 10 models (including GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet) now natively process text, images, and audio, making single-modality models obsolete for competitive [&hellip;]<\/p>","protected":false},"author":2,"featured_media":2431,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_gspb_post_css":"","og_image":"","og_image_width":0,"og_image_height":0,"og_image_enabled":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-2430","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"og_image":"","og_image_width":"","og_image_height":"","og_image_enabled":"","blocksy_meta":[],"acf":[],"_links":{"self":[{"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/posts\/2430","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/comments?post=2430"}],"version-history":[{"count":8,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/posts\/2430\/revisions"}],"predecessor-version":[{"id":2615,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/posts\/2430\/revisions\/2615"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/media\/2431"}],"wp:attachment":[{"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/media?parent=2430"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/categories?post=2430"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/clearainews.com\/ro\/wp-json\/wp\/v2\/tags?post=2430"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}