{"data":[{"id":"anthropic-claude-5-opus","name":"claude-5-opus","display_name":"Claude Opus 5","description":"Anthropic's flagship Opus-tier LLM in the Claude 5 generation, supporting tool use, vision, reasoning, web search, and explicit caching for demanding agentic workflows.","creator":"anthropic","family":"claude","tier":"opus","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-05","training_data_cutoff":"2026-05","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-07-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-5-opus","anthropic.claude-opus-5","anthropic/claude-opus-5","anthropic/claude-opus-5:batch","au.anthropic.claude-opus-5","azure_ai/claude-opus-5","claude-opus-5","claude-opus-5-high","claude-opus-5-low","claude-opus-5-medium","claude-opus-5-xhigh","eu.anthropic.claude-opus-5","global.anthropic.claude-opus-5","jp.anthropic.claude-opus-5","publishers/google/models/claude-opus-5","us.anthropic.claude-opus-5","vertex_ai/claude-opus-5","vertex_ai/claude-opus-5@default"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-5-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.5,"max_input_per_1m":6,"min_output_per_1m":12.5,"max_output_per_1m":30,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":3.125,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-5-fable","name":"claude-5-fable","display_name":"Claude Fable 5","description":"A highly capable Claude LLM optimized for demanding reasoning and long-horizon agentic tasks, with vision, tool-use, and explicit-caching support.","creator":"anthropic","family":"claude","tier":"fable","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-09","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-5-fable","anthropic.claude-fable-5","anthropic/claude-fable-5","anthropic/claude-fable-5:batch","au.anthropic.claude-fable-5","azure_ai/claude-fable-5","claude-fable-5","claude-fable-5-opus-5-fallback","eu.anthropic.claude-fable-5","global.anthropic.claude-fable-5","publishers/anthropic/models/claude-fable-5","publishers/google/models/claude-fable-5","us.anthropic.claude-fable-5","vertex_ai/claude-fable-5","vertex_ai/claude-fable-5@default"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-5-fable","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":5,"max_input_per_1m":12,"min_output_per_1m":25,"max_output_per_1m":60,"min_cache_read_per_1m":0.5,"min_cache_write_per_1m":6.25,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-6-sol","name":"gpt-5-6-sol","display_name":"GPT-5.6 Sol","description":"The flagship model in the GPT-5.6 family, representing the unsuffixed frontier tier with vision, tool use, and web-search capabilities.","creator":"openai","family":"gpt","tier":"","version":"5-6","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-02","training_data_cutoff":null,"supported_reasoning_efforts":["default","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-09","earliest_deprecation_date":"2028-01-11","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-5.6-sol","azure/gpt-5.6-sol","azure/us/gpt-5.6-sol","bedrock_mantle/openai.gpt-5.6-sol","gpt-5-6-sol","gpt-5-6-sol-high","gpt-5-6-sol-low","gpt-5-6-sol-medium","gpt-5-6-sol-non-reasoning","gpt-5-6-sol-xhigh","gpt-5.6-sol","openai-gpt-5-6-sol","openai/gpt-5.6-sol","openai/gpt-5.6-sol:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-6-sol","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.5,"max_input_per_1m":6,"min_output_per_1m":15,"max_output_per_1m":36,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":6.25,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"xai-grok-4-6","name":"grok-4-6","display_name":"Grok 4.6","description":"A frontier LLM from xAI with strong performance across coding, STEM, and knowledge-intensive tasks, featuring reasoning and tool-use capabilities.","creator":"xai","family":"grok","tier":"","version":"4-6","type":"language","size_in_bn":null,"modalities":{"input":["image","text"],"output":["text"]},"context_window":500000,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Grok","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["grok-4-6","grok-4.6","x-ai/grok-4.6","xai-grok-4-6","xai/grok-4.6"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"xai-grok-4-6","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2,"min_output_per_1m":6,"max_output_per_1m":6,"min_cache_read_per_1m":0.5,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway","xai"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k3","name":"kimi-k3","display_name":"Kimi K3","description":"A flagship reasoning-capable multimodal LLM with 2.8 trillion parameters, built on Kimi Delta Attention (a hybrid linear attention mechanism) with native visual understanding and tool-use support.","creator":"moonshot","family":"kimi","tier":"","version":"k3","type":"language","size_in_bn":2779.932,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/kimi-k3","kimi-k3","kimi-k3-low","moonshot-kimi-k3","moonshotai/kimi-k3","moonshotai/Kimi-K3"],"hf_likes":7099,"hf_downloads":2850,"hf_downloads_all_time":2855,"hf_trending_score":6642,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"moonshot-kimi-k3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":3,"max_input_per_1m":3,"min_output_per_1m":15,"max_output_per_1m":15,"min_cache_read_per_1m":0.3,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","openrouter","vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-8-max","name":"qwen3-8-max","display_name":"Qwen3.8 Max","description":"A massive 2.4T-parameter MoE flagship LLM optimized for coding, knowledge work, and autonomous multi-day programming tasks with native visual understanding.