[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"aiModelCatalog":3},{"developers":4,"tags":49,"models":161},[5,9,13,17,21,25,29,33,37,41,45],{"code":6,"name":7,"logo_url":8},"anthropic","Anthropic","https://img.beget.com/b/plain/icons/anthropic-72-outlined.svg",{"code":10,"name":11,"logo_url":12},"deepseek","DeepSeek","https://img.beget.com/b/plain/icons/deepseek-72-outlined.svg",{"code":14,"name":15,"logo_url":16},"glm","GLM","https://img.beget.com/b/plain/icons/glm-72-outlined.svg",{"code":18,"name":19,"logo_url":20},"google","Google","https://img.beget.com/b/plain/icons/google-72-outlined.svg",{"code":22,"name":23,"logo_url":24},"kimi","Kimi","https://img.beget.com/b/plain/icons/kimi-72-outlined.svg",{"code":26,"name":27,"logo_url":28},"meta","Meta","https://img.beget.com/b/plain/icons/meta-72-outlined.svg",{"code":30,"name":31,"logo_url":32},"minimax","MiniMax","https://img.beget.com/b/plain/icons/minimax-72-outlined.svg",{"code":34,"name":35,"logo_url":36},"mistralai","Mistral AI","https://img.beget.com/b/plain/icons/mistralai-72-outlined.svg",{"code":38,"name":39,"logo_url":40},"openai","OpenAI","https://img.beget.com/b/plain/icons/openai-72-outlined.svg",{"code":42,"name":43,"logo_url":44},"qwen","Qwen","https://img.beget.com/b/plain/icons/qwen-72-outlined.svg",{"code":46,"name":47,"logo_url":48},"xai","xAI","https://img.beget.com/b/plain/icons/xai-72-outlined.svg",[50,65,76,87,98,110,121,133,144],{"code":51,"title":52,"tooltip":59,"tag_class":60,"is_filter":61,"filter_title":62},"universal-quality",[53,56],{"locale":54,"value":55},"EN","General-purpose",{"locale":57,"value":58},"RU","Универсальная",[],"CLASS_UNSPECIFIED",true,[63,64],{"locale":54,"value":55},{"locale":57,"value":58},{"code":66,"title":67,"tooltip":72,"tag_class":60,"is_filter":61,"filter_title":73},"cheap-fast",[68,70],{"locale":54,"value":69},"Fast and affordable",{"locale":57,"value":71},"Дешёвая быстрая",[],[74,75],{"locale":54,"value":69},{"locale":57,"value":71},{"code":77,"title":78,"tooltip":83,"tag_class":60,"is_filter":61,"filter_title":84},"long-context",[79,81],{"locale":54,"value":80},"Long context",{"locale":57,"value":82},"Длинный контекст",[],[85,86],{"locale":54,"value":80},{"locale":57,"value":82},{"code":88,"title":89,"tooltip":94,"tag_class":60,"is_filter":61,"filter_title":95},"complex-tasks",[90,92],{"locale":54,"value":91},"Complex tasks",{"locale":57,"value":93},"Сложные задачи",[],[96,97],{"locale":54,"value":91},{"locale":57,"value":93},{"code":99,"title":100,"tooltip":105,"tag_class":106,"is_filter":61,"filter_title":107},"experimental",[101,103],{"locale":54,"value":102},"Experimental",{"locale":57,"value":104},"Экспериментальная",[],"EXPERIMENTAL",[108,109],{"locale":54,"value":102},{"locale":57,"value":104},{"code":111,"title":112,"tooltip":117,"tag_class":60,"is_filter":61,"filter_title":118},"coding",[113,115],{"locale":54,"value":114},"Coding",{"locale":57,"value":116},"Кодинг",[],[119,120],{"locale":54,"value":114},{"locale":57,"value":116},{"code":122,"title":123,"tooltip":128,"tag_class":60,"is_filter":61,"filter_title":129},"price-quality",[124,126],{"locale":54,"value":125},"Value for money",{"locale":57,"value":127},"Баланс цена/качество",[],[130,131],{"locale":54,"value":125},{"locale":57,"value":132},"Цена/качество",{"code":134,"title":135,"tooltip":140,"tag_class":60,"is_filter":61,"filter_title":141},"agent-scenarios",[136,138],{"locale":54,"value":137},"Agent workflows",{"locale":57,"value":139},"Агентские