{"data":[{"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-qwen3-8-2-4t-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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"moonshot-kimi-k2-5","name":"kimi-k2-5","display_name":"Kimi K2.5","description":"An updated iteration of Kimi K2 with enhanced reasoning, vision, and tool-use capabilities, supporting implicit caching for efficient inference.","creator":"moonshot","family":"kimi_k25","tier":"","version":"k2-5","type":"language","size_in_bn":1058.589,"modalities":{"input":["image","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":"2026-01-27","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["@cf/moonshotai/kimi-k2.5","accounts/fireworks/models/kimi-k2p5","azure_ai/kimi-k2.5","baseten/moonshotai/Kimi-K2.5","bedrock/ap-northeast-1/moonshotai.kimi-k2.5","bedrock/ap-south-1/moonshotai.kimi-k2.5","bedrock/ap-southeast-3/moonshotai.kimi-k2.5","bedrock/eu-north-1/moonshotai.kimi-k2.5","bedrock/moonshotai.kimi-k2.5","bedrock/sa-east-1/moonshotai.kimi-k2.5","bedrock/us-east-1/moonshotai.kimi-k2.5","bedrock/us-east-2/moonshotai.kimi-k2.5","bedrock/us-west-2/moonshotai.kimi-k2.5","fireworks_ai/accounts/fireworks/models/kimi-k2p5","fireworks_ai/kimi-k2p5","huggingface-llm-kimi-k2-5","kimi-k2-5","kimi-k2-5-non-reasoning","kimi-k2.5","moonshot-kimi-k2-5","moonshot/kimi-k2.5","moonshotai.kimi-k2.5","moonshotai/kimi-k2.5","moonshotai/Kimi-K2.5","openrouter/moonshotai/kimi-k2.5","together_ai/moonshotai/Kimi-K2.5","wandb/moonshotai/Kimi-K2.5"],"hf_likes":2753,"hf_downloads":5222216,"hf_downloads_all_time":9851195,"hf_trending_score":34,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"moonshot-kimi-k2-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":0.6,"min_output_per_1m":2.8,"max_output_per_1m":3.011,"min_cache_read_per_1m":0.095,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-27b","name":"qwen3-5-27b","display_name":"Qwen3.5 27B","description":"A 27B-parameter dense LLM from the Qwen3.5 series, offering strong general-purpose text generation and reasoning capabilities.","creator":"alibaba","family":"qwen3_5","tier":"","version":null,"type":"language","size_in_bn":27,"modalities":{"input":["image","text","video"],"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":"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":"2026-02-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen3p5-27b","alibaba-qwen3-5-27b","huggingface-vlm-qwen3-5-27b","openrouter/qwen/qwen3.5-27b","qwen/qwen3.5-27b","Qwen/Qwen3.5-27B","qwen3-5-27b","qwen3-5-27b-non-reasoning","qwen3.5-27b"],"hf_likes":951,"hf_downloads":3247187,"hf_downloads_all_time":5302164,"hf_trending_score":27,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-5-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.195,"max_input_per_1m":0.3,"min_output_per_1m":1.56,"max_output_per_1m":2.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m2-5","name":"minimax-m2-5","display_name":"MiniMax M2.5","description":"MiniMax's M2.5 generation MoE language model offering strong reasoning and tool-use performance for complex productivity and agent tasks.","creator":"minimax","family":"minimax_m2","tier":"","version":"5","type":"language","size_in_bn":228.704,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":196608,"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":"2026-02-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/minimax-m2p5","baseten/MiniMaxAI/MiniMax-M2.5","bedrock/ap-northeast-1/minimax.minimax-m2.5","bedrock/ap-south-1/minimax.minimax-m2.5","bedrock/ap-southeast-2/minimax.minimax-m2.5","bedrock/ap-southeast-3/minimax.minimax-m2.5","bedrock/eu-central-1/minimax.minimax-m2.5","bedrock/eu-north-1/minimax.minimax-m2.5","bedrock/eu-south-1/minimax.minimax-m2.5","bedrock/eu-west-1/minimax.minimax-m2.5","bedrock/eu-west-2/minimax.minimax-m2.5","bedrock/sa-east-1/minimax.minimax-m2.5","bedrock/us-east-1/minimax.minimax-m2.5","bedrock/us-east-2/minimax.minimax-m2.5","bedrock/us-west-2/minimax.minimax-m2.5","huggingface-llm-minimax-m2-5","minimax-m2-5","minimax.minimax-m2.5","minimax/minimax-m2.5","minimax/MiniMax-M2.5","minimax/minimax-m2.5:free","MiniMaxAI/MiniMax-M2.5","openrouter/minimax/minimax-m2.5","tensormesh/MiniMaxAI/MiniMax-M2.5","wandb/MiniMaxAI/MiniMax-M2.5"],"hf_likes":1461,"hf_downloads":928266,"hf_downloads_all_time":1586202,"hf_trending_score":13,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"minimax-m2-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.22,"max_input_per_1m":0.3,"min_output_per_1m":0.9,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.375,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-7","name":"glm-4-7","display_name":"GLM-4.7","description":"A multilingual MoE LLM from Z AI designed for complex reasoning, agentic coding, and tool use, building on the GLM-4.6 