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen3p8-max","alibaba-qwen3-8-max","alibaba/qwen3.8-max","dashscope/qwen3.8-max","qwen/qwen3.8-max","Qwen/Qwen3.8-Max","qwen3-8-max"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-8-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2,"min_output_per_1m":6,"max_output_per_1m":6,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":2.5,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen","openrouter","vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-8-2-4t-a95b","name":"qwen3-8-2-4t-a95b","display_name":"Qwen3.8 2.4T A95B","description":"A sparse mixture-of-experts LLM with 95 billion active parameters out of 2.4 trillion total, serving as the open-weight counterpart to Qwen3.8 Max.","creator":"alibaba","family":"qwen","tier":"","version":"8-2","type":"language","size_in_bn":2446.183,"modalities":{"input":["text"],"output":["text"]},"context_window":1010000,"max_output_tokens":262144,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen3p8-2p4t-a95b","alibaba-qwen3-8-2-4t-a95b","alibaba/qwen3.8-2.4t-a95b","qwen/qwen3.8-2.4t-a95b","Qwen/Qwen3.8-2.4T-A95B","qwen3-8-2-4t-a95b"],"hf_likes":625,"hf_downloads":978,"hf_downloads_all_time":978,"hf_trending_score":616,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-8-2-4t-a95b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2.5,"min_output_per_1m":6,"max_output_per_1m":6.25,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-8-opus","name":"claude-4-8-opus","display_name":"Claude Opus 4.8","description":"A flagship Anthropic LLM in the Claude Opus tier at version 4.8, supporting adaptive reasoning, vision, tool use, file input, and web search across multiple geographic regions.","creator":"anthropic","family":"claude","tier":"opus","version":"4-8","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-05-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-4-8-opus","anthropic.claude-opus-4-8","anthropic/claude-opus-4-8","anthropic/claude-opus-4.8","anthropic/claude-opus-4.8:batch","au.anthropic.claude-opus-4-8","azure_ai/claude-opus-4-8","claude-opus-4-8","eu.anthropic.claude-opus-4-8","global.anthropic.claude-opus-4-8","jp.anthropic.claude-opus-4-8","publishers/anthropic/models/claude-opus-4-8","publishers/google/models/claude-opus-4-8","us.anthropic.claude-opus-4-8","vertex_ai/claude-opus-4-8","vertex_ai/claude-opus-4-8@default"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-4-8-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.5,"max_input_per_1m":6,"min_output_per_1m":12.5,"max_output_per_1m":30,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":3.125,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-muse-spark-1-2","name":"muse-spark-1-2","display_name":"Muse Spark 1.2","description":"A multimodal reasoning LLM from Meta designed for complex agentic tasks, accepting text, images, video, audio, and PDFs with a 1M-token context window.","creator":"meta","family":"muse","tier":"","version":"1-2","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["meta-muse-spark-1-2","meta/muse-spark-1.2","muse-spark-1-2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-muse-spark-1-2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.25,"max_input_per_1m":1.25,"min_output_per_1m":4.25,"max_output_per_1m":4.25,"min_cache_read_per_1m":0.15,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-6-terra","name":"gpt-5-6-terra","display_name":"GPT-5.6 Terra","description":"A balanced intelligence-and-cost LLM in the GPT-5.6 family, corresponding to the mini tier of earlier GPT-5 families.","creator":"openai","family":"gpt","tier":"","version":"5-6","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-02","training_data_cutoff":null,"supported_reasoning_efforts":["default","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-09","earliest_deprecation_date":"2028-01-11","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-5.6-terra","azure/gpt-5.6-terra","azure/us/gpt-5.6-terra","bedrock_mantle/openai.gpt-5.6-terra","gpt-5-6-terra","gpt-5-6-terra-high","gpt-5-6-terra-low","gpt-5-6-terra-medium","gpt-5-6-terra-non-reasoning","gpt-5-6-terra-xhigh","gpt-5.6-terra","openai-gpt-5-6-terra","openai/gpt-5.6-terra","openai/gpt-5.6-terra:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-6-terra","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":3,"min_output_per_1m":6,"max_output_per_1m":18,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":1.25,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-5","name":"gpt-5-5","display_name":"GPT-5.5","description":"A GPT-5 series large language model from OpenAI targeting high-capability reasoning and generation tasks at the xhigh performance tier.","creator":"openai","family":"gpt","tier":"","version":"5-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-12","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure_ai/gpt-5.5","azure_ai/gpt-5.5-2026-04-23","azure/eu/gpt-5.5","azure/eu/gpt-5.5-2026-04-23","azure/gpt-5.5","azure/gpt-5.5-2026-04-23","azure/us/gpt-5.5","azure/us/gpt-5.5-2026-04-23","bedrock_mantle/openai.gpt-5.5","gpt-5-5","gpt-5-5-high","gpt-5-5-instant-05-26","gpt-5-5-instant-06-26","gpt-5-5-low","gpt-5-5-medium","gpt-5-5-non-reasoning","gpt-5.5","gpt-5.5-2026-04-23","openai-gpt-5-5","openai/gpt-5.5","openai/gpt-5.5:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.5,"max_input_per_1m":6,"min_output_per_1m":15,"max_output_per_1m":36,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-3-7-flash","name":"gemini-3-7-flash","display_name":"Gemini 3.7 Flash","description":"A fast, efficient Gemini model at the 3.7 generation with multimodal capabilities including vision, tool use, and web search.","creator":"google","family":"gemini","tier":"flash","version":"3-7","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-13","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["gemini-3-7-flash","gemini-3-7-flash-low","gemini-3-7-flash-medium","gemini-3.7-flash","gemini/gemini-3.7-flash","google-gemini-3-7-flash","google/gemini-3.7-flash","google/gemini-3.7-flash:batch","publishers/google/models/gemini-3.7-flash","vertex_ai/gemini-3.7-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemini-3-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.1875,"max_input_per_1m":0.75,"min_output_per_1m":0.9375,"max_output_per_1m":3.75,"min_cache_read_per_1m":0.01875,"min_cache_write_per_1m":0.0208333333,"min_reasoning_per_1m":0.9375,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"xai-grok-4-5","name":"grok-4-5","display_name":"Grok 4.5","description":"A frontier multimodal LLM from xAI with strong performance across coding, STEM, and knowledge work, supporting tool use, web search, vision, and implicit caching.","creator":"xai","family":"grok","tier":"","version":"4-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":500000,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Grok","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-08","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["grok-4-5","grok-4.5","x-ai/grok-4.5","xai-grok-4-5","xai/grok-4.5","xai/grok-4.5-latest"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"xai-grok-4-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2,"min_output_per_1m":6,"max_output_per_1m":6,"min_cache_read_per_1m":0.3,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway","xai"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-5-sonnet","name":"claude-5-sonnet","display_name":"Claude