сценарии",[],[142,143],{"locale":54,"value":137},{"locale":57,"value":139},{"code":145,"title":146,"tooltip":151,"tag_class":156,"is_filter":61,"filter_title":157},"beget-recommended",[147,149],{"locale":54,"value":148},"Recommended by Beget",{"locale":57,"value":150},"Рекомендовано Beget",[152,154],{"locale":54,"value":153},"Based on value for money and benchmark analysis",{"locale":57,"value":155},"По соотношению цена/качество и анализу бенчмарков","RECOMMENDED",[158,159],{"locale":54,"value":148},{"locale":57,"value":160},"Рекомендует Beget",[162,177,191,203,217,231,245,259,273,287,301,315,330,345,358,372,386,401,412,425,439,452,466,479,492,504,516,530,542,556],{"id":163,"display_name":164,"api_name":165,"type":166,"context_size":167,"input_price_per_million_tokens":168,"output_price_per_million_tokens":169,"active":61,"developer_code":38,"description":170,"tag":175},"1","GPT-5.6 Sol","gpt-5.6-sol","AI_MODEL_TYPE_CHAT",1050000,238,1190,[171,173],{"locale":54,"value":172},"OpenAI's previous-generation flagship for complex assistants, coding, and document analysis. The new model in this family is GPT-6.1 Sol.",{"locale":57,"value":174},"Предыдущее поколение флагмана OpenAI для сложных ассистентов, кода и анализа документов. Новая модель этой линейки — GPT-6.1 Sol.",[176],{"code":51,"is_visible":61},{"id":178,"display_name":179,"api_name":180,"type":166,"context_size":167,"input_price_per_million_tokens":181,"output_price_per_million_tokens":182,"active":61,"developer_code":38,"description":183,"tag":188},"2","GPT-5.6 Luna","gpt-5.6-luna",24,143,[184,186],{"locale":54,"value":185},"OpenAI's lightweight model family for classification, short responses, and batch requests. The new model in this family is GPT-6 Luna.",{"locale":57,"value":187},"Лёгкая линейка OpenAI для классификации, коротких ответов и массовых запросов. Новая модель этой линейки — GPT-6 Luna.",[189,190],{"code":66,"is_visible":61},{"code":122,"is_visible":61},{"id":192,"display_name":193,"api_name":194,"type":166,"context_size":195,"input_price_per_million_tokens":168,"output_price_per_million_tokens":169,"active":61,"developer_code":6,"description":196,"tag":201},"3","Claude Sonnet 5","claude-sonnet-5",1000000,[197,199],{"locale":54,"value":198},"Anthropic's workhorse for instructions, coding, analytics, and complex conversations. The new model in this family is Sonnet 5.5.",{"locale":57,"value":200},"Рабочая модель Anthropic для инструкций, кода, аналитики и сложных диалогов. Новая модель этой линейки — Sonnet 5.5.",[202],{"code":51,"is_visible":61},{"id":204,"display_name":205,"api_name":206,"type":166,"context_size":195,"input_price_per_million_tokens":207,"output_price_per_million_tokens":208,"active":61,"developer_code":6,"description":209,"tag":214},"4","Claude Opus 5","claude-opus-5",595,2975,[210,212],{"locale":54,"value":211},"Anthropic's model for multi-step reasoning, architectural decisions, and complex agentic workflows. The new model in this family is Opus 5.5.",{"locale":57,"value":213},"Модель Anthropic для многошаговых рассуждений, архитектурных решений и сложных агентских процессов. Новая модель этой линейки — Opus 5.5.",[215,216],{"code":88,"is_visible":61},{"code":51,"is_visible":61},{"id":218,"display_name":219,"api_name":220,"type":166,"context_size":221,"input_price_per_million_tokens":168,"output_price_per_million_tokens":222,"active":61,"developer_code":18,"description":223,"tag":228},"5","Gemini 3.1 Pro Preview","gemini-3.1-pro",1048576,1428,[224,226],{"locale":54,"value":225},"Google's Pro model: analyzing long documents, knowledge bases, and conversations with a large 1M context.",{"locale":57,"value":227},"Pro-линейка Google: анализ длинных документов, knowledge bases и диалоги с большим контекстом 1M.",[229,230],{"code":77,"is_visible":61},{"code":145,"is_visible":61},{"id":232,"display_name":233,"api_name":234,"type":166,"context_size":221,"input_price_per_million_tokens":235,"output_price_per_million_tokens":236,"active":61,"developer_code":18,"description":237,"tag":242},"6","Gemini 3.1 Flash Lite Preview","gemini-3.1-flash-lite",30,179,[238,240],{"locale":54,"value":239},"Flash Lite: low latency and cost with a 1M context — for classification and high-throughput workloads.",{"locale":57,"value":241},"Flash Lite: низкая latency и стоимость при контексте 1M — classification и массовый high-throughput.",[243,244],{"code":66,"is_visible":61},{"code":77,"is_visible":61},{"id":246,"display_name":247,"api_name":248,"type":166,"context_size":249,"input_price_per_million_tokens":250,"output_price_per_million_tokens":168,"active":61,"developer_code":10,"description":251,"tag":256},"7","DeepSeek V4 Pro","deepseek-v4-pro",600000,80,[252,254],{"locale":54,"value":253},"Strong quality at a low cost — a go-to choice for results without a premium budget.",{"locale":57,"value":255},"Сильное качество при низкой стоимости — default-выбор, когда нужен результат без премиум-бюджета.",[257,258],{"code":122,"is_visible":61},{"code":145,"is_visible":61},{"id":260,"display_name":261,"api_name":262,"type":166,"context_size":221,"input_price_per_million_tokens":263,"output_price_per_million_tokens":264,"active":61,"developer_code":10,"description":265,"tag":270},"8","DeepSeek V4 Flash","deepseek-v4-flash",27,79,[266,268],{"locale":54,"value":267},"A high-throughput model for simple responses, classification, and large request volumes.",{"locale":57,"value":269},"High-throughput модель для простых ответов, классификации и большого объёма запросов.",[271,272],{"code":66,"is_visible":61},{"code":145,"is_visible":61},{"id":274,"display_name":275,"api_name":276,"type":166,"context_size":277,"input_price_per_million_tokens":278,"output_price_per_million_tokens":279,"active":61,"developer_code":10,"description":280,"tag":285},"9","DeepSeek R1 0528","deepseek-r1",131072,84,298,[281,283],{"locale":54,"value":282},"A reasoning model for planning, multi-step analysis, and tasks that require a chain of reasoning.",{"locale":57,"value":284},"Reasoning-модель: планирование, multi-step анализ и задачи, где важна цепочка рассуждений.",[286],{"code":88,"is_visible":61},{"id":288,"display_name":289,"api_name":290,"type":166,"context_size":195,"input_price_per_million_tokens":291,"output_price_per_million_tokens":292,"active":61,"developer_code":42,"description":293,"tag":298},"10","Qwen3.7 Max","qwen-3.7-max",176,527,[294,296],{"locale":54,"value":295},"A general-purpose Max model with a 1M context and strong Russian-language support.",{"locale":57,"value":297},"Универсальная Max-модель с контекстом 1M и сильной поддержкой русского языка.",[299,300],{"code":51,"is_visible":61},{"code":77,"is_visible":61},{"id":302,"display_name":303,"api_name":304,"type":166,"context_size":305,"input_price_per_million_tokens":306,"output_price_per_million_tokens":307,"active":61,"developer_code":42,"description":308,"tag":313},"11","Qwen3 Coder Next","qwen3-coder-next",256000,22,108,[309,311],{"locale":54,"value":310},"A specialized coding model for code generation, review, explanation, and automated tests.",{"locale":57,"value":312},"Специализированная coding-модель: генерация, ревью, объяснение кода и