Sonnet 5","description":"A flagship-tier LLM from Anthropic featuring adaptive reasoning, vision, tool use, and web search capabilities for complex, multi-step tasks.","creator":"anthropic","family":"claude","tier":"sonnet","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-06-30","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-5-sonnet","anthropic.claude-sonnet-5","anthropic/claude-sonnet-5","anthropic/claude-sonnet-5:batch","au.anthropic.claude-sonnet-5","azure_ai/claude-sonnet-5","claude-sonnet-5","claude-sonnet-5-high","claude-sonnet-5-low","claude-sonnet-5-medium","claude-sonnet-5-non-reasoning","claude-sonnet-5-xhigh","eu.anthropic.claude-sonnet-5","global.anthropic.claude-sonnet-5","jp.anthropic.claude-sonnet-5","publishers/google/models/claude-sonnet-5","us.anthropic.claude-sonnet-5","vertex_ai/claude-sonnet-5","vertex_ai/claude-sonnet-5@default"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-5-sonnet","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":2.4,"min_output_per_1m":5,"max_output_per_1m":12,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":1.25,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-7-opus","name":"claude-4-7-opus","display_name":"Claude Opus 4.7","description":"Anthropic's Claude 4.7 Opus model with adaptive reasoning at maximum effort, vision, and tool-use for complex enterprise tasks.","creator":"anthropic","family":"claude","tier":"opus","version":"4-7","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":346,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","minimal","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-04-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-4-7-opus","anthropic.claude-opus-4-7","anthropic/claude-opus-4-7","anthropic/claude-opus-4.7","anthropic/claude-opus-4.7:batch","au.anthropic.claude-opus-4-7","azure_ai/claude-opus-4-7","claude-opus-4-7","claude-opus-4-7-20260416","claude-opus-4-7-non-reasoning","eu.anthropic.claude-opus-4-7","global.anthropic.claude-opus-4-7","jp.anthropic.claude-opus-4-7","openrouter/anthropic/claude-opus-4.7","perplexity/anthropic/claude-opus-4-7","publishers/anthropic/models/claude-opus-4-7","publishers/google/models/claude-opus-4-7","us.anthropic.claude-opus-4-7","vertex_ai/claude-opus-4-7","vertex_ai/claude-opus-4-7@default"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-4-7-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.5,"max_input_per_1m":6,"min_output_per_1m":12.5,"max_output_per_1m":30,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":3.125,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v4-pro","name":"deepseek-v4-pro","display_name":"DeepSeek V4 Pro","description":"A large-scale Mixture-of-Experts LLM from DeepSeek with 1.6T total and 49B activated parameters, supporting a 1M-token context window for advanced reasoning and tool-use tasks.","creator":"deepseek","family":"v4","tier":"pro","version":null,"type":"language","size_in_bn":861.608,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1048600,"max_output_tokens":393216,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/deepseek-v4-pro","azure_ai/deepseek-v4-pro","dashscope/deepseek-v4-pro","deepseek-ai/DeepSeek-V4-Pro","deepseek-v4-pro","deepseek-v4-pro-high","deepseek-v4-pro-non-reasoning","deepseek/deepseek-v4-pro","fireworks_ai/accounts/fireworks/models/deepseek-v4-pro","fireworks_ai/deepseek-v4-pro","tencent/deepseek-v4-pro"],"hf_likes":2540,"hf_downloads":78864,"hf_downloads_all_time":78864,"hf_trending_score":2449,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-v4-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.435,"max_input_per_1m":2.4,"min_output_per_1m":0.87,"max_output_per_1m":4.8,"min_cache_read_per_1m":0.003625,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepseek","other/tencent"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-muse-spark-1-1","name":"muse-spark-1-1","display_name":"Muse Spark 1.1","description":"A powerful agentic LLM optimized for tool use, computer use, and long-running multi-agent tasks with a 1M token context window.","creator":"meta","family":"muse","tier":"","version":"1-1","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal","xhigh"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["meta-muse-spark-1-1","meta/muse-spark-1.1","muse-spark-1-1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-muse-spark-1-1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.25,"max_input_per_1m":1.25,"min_output_per_1m":4.25,"max_output_per_1m":4.25,"min_cache_read_per_1m":0.15,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","other/meta","vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-4","name":"gpt-5-4","display_name":"GPT-5.4","description":"OpenAI's frontier reasoning model for complex professional work, supporting vision, file input, tool use, and configurable reasoning effort from none to xhigh.","creator":"openai","family":"gpt","tier":"","version":"5-4","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-08","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-05","earliest_deprecation_date":"2027-09-02","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure_ai/gpt-5.4","azure_ai/gpt-5.4-2026-03-05","azure/eu/gpt-5.4","azure/eu/gpt-5.4-2026-03-05","azure/gpt-5.4","azure/gpt-5.4-2026-03-05","azure/us/gpt-5.4","azure/us/gpt-5.4-2026-03-05","bedrock_mantle/openai.gpt-5.4","chatgpt/gpt-5.4","gpt-5-4","gpt-5-4-low","gpt-5-4-non-reasoning","gpt-5.4","gpt-5.4-2026-03-05","openai-gpt-5-4","openai/gpt-5.4","openai/gpt-5.4:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-4","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.25,"max_input_per_1m":3,"min_output_per_1m":7.5,"max_output_per_1m":18,"min_cache_read_per_1m":0.125,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-2","name":"glm-5-2","display_name":"GLM-5.2","description":"Z.AI's flagship long-horizon autonomous LLM capable of sustained multi-hour task execution with agentic