автотесты.",[314],{"code":111,"is_visible":61},{"id":316,"display_name":317,"api_name":318,"type":166,"context_size":319,"input_price_per_million_tokens":320,"output_price_per_million_tokens":321,"active":61,"developer_code":22,"description":322,"tag":327},"12","Kimi K2.6","kimi-k2.6",262144,56,292,[323,325],{"locale":54,"value":324},"A model for agent and research workflows: multi-step reasoning, tool calling, and a 262K context.",{"locale":57,"value":326},"Модель для агентских и research-сценариев: multi-step reasoning, tool-calling, контекст 262K.",[328,329],{"code":77,"is_visible":61},{"code":134,"is_visible":61},{"id":331,"display_name":332,"api_name":333,"type":166,"context_size":334,"input_price_per_million_tokens":335,"output_price_per_million_tokens":336,"active":61,"developer_code":14,"description":337,"tag":342},"13","GLM 5.2","glm-5.2",202752,141,524,[338,340],{"locale":54,"value":339},"An open-weight model for agent pipelines and multi-step tasks. Good value for money.",{"locale":57,"value":341},"Open-weight модель для агентских пайплайнов и multi-step задач. Хороший баланс цены и качества.",[343,344],{"code":122,"is_visible":61},{"code":134,"is_visible":61},{"id":346,"display_name":347,"api_name":348,"type":166,"context_size":195,"input_price_per_million_tokens":349,"output_price_per_million_tokens":182,"active":61,"developer_code":30,"description":350,"tag":355},"14","MiniMax M3","minimax-m3",36,[351,353],{"locale":54,"value":352},"An affordable model with a 1M context for high-throughput tasks and long inputs.",{"locale":57,"value":354},"Бюджетная модель с контекстом 1M для high-throughput задач и длинных входных данных.",[356,357],{"code":66,"is_visible":61},{"code":77,"is_visible":61},{"id":359,"display_name":360,"api_name":361,"type":166,"context_size":221,"input_price_per_million_tokens":362,"output_price_per_million_tokens":363,"active":61,"developer_code":26,"description":364,"tag":369},"15","Llama 4 Maverick","llama-4-maverick",42,119,[365,367],{"locale":54,"value":366},"Meta's open-weight model — a familiar stack for experiments and general-purpose tasks.",{"locale":57,"value":368},"Open-weight модель Meta — знакомый стек для экспериментов и универсальных задач.",[370,371],{"code":51,"is_visible":61},{"code":99,"is_visible":61},{"id":373,"display_name":374,"api_name":375,"type":166,"context_size":376,"input_price_per_million_tokens":377,"output_price_per_million_tokens":279,"active":61,"developer_code":46,"description":378,"tag":383},"17","Grok 4.20","grok-4.20",2000000,149,[379,381],{"locale":54,"value":380},"A record 2M context — for research and analyzing entire logs and long conversations.",{"locale":57,"value":382},"Рекордный контекст 2M — research, анализ логов и длинных переписок целиком.",[384,385],{"code":99,"is_visible":61},{"code":77,"is_visible":61},{"id":387,"display_name":388,"api_name":388,"type":389,"context_size":390,"input_price_per_million_tokens":391,"output_price_per_million_tokens":392,"active":61,"developer_code":38,"description":393,"tag":398},"18","text-embedding-3-small","AI_MODEL_TYPE_EMBEDDING",8192,3,0,[394,396],{"locale":54,"value":395},"Compact OpenAI embeddings: semantic search, RAG, and clustering at a low cost.",{"locale":57,"value":397},"Компактные эмбеддинги OpenAI: семантический поиск, RAG и кластеризация при низкой стоимости.",[399,400],{"code":66,"is_visible":61},{"code":122,"is_visible":61},{"id":402,"display_name":403,"api_name":403,"type":389,"context_size":390,"input_price_per_million_tokens":404,"output_price_per_million_tokens":392,"active":61,"developer_code":38,"description":405,"tag":410},"19","text-embedding-3-large",16,[406,408],{"locale":54,"value":407},"Higher-dimensional