reasoning.","creator":"zhipu","family":"glm","tier":"","version":"5-2","type":"language","size_in_bn":753.33,"modalities":{"input":["text"],"output":["text"]},"context_window":1048576,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/glm-5p2","accounts/fireworks/models/glm-5p2-fp8","cloudflare/@cf/zai-org/glm-5.2","dashscope/glm-5.2","fireworks_ai/accounts/fireworks/models/glm-5p2","fireworks_ai/glm-5p2","glm-5-2","glm-5-2-non-reasoning","glm-5.2","huggingface-llm-glm-5-2-fp8","z-ai/glm-5.2","z-ai/glm-5.2:batch","zai-glm-5-2","zai-org/glm-5.2","zai-org/GLM-5.2","zai/glm-5.2","zhipu-glm-5-2"],"hf_likes":692,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":675,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-5-2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.63,"max_input_per_1m":2.052,"min_output_per_1m":1.98,"max_output_per_1m":6.27,"min_cache_read_per_1m":0.0945,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-6-luna","name":"gpt-5-6-luna","display_name":"GPT-5.6 Luna","description":"A cost-optimized LLM in the GPT-5.6 family targeting high-volume workloads, corresponding to the nano tier of earlier GPT-5 families.","creator":"openai","family":"gpt","tier":"","version":"5-6","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-02","training_data_cutoff":null,"supported_reasoning_efforts":["default","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-09","earliest_deprecation_date":"2028-01-11","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-5.6-luna","azure/gpt-5.6-luna","azure/us/gpt-5.6-luna","bedrock_mantle/openai.gpt-5.6-luna","gpt-5-6-luna","gpt-5-6-luna-high","gpt-5-6-luna-low","gpt-5-6-luna-medium","gpt-5-6-luna-non-reasoning","gpt-5-6-luna-xhigh","gpt-5.6-luna","openai-gpt-5-6-luna","openai/gpt-5.6-luna","openai/gpt-5.6-luna:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-6-luna","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":1.2,"min_output_per_1m":0.6,"max_output_per_1m":7.2,"min_cache_read_per_1m":0.01,"min_cache_write_per_1m":0.125,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-3-5-flash","name":"gemini-3-5-flash","display_name":"Gemini 3.5 Flash","description":"A fast, efficient Gemini 3.5 model optimized for high-throughput tasks with support for reasoning, vision, tool use, and web search.","creator":"google","family":"gemini","tier":"flash","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-01-01","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["gemini-3-5-flash","gemini-3-5-flash-medium","gemini-3-5-flash-minimal","gemini-3.5-flash","gemini/gemini-3.5-flash","google-gemini-3-5-flash","google/gemini-3.5-flash","google/gemini-3.5-flash:batch","publishers/google/models/gemini-3.5-flash","vertex_ai/gemini-3.5-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemini-3-5-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.75,"max_input_per_1m":1.8,"min_output_per_1m":4.5,"max_output_per_1m":10.8,"min_cache_read_per_1m":0.075,"min_cache_write_per_1m":0.0833333333,"min_reasoning_per_1m":4.5,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v4-flash","name":"deepseek-v4-flash","display_name":"DeepSeek V4 Flash","description":"An efficiency-optimized Mixture-of-Experts LLM from DeepSeek with 284B total and 13B activated parameters, supporting a 1M-token context window with reasoning and tool-use capabilities.","creator":"deepseek","family":"v4","tier":"flash","version":null,"type":"language","size_in_bn":158.069,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":393216,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["~deepseek/deepseek-v4-flash-latest","accounts/fireworks/models/deepseek-v4-flash","azure_ai/deepseek-v4-flash","dashscope/deepseek-v4-flash","deepseek-ai/DeepSeek-V4-Flash","deepseek-v4-flash","deepseek-v4-flash-high","deepseek-v4-flash-non-reasoning","deepseek-v4-flash(1)","deepseek-v4-flash*","deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash:free","fireworks_ai/accounts/fireworks/models/deepseek-v4-flash","fireworks_ai/deepseek-v4-flash","libertai/deepseek-v4-flash","pinstripes/ps/deepseek-v4-flash","tencent/deepseek-v4-flash","tensormesh/deepseek-ai/DeepSeek-V4-Flash"],"hf_likes":649,"hf_downloads":25391,"hf_downloads_all_time":25391,"hf_trending_score":639,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-v4-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.079996,"max_input_per_1m":0.25,"min_output_per_1m":0.2,"max_output_per_1m":1.75,"min_cache_read_per_1m":0.0028,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-3-6-flash","name":"gemini-3-6-flash","display_name":"Gemini 3.6 Flash","description":"A fast, multimodal Gemini LLM supporting reasoning, vision, tool-use, and web-search, optimized for high-throughput production workloads.","creator":"google","family":"gemini","tier":"flash","version":"3-6","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-21","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["gemini-3-6-flash","gemini-3.6-flash","gemini/gemini-3.6-flash","google-gemini-3-6-flash","google/gemini-3.6-flash","google/gemini-3.6-flash:batch","publishers/google/models/gemini-3.6-flash","vertex_ai/gemini-3.6-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemini-3-6-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.375,"max_input_per_1m":1.5,"min_output_per_1m":1.875,"max_output_per_1m":7.5,"min_cache_read_per_1m":0.0375,"min_cache_write_per_1m":0.0416666667,"min_reasoning_per_1m":1.875,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-3-1-pro-preview","name":"gemini-3-1-pro-preview","display_name":"Gemini 3.1 Pro Preview","description":"A preview release of Gemini 3.1 Pro providing early access to its frontier reasoning, vision, and tool-use capabilities.","creator":"google","family":"gemini","tier":"pro","version":"3-1","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-01","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-02-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["gemini-3-1-pro-preview","gemini-3.1-pro-preview","gemini/gemini-3.1-pro-preview","google-gemini-3-1-pro-preview","google/gemini-3.1-pro-preview","google/gemini-3.1-pro-preview:batch","openrouter/google/gemini-3.1-pro-preview","publishers/google/models/gemini-3.1-pro-preview","vertex_ai/gemini-3.1-pro-preview"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemini-3-1-pro-preview","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":2,"min_output_per_1m":6,"max_output_per_1m":12,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":0.375,"min_reasoning_per_1m":6,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-7-max","name":"qwen3-7-max","display_name":"Qwen3.7 Max","description":"A Mixture-of-Experts Qwen3 variant tuned for maximum capability, combining reasoning, vision, and multilingual performance in a high-throughput configuration.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-21","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen3p7-max","alibaba-qwen3-7-max","alibaba/qwen3.7-max","dashscope/qwen3.7-max","qwen/qwen3.7-max","Qwen/Qwen3.7-Max","qwen3-7-max","qwen3.7-max","qwen3.7-max-2026-05-17","qwen3.7-max-2026-05-20","qwen3.7-max-2026-06-08","qwen3.7-max-us"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-7-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.475,"max_input_per_1m":2.5,"min_output_per_1m":4.425,"max_output_per_1m":7.5,"min_cache_read_per_1m":0.295,"min_cache_write_per_1m":1.84375,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-3-codex","name":"gpt-5-3-codex","display_name":"GPT-5.3 Codex","description":"A GPT-5.3 variant optimized for agentic coding tasks in Codex environments, supporting multiple reasoning effort levels from low to xhigh.","creator":"openai","family":"gpt","tier":"","version":"5-3","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":400000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-08","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-02-24","earliest_deprecation_date":"2027-08-24","deprecated":false,"has_pricing":true,"provider_count":4,"ids":["azure/gpt-5.3-codex","chatgpt/gpt-5.3-codex","github_copilot/gpt-5.3-codex","gpt-5-3-codex","gpt-5.3-codex","openai-gpt-5-3-codex","openai/gpt-5.3-codex"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-3-codex","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.75,"max_input_per_1m":1.75,"min_output_per_1m":14,"max_output_per_1m":14,"min_cache_read_per_1m":0.175,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","openai","openrouter","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m3","name":"minimax-m3","display_name":"MiniMax M3","description":"A multimodal foundation model supporting text, image, and video inputs with a 1M-token context window, designed for long-horizon agentic tasks, coding, and reasoning.","creator":"minimax","family":"m3","tier":"","version":null,"type":"language","size_in_bn":427.04,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":512000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-31","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/minimax-m3","fireworks_ai/accounts/fireworks/models/minimax-m3","fireworks_ai/minimax-m3","minimax-m3","minimax/minimax-m3","minimax/MiniMax-M3","minimax/minimax-m3:batch","MiniMaxAI/MiniMax-M3"],"hf_likes":320,"hf_downloads":442,"hf_downloads_all_time":442,"hf_trending_score":314,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"minimax-m3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.3,"min_output_per_1m":0.6,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k2-6","name":"kimi-k2-6","display_name":"Kimi K2.6","description":"An open-source native multimodal agentic LLM specializing in long-horizon coding, coding-driven design, autonomous execution, and swarm-based task orchestration.","creator":"moonshot","family":"kimi_k25","tier":"","version":"k2-6","type":"language","size_in_bn":1058.589,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-20","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/kimi-k2p6","azure_ai/kimi-k2.6","cloudflare/@cf/moonshotai/kimi-k2.6","fireworks_ai/accounts/fireworks/models/kimi-k2p6","fireworks_ai/kimi-k2p6","kimi-k2-6","kimi-k2-6-non-reasoning","kimi-k2.6","moonshot-kimi-k2-6","moonshot/kimi-k2.6","moonshotai/kimi-k2.6","moonshotai/Kimi-K2.6","moonshotai/kimi-k2.6:free","tensormesh/moonshotai/Kimi-K2.6"],"hf_likes":568,"hf_downloads":8241,"hf_downloads_all_time":8241,"hf_trending_score":560,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"moonshot-kimi-k2-6","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.8,"max_input_per_1m":1.2,"min_output_per_1m":3.4,"max_output_per_1m":4.5,"min_cache_read_per_1m":0.16,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-2","name":"gpt-5-2","display_name":"GPT-5.2","description":"A frontier GPT-5 generation LLM for complex professional work with configurable reasoning effort, available via the Responses API.","creator":"openai","family":"gpt","tier":"","version":"5-2","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":409600,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-08","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-11","earliest_deprecation_date":"2027-06-08","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/gpt-5.2","azure/gpt-5.2-2025-12-11","chatgpt/gpt-5.2","github_copilot/gpt-5.2","gmi/openai/gpt-5.2","gpt-5-2","gpt-5-2-medium","gpt-5-2-non-reasoning","gpt-5.2","gpt-5.2-2025-12-11","openai-gpt-5-2","openai/gpt-5.2","openai/gpt-5.2:batch","openrouter/openai/gpt-5.2","perplexity/openai/gpt-5.2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.875,"max_input_per_1m":2.1,"min_output_per_1m":7,"max_output_per_1m":16.8,"min_cache_read_per_1m":0.0875,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k2-code","name":"kimi-k2-code","display_name":"Kimi K2.7 Code","description":"A coding-focused agentic LLM built on Kimi K2.6, optimized for long-horizon real-world coding tasks and end-to-end task completion with tool-use and vision support.","creator":"moonshot","family":"kimi_k25","tier":"","version":"k2","type":"language","size_in_bn":1058.589,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/kimi-k2p7-code","cloudflare/@cf/moonshotai/kimi-k2.7-code","dashscope/kimi-k2.7-code","fireworks_ai/accounts/fireworks/models/kimi-k2p7-code","fireworks_ai/kimi-k2p7-code","kimi-k2-7-code","kimi-k2.7-code","moonshot-kimi-k2-code","moonshotai/kimi-k2.7-code","moonshotai/Kimi-K2.7-Code"],"hf_likes":390,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":383,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"moonshot-kimi-k2-code","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.67,"max_input_per_1m":0.95,"min_output_per_1m":3.4,"max_output_per_1m":4,"min_cache_read_per_1m":0.15,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"xiaomi-mimo-2-5-pro","name":"mimo-2-5-pro","display_name":"MiMo V2.5 Pro","description":"Xiaomi's flagship omnimodal LLM excelling in general agentic tasks, complex software engineering, and long-horizon reasoning