OpenAI embeddings — maximum accuracy for semantic search and RAG over large text corpora.",{"locale":57,"value":409},"Эмбеддинги OpenAI повышенной размерности — максимальная точность семантического поиска и RAG на больших корпусах.",[411],{"code":51,"is_visible":61},{"id":413,"display_name":414,"api_name":415,"type":166,"context_size":195,"input_price_per_million_tokens":169,"output_price_per_million_tokens":416,"active":61,"developer_code":6,"description":417,"tag":422},"20","Claude Fable 5.1","claude-fable-5.1",5950,[418,420],{"locale":54,"value":419},"Anthropic's flagship: the highest Intelligence and Coding Index scores for long agent and reasoning workflows.",{"locale":57,"value":421},"Флагман Anthropic: максимальный Intelligence/Coding Index для длинных агентских и reasoning-сценариев.",[423,424],{"code":88,"is_visible":61},{"code":51,"is_visible":61},{"id":426,"display_name":427,"api_name":428,"type":166,"context_size":221,"input_price_per_million_tokens":429,"output_price_per_million_tokens":430,"active":61,"developer_code":18,"description":431,"tag":436},"21","Gemini 3.8 Flash","gemini-3.8-flash",90,447,[432,434],{"locale":54,"value":433},"Google's Flash model: high quality at a low price with a 1M context — fast responses without a major drop in quality.",{"locale":57,"value":435},"Flash Google: высокое качество при низкой цене, контекст 1M — быстрые ответы без сильной деградации.",[437,438],{"code":66,"is_visible":61},{"code":77,"is_visible":61},{"id":440,"display_name":441,"api_name":442,"type":166,"context_size":195,"input_price_per_million_tokens":168,"output_price_per_million_tokens":443,"active":61,"developer_code":42,"description":444,"tag":449},"22","Qwen3.8 Max","qwen3.8-max",714,[445,447],{"locale":54,"value":446},"Qwen's current Max model: general-purpose tasks, Russian-language support, and a long 1M context.",{"locale":57,"value":448},"Актуальный Max Qwen: универсальные задачи, русский язык, длинный контекст 1M.",[450,451],{"code":51,"is_visible":61},{"code":77,"is_visible":61},{"id":453,"display_name":454,"api_name":455,"type":166,"context_size":221,"input_price_per_million_tokens":456,"output_price_per_million_tokens":457,"active":61,"developer_code":22,"description":458,"tag":463},"23","Kimi K3","kimi-k3",357,1785,[459,461],{"locale":54,"value":460},"Kimi for agent pipelines and tool calling with a long 1M context.",{"locale":57,"value":462},"Kimi для агентских пайплайнов и tool-calling на длинном контексте 1M.",[464,465],{"code":134,"is_visible":61},{"code":77,"is_visible":61},{"id":467,"display_name":468,"api_name":469,"type":166,"context_size":221,"input_price_per_million_tokens":470,"output_price_per_million_tokens":336,"active":61,"developer_code":14,"description":471,"tag":476},"24","GLM 5.3","glm-5.3",167,[472,474],{"locale":54,"value":473},"GLM for agent workflows and tool calling. A 1M context and a strong Coding Index at a moderate price.",{"locale":57,"value":475},"GLM для агентских сценариев и tool-calling. Контекст 1M, сильный Coding Index при умеренной цене.",[477,478],{"code":134,"is_visible":61},{"code":122,"is_visible":61},{"id":480,"display_name":481,"api_name":482,"type":166,"context_size":483,"input_price_per_million_tokens":168,"output_price_per_million_tokens":443,"active":61,"developer_code":46,"description":484,"tag":489},"25","Grok 4.6","grok-4.6",500000,[485,487],{"locale":54,"value":486},"xAI's general-purpose model for reasoning and coding with a 500,000-token context window. The new model in this family is Grok 4.7.",{"locale":57,"value":488},"Универсальная модель xAI для