benchmarks.","creator":"xiaomi","family":"mimo","tier":"","version":"2-5","type":"language","size_in_bn":1023.245,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-22","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["mimo-v2-5-pro","mimo-v2-5-pro-non-reasoning","openrouter/xiaomi/mimo-v2.5-pro","xiaomi-mimo-2-5-pro","xiaomi/mimo-v2.5-pro","xiaomimimo/mimo-v2.5-pro","XiaomiMiMo/MiMo-V2.5-Pro"],"hf_likes":653,"hf_downloads":66027,"hf_downloads_all_time":128095,"hf_trending_score":34,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"xiaomi-mimo-2-5-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.435,"max_input_per_1m":0.435,"min_output_per_1m":0.87,"max_output_per_1m":0.87,"min_cache_read_per_1m":0.0036,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"thinkingmachines-inkling","name":"inkling","display_name":"Inkling","description":"A 975B Mixture-of-Experts multimodal LLM with 41B active parameters from Thinking Machines Lab, supporting audio, vision, reasoning, and tool use as the first open-weights release from the creator.","creator":"thinkingmachines","family":"inkling_mm_model","tier":"","version":null,"type":"language","size_in_bn":952.378,"modalities":{"input":["audio","image","pdf","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":262144,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-07-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/inkling","inkling","thinkingmachines-inkling","thinkingmachines/inkling","thinkingmachines/Inkling","thinkingmachines/inkling:batch"],"hf_likes":858,"hf_downloads":4,"hf_downloads_all_time":4,"hf_trending_score":844,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"thinkingmachines-inkling","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":1,"min_output_per_1m":2.025,"max_output_per_1m":4.05,"min_cache_read_per_1m":0.085,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"tencent-hy-3","name":"hy-3","display_name":"Hy 3","description":"A preview-stage Hunyuan-series LLM from Tencent, identified by the compact 'Hy3' designation and targeting general-purpose text generation.","creator":"tencent","family":"hy","tier":"","version":"3","type":"language","size_in_bn":298.786,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["hy3","tencent-hy-3","tencent/hy3","tencent/Hy3"],"hf_likes":860,"hf_downloads":14143,"hf_downloads_all_time":14143,"hf_trending_score":49,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"tencent-hy-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.132,"max_input_per_1m":0.14,"min_output_per_1m":0.528,"max_output_per_1m":0.58,"min_cache_read_per_1m":0.033,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"nex-agi-n2-pro","name":"n2-pro","display_name":"Nex-N2-Pro","description":"An open-source agentic reasoning MoE LLM post-trained on Qwen3.5-397B-A17B, featuring an Agentic Thinking framework that unifies reasoning, tool use, and environment execution for complex multi-step tasks.","creator":"nex-agi","family":"n2","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":256000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-08","earliest_deprecation_date":"2026-06-22","deprecated":false,"has_pricing":true,"provider_count":1,"ids":["nex-agi-n2-pro","nex-agi/nex-n2-pro","nex-agi/nex-n2-pro:free","nex-n2-pro"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"nex-agi-n2-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.25,"max_input_per_1m":0.25,"min_output_per_1m":1,"max_output_per_1m":1,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"upstage-solar-4-pro","name":"solar-4-pro","display_name":"Solar Pro 4","description":"A large language model from Upstage suited for agentic workflows, office productivity, document-intensive work, and coding.","creator":"upstage","family":"solar","tier":"pro","version":"4","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":524288,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-10","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["solar-pro4","upstage-solar-4-pro","upstage/solar-pro4"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"upstage-solar-4-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.03,"min_output_per_1m":0.12,"max_output_per_1m":0.12,"min_cache_read_per_1m":0.006,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"thinkingmachines-inkling-small","name":"inkling-small","display_name":"Inkling Small","description":"A lightweight 12B-parameter reasoning LLM with vision and tool-use capabilities, offering lower cost and latency than the full Inkling model.","creator":"thinkingmachines","family":"inkling","tier":"","version":null,"type":"language","size_in_bn":265.956,"modalities":{"input":["audio","image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":262144,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-30","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/inkling-small","inkling-small","thinkingmachines-inkling-small","thinkingmachines/inkling-small","thinkingmachines/Inkling-Small"],"hf_likes":201,"hf_downloads":2971,"hf_downloads_all_time":2971,"hf_trending_score":201,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"thinkingmachines-inkling-small","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.45,"max_input_per_1m":0.5,"min_output_per_1m":1.2,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-6-max-preview","name":"qwen3-6-max-preview","display_name":"Qwen3.6 Max Preview","description":"A large-scale reasoning and vision-capable LLM with enhanced vibe coding abilities, more efficient coding agent execution, and improved front-end development performance.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":262144,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-27","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["alibaba-qwen3-6-max-preview","alibaba/qwen-3.6-max-preview","qwen/qwen3.6-max-preview","qwen3-6-max","qwen3.6-max-preview"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-6-max-preview","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.027,"max_input_per_1m":1.3,"min_output_per_1m":6.162,"max_output_per_1m":7.8,"min_cache_read_per_1m":0.26,"min_cache_write_per_1m":1.28375,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-1","name":"glm-5-1","display_name":"GLM-5.1","description":"Z AI's next-generation flagship agentic LLM with significantly stronger coding capabilities, vision support, and file input, achieving top performance on