рассуждений и кода с контекстом 500 тысяч токенов. Новая модель этой линейки — Grok 4.7.",[490,491],{"code":51,"is_visible":61},{"code":99,"is_visible":61},{"id":493,"display_name":494,"api_name":495,"type":166,"context_size":167,"input_price_per_million_tokens":168,"output_price_per_million_tokens":169,"active":61,"developer_code":38,"description":496,"tag":501},"26","GPT-6.1 Sol","gpt-6.1-sol",[497,499],{"locale":54,"value":498},"OpenAI's next-generation flagship for agentic coding, document analysis, and multi-step workflows.",{"locale":57,"value":500},"Флагман OpenAI нового поколения для агентного кода, анализа документов и многошаговых процессов.",[502,503],{"code":51,"is_visible":61},{"code":145,"is_visible":61},{"id":505,"display_name":506,"api_name":507,"type":166,"context_size":167,"input_price_per_million_tokens":169,"output_price_per_million_tokens":416,"active":61,"developer_code":38,"description":508,"tag":513},"27","GPT-6 Astra","gpt-6-astra",[509,511],{"locale":54,"value":510},"OpenAI's model for complex analysis, engineering, research, and long-running agentic tasks.",{"locale":57,"value":512},"Модель OpenAI для сложного анализа, инженерии и исследований с длинными агентными задачами.",[514,515],{"code":88,"is_visible":61},{"code":51,"is_visible":61},{"id":517,"display_name":518,"api_name":519,"type":166,"context_size":167,"input_price_per_million_tokens":520,"output_price_per_million_tokens":521,"active":61,"developer_code":38,"description":522,"tag":527},"28","GPT-6 Luna","gpt-6-luna",12,60,[523,525],{"locale":54,"value":524},"OpenAI's lightweight next-generation model for conversations, classification, and low-cost batch requests.",{"locale":57,"value":526},"Лёгкая модель OpenAI нового поколения для диалогов, классификации и массовых запросов с низкой стоимостью.",[528,529],{"code":66,"is_visible":61},{"code":122,"is_visible":61},{"id":531,"display_name":532,"api_name":533,"type":166,"context_size":195,"input_price_per_million_tokens":168,"output_price_per_million_tokens":169,"active":61,"developer_code":6,"description":534,"tag":539},"29","Claude Sonnet 5.5","claude-sonnet-5.5",[535,537],{"locale":54,"value":536},"Anthropic's next-generation workhorse for coding, instructions, business documents, and analytics.",{"locale":57,"value":538},"Рабочая модель Anthropic нового поколения для кода, инструкций, деловых документов и аналитики.",[540,541],{"code":51,"is_visible":61},{"code":145,"is_visible":61},{"id":543,"display_name":544,"api_name":545,"type":166,"context_size":195,"input_price_per_million_tokens":546,"output_price_per_million_tokens":547,"active":61,"developer_code":6,"description":548,"tag":553},"30","Claude Opus 5.5","claude-opus-5.5",476,2380,[549,551],{"locale":54,"value":550},"Anthropic's model for complex tasks, in-depth analysis, and long-running agentic workflows.",{"locale":57,"value":552},"Модель Anthropic для сложных задач, глубокого анализа и длинных агентных процессов.",[554,555],{"code":88,"is_visible":61},{"code":51,"is_visible":61},{"id":557,"display_name":558,"api_name":559,"type":166,"context_size":483,"input_price_per_million_tokens":168,"output_price_per_million_tokens":443,"active":61,"developer_code":46,"description":560,"tag":565},"31","Grok 4.7","grok-4.7",[561,563],{"locale":54,"value":562},"xAI's next-generation general-purpose model for reasoning and coding with a 500,000-token context window.",{"locale":57,"value":564},"Универсальная модель xAI нового поколения для рассуждений и кода с контекстом 500 тысяч токенов.",[566,567],{"code":51,"is_visible":61},{"code":99,"is_visible":61}]