SWE-Bench.","creator":"zhipu","family":"glm_moe_dsa","tier":"","version":"5-1","type":"language","size_in_bn":753.864,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":204800,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-07","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/glm-5p1","dashscope/glm-5.1","fireworks_ai/accounts/fireworks/models/glm-5p1","fireworks_ai/glm-5p1","glm-5-1","glm-5-1-non-reasoning","glm-5.1","huggingface-llm-glm-5-1-fp8","openrouter/z-ai/glm-5.1","z-ai/glm-5.1","zai-org/glm-5.1","zai-org/GLM-5.1","zai/glm-5.1","zhipu-glm-5-1"],"hf_likes":1449,"hf_downloads":147738,"hf_downloads_all_time":147738,"hf_trending_score":214,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-5-1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.4,"max_input_per_1m":1.4,"min_output_per_1m":4.4,"max_output_per_1m":4.4,"min_cache_read_per_1m":0.26,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen","fireworks_ai","openrouter","vercel_ai_gateway","z_ai"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-4-mini","name":"gpt-5-4-mini","display_name":"GPT-5.4 Mini","description":"A faster, cost-efficient variant of GPT-5.4 designed for high-volume workloads while retaining strong reasoning, vision, and tool-use capabilities.","creator":"openai","family":"gpt","tier":"mini","version":"5-4","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":400000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-08","training_data_cutoff":null,"supported_reasoning_efforts":["default","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-17","earliest_deprecation_date":"2027-09-21","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["azure_ai/gpt-5.4-mini","azure_ai/gpt-5.4-mini-2026-03-17","azure/gpt-5.4-mini","azure/gpt-5.4-mini-2026-03-17","gpt-5-4-mini","gpt-5-4-mini-medium","gpt-5-4-mini-non-reasoning","gpt-5.4-mini","gpt-5.4-mini-2026-03-17","openai-gpt-5-4-mini","openai/gpt-5.4-mini","openai/gpt-5.4-mini:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-4-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.375,"max_input_per_1m":0.9,"min_output_per_1m":2.25,"max_output_per_1m":5.4,"min_cache_read_per_1m":0.0375,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5","name":"glm-5","display_name":"GLM-5","description":"An open-source MoE LLM from Z AI designed for long-context reasoning, multi-step tool orchestration, and complex agentic engineering tasks.","creator":"zhipu","family":"glm_moe_dsa","tier":"","version":"5","type":"language","size_in_bn":753.864,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":204800,"max_output_tokens":131100,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-02-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/glm-5","baseten/zai-org/GLM-5","bedrock/us-east-1/zai.glm-5","bedrock/us-west-2/zai.glm-5","glm-5","glm-5-maas","glm-5-non-reasoning","openrouter/z-ai/glm-5","publishers/google/models/glm-5-maas","vertex_ai/zai-org/glm-5-maas","z-ai/glm-5","zai-org/glm-5","zai-org/GLM-5","zai.glm-5","zai/glm-5","zhipu-glm-5"],"hf_likes":2070,"hf_downloads":477667,"hf_downloads_all_time":777726,"hf_trending_score":5,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.573,"max_input_per_1m":1,"min_output_per_1m":2.55,"max_output_per_1m":3.2,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":0.1,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-6-plus","name":"qwen3-6-plus","display_name":"Qwen3.6 Plus","description":"A Plus-tier Qwen3.6 closed model with reasoning, tool use, and vision capabilities, available exclusively through select infrastructure partners.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1000000,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen3p6-plus","alibaba-qwen3-6-plus","alibaba/qwen3.6-plus","openrouter/qwen/qwen3.6-plus","qwen/qwen3.6-plus","qwen3-6-plus","qwen3.6-plus","qwen3.6-plus-2026-04-02"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-6-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.325,"max_input_per_1m":0.5,"min_output_per_1m":1.95,"max_output_per_1m":3,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":0.40625,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-4-nano","name":"gpt-5-4-nano","display_name":"GPT-5.4 Nano","description":"The smallest and fastest GPT-5.4 tier, optimized for speed- and cost-sensitive tasks such as classification, data extraction, ranking, and sub-agent orchestration.","creator":"openai","family":"gpt","tier":"nano","version":"5-4","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":400000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-08","training_data_cutoff":null,"supported_reasoning_efforts":["default","none","xhigh"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-17","earliest_deprecation_date":"2027-09-21","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["azure_ai/gpt-5.4-nano","azure_ai/gpt-5.4-nano-2026-03-17","azure/gpt-5.4-nano","azure/gpt-5.4-nano-2026-03-17","gpt-5-4-nano","gpt-5-4-nano-medium","gpt-5-4-nano-non-reasoning","gpt-5.4-nano","gpt-5.4-nano-2026-03-17","openai-gpt-5-4-nano","openai/gpt-5.4-nano","openai/gpt-5.4-nano:batch"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-4-nano","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.24,"min_output_per_1m":0.625,"max_output_per_1m":1.5,"min_cache_read_per_1m":0.01,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-7-plus","name":"qwen3-7-plus","display_name":"Qwen3.7 Plus","description":"A cost-effective Qwen3.7-series LLM with strong vision-language, reasoning, and tool-use capabilities, optimized for balanced performance and efficiency.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen3p7-plus","alibaba-qwen3-7-plus","alibaba/qwen3.7-plus","dashscope/qwen3.7-plus","fireworks_ai/accounts/fireworks/models/qwen3p7-plus","fireworks_ai/qwen3p7-plus","qwen/qwen3.7-plus","qwen3-7-plus","qwen3.7-plus","qwen3.7-plus-2026-05-26","qwen3.7-plus-us"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-7-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.32,"max_input_per_1m":0.4,"min_output_per_1m":1.28,"max_output_per_1m":1.6,"min_cache_read_per_1m":0.064,"min_cache_write_per_1m":0.4,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-turbo","name":"glm-5-turbo","display_name":"GLM-5 Turbo","description":"A fast-inference variant of Z AI's GLM-5 model, deeply optimized for real-world agent workflows and OpenClaw-style agentic scenarios.","creator":"zhipu","family":"glm","tier":"","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":202800,"max_output_tokens":131100,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-03-15","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":2,"ids":["glm-5-turbo","z-ai/glm-5-turbo","zai-org/glm-5-turbo","zai/glm-5-turbo","zhipu-glm-5-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-5-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.2,"max_input_per_1m":1.2,"min_output_per_1m":4,"max_output_per_1m":4,"min_cache_read_per_1m":0.24,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m2-7","name":"minimax-m2-7","display_name":"MiniMax M2.7","description":"MiniMax's M2.7 MoE language model with vision support and advanced agent capabilities, designed for complex multi-step productivity tasks and dynamic tool use.","creator":"minimax","family":"minimax_m2","tier":"","version":"7","type":"language","size_in_bn":228.704,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000192,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-18","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/minimax-m2p7","fireworks_ai/accounts/fireworks/models/minimax-m2p7","fireworks_ai/minimax-m2p7","huggingface-llm-minimax-m2-7","minimax-m2-7","minimax/minimax-m2.7","MiniMaxAI/MiniMax-M2.7","pinstripes/ps/minimax-m2.7","sambanova/MiniMax-M2.7"],"hf_likes":1015,"hf_downloads":358255,"hf_downloads_all_time":358255,"hf_trending_score":295,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"minimax-m2-7","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.255,"max_input_per_1m":0.6,"min_output_per_1m":0.55,"max_output_per_1m":2.4,"min_cache_read_per_1m":0.06,"min_cache_write_per_1m":0.375,"min_reasoning_per_1m":null,"cheapest_providers":["other/pinstripes"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"nvidia-nemotron-3-ultra-550b-a55b","name":"nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","description":"A 550B-parameter mixture-of-experts Nemotron model with 55B active parameters, built for frontier-scale reasoning, tool use, and agentic tasks.","creator":"nvidia","family":"nemotron","tier":"ultra","version":"3","type":"language","size_in_bn":550,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-04","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["huggingface-reasoning-nvidia-nemotron-3-ultra-550b-a55b-nvfp4","nvidia-nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b","nvidia/nemotron-3-ultra-550b-a55b:batch","nvidia/nemotron-3-ultra-550b-a55b:free","nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"],"hf_likes":225,"hf_downloads":111067,"hf_downloads_all_time":111067,"hf_trending_score":22,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"nvidia-nemotron-3-ultra-550b-a55b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.3,"max_input_per_1m":0.6,"min_output_per_1m":1.8,"max_output_per_1m":3.6,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"xai-grok-4-3","name":"grok-4-3","display_name":"Grok 4.3","description":"A multimodal reasoning LLM from xAI that accepts text and image inputs, designed for agentic workflows, instruction-following, and tool-use tasks requiring high factual accuracy.","creator":"xai","family":"grok","tier":"","version":"4-3","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Grok","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-30","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["bedrock_mantle/xai.grok-4.3","grok-4-3","grok-4-3-low","grok-4-3-medium","grok-4-3-non-reasoning","grok-4.3","publishers/google/models/grok-4.3","x-ai/grok-4.3","xai-grok-4-3","xai/grok-4.3","xai/grok-4.3-latest"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"xai-grok-4-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.25,"max_input_per_1m":1.5,"min_output_per_1m":2.5,"max_output_per_1m":3,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","openrouter","vercel_ai_gateway","xai"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"inclusionai-ling-3-flash","name":"ling-3-flash","display_name":"InclusionAI Ling 3 Flash","description":"A 124B-parameter Mixture-of-Experts LLM with ~5.1B active parameters per token, optimized for token-efficient inference with reasoning and tool-use capabilities.","creator":"inclusionai","family":"bailing_hybrid","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/ling-3-flash","inclusionai-ling-3-flash","inclusionai/ling-3.0-flash","inclusionAI/Ling-3.0-flash","inclusionai/ling-3.0-flash-free","inclusionai/ling-3.0-flash:free","ling-3-0-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"inclusionai-ling-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.021,"max_input_per_1m":0.06,"min_output_per_1m":0.063,"max_output_per_1m":0.18,"min_cache_read_per_1m":0.0042,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-6-27b","name":"qwen3-6-27b","display_name":"Qwen3.6 27B","description":"A dense vision-language model in the Qwen3 series with 27B parameters, offering improvements in agentic coding, STEM reasoning, and multimodal inference over its predecessor.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":27,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-27","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3p6-27b","alibaba-qwen3-6-27b","alibaba/qwen3.6-27b","groq/qwen/qwen3.6-27b","huggingface-vlm-qwen3-6-27b","libertai/qwen3.6-27b","qwen/qwen3.6-27b","Qwen/Qwen3.6-27B","qwen3-6-27b","qwen3-6-27b-non-reasoning","qwen3.6-27b"],"hf_likes":1262,"hf_downloads":2772193,"hf_downloads_all_time":2772193,"hf_trending_score":117,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-6-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.6,"min_output_per_1m":0.5,"max_output_per_1m":3.6,"min_cache_read_per_1m":0.12,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/libertai"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-1","name":"gpt-5-1","display_name":"GPT-5.1","description":"OpenAI's flagship LLM for coding and agentic tasks with configurable reasoning effort levels, available via the Responses API.","creator":"openai","family":"gpt","tier":"","version":"5-1","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":409600,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-09","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal","none"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-11-13","earliest_deprecation_date":"2027-05-15","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-5.1","azure/global/gpt-5.1","azure/gpt-5.1","azure/gpt-5.1-2025-11-13","azure/us/gpt-5.1","databricks/databricks-gpt-5-1","github_copilot/gpt-5.1","gmi/openai/gpt-5.1","gpt-5-1","gpt-5-1-non-reasoning","gpt-5.1","gpt-5.1-2025-11-13","openai-gpt-5-1","openai/gpt-5.1","openai/gpt-5.1:batch","perplexity/openai/gpt-5.1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.625,"max_input_per_1m":1.5,"min_output_per_1m":5,"max_output_per_1m":12,"min_cache_read_per_1m":0.0625,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":273},"meta":{"updated_at":"2026-08-14","request_id":"dccd8a59-f1d1-4a30-837f-7440d2d474a5","execution_ms":12}}