architecture.","creator":"zhipu","family":"glm4_moe","tier":"","version":"4-7","type":"language","size_in_bn":358.338,"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":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-22","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":13,"ids":["accounts/fireworks/models/glm-4p7","baseten/zai-org/GLM-4.7","cerebras/zai-glm-4.7","fireworks_ai/accounts/fireworks/models/glm-4p7","fireworks_ai/glm-4p7","glm-4-7","glm-4-7-251222","glm-4-7-non-reasoning","glm-4.7","glm-4.7-maas","novita/zai-org/glm-4.7","openrouter/z-ai/glm-4.7","publishers/google/models/glm-4.7-maas","together_ai/zai-org/GLM-4.7","vertex_ai/zai-org/glm-4.7-maas","z-ai/glm-4.7","zai-org/glm-4.7","zai-org/GLM-4.7","zai.glm-4.7","zai/glm-4.7","zhipu-glm-4-7"],"hf_likes":2026,"hf_downloads":117151,"hf_downloads_all_time":436300,"hf_trending_score":4,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-4-7","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.4,"max_input_per_1m":2.25,"min_output_per_1m":1.75,"max_output_per_1m":2.75,"min_cache_read_per_1m":0.08,"min_cache_write_per_1m":0.06,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":13},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-397b-a17b","name":"qwen3-5-397b-a17b","display_name":"Qwen3.5 397B A17B","description":"Alibaba's largest Qwen3.5 MoE model with 397B total parameters and 17B activated per token, targeting maximum capability for complex reasoning and generation.","creator":"alibaba","family":"qwen3_5_moe","tier":"","version":null,"type":"language","size_in_bn":397,"modalities":{"input":["image","text","video"],"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":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"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":"2026-02-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3p5-397b-a17b","alibaba-qwen3-5-397b-a17b","openrouter/qwen/qwen3.5-397b-a17b","qwen/qwen3.5-397b-a17b","Qwen/Qwen3.5-397B-A17B","qwen3-5-397b-a17b","qwen3-5-397b-a17b-non-reasoning","qwen3.5-397b-a17b","scaleway/qwen/qwen3.5-397b-a17b","together_ai/Qwen/Qwen3.5-397B-A17B"],"hf_likes":1462,"hf_downloads":710153,"hf_downloads_all_time":2631436,"hf_trending_score":11,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-5-397b-a17b","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":0.71,"min_output_per_1m":3.6,"max_output_per_1m":4.25,"min_cache_read_per_1m":0.3,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-122b-a10b","name":"qwen3-5-122b-a10b","display_name":"Qwen3.5 122B A10B","description":"A large Qwen3.5 Mixture-of-Experts model with 122B total parameters and 10B activated per token, featuring a 262K token context window for complex reasoning tasks.","creator":"alibaba","family":"qwen3_5_moe","tier":"","version":null,"type":"language","size_in_bn":122,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":81920,"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":"2026-02-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen3p5-122b-a10b","alibaba-qwen3-5-122b-a10b","huggingface-llm-qwen3-5-122b-a10b","libertai/qwen3.5-122b-a10b","openrouter/qwen/qwen3.5-122b-a10b","qwen/qwen3.5-122b-a10b","Qwen/Qwen3.5-122B-A10B","qwen3-5-122b-a10b","qwen3-5-122b-a10b-non-reasoning","qwen3.5-122b-a10b"],"hf_likes":523,"hf_downloads":906547,"hf_downloads_all_time":1516880,"hf_trending_score":8,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-5-122b-a10b","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":0.4,"min_output_per_1m":1.75,"max_output_per_1m":3.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/libertai"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-6-35b-a3b","name":"qwen3-6-35b-a3b","display_name":"Qwen3.6 35B A3B","description":"Alibaba's flagship Qwen3.6 MoE model with 35B total parameters and 3B activated per token, built with 256 experts and direct community feedback integration.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":35,"modalities":{"input":["image","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":"Qwen","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":true,"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/qwen3p6-35b-a3b","alibaba-qwen3-6-35b-a3b","huggingface-vlm-qwen3-6-35b-a3b","libertai/qwen3.6-35b-a3b","pinstripes/ps/qwen3.6-35b-a3b","qwen/qwen3.6-35b-a3b","Qwen/Qwen3.6-35B-A3B","qwen3-6-35b-a3b","qwen3-6-35b-a3b-non-reasoning","qwen3.6-35b-a3b","scaleway/qwen/qwen3.6-35b-a3b"],"hf_likes":1495,"hf_downloads":1510129,"hf_downloads_all_time":1510129,"hf_trending_score":292,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-6-35b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.14,"max_input_per_1m":0.375,"min_output_per_1m":0.45,"max_output_per_1m":2.25,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/pinstripes"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m2-1","name":"minimax-m2-1","display_name":"MiniMax M2.1","description":"A refined M2.1 sub-version of MiniMax's MoE language model with improved reasoning, tool-use, and implicit caching for agentic tasks.","creator":"minimax","family":"minimax_m2","tier":"","version":"1","type":"language","size_in_bn":228.704,"modalities":{"input":["image","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":"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":"2025-12-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/minimax-m2p1","bedrock/ap-northeast-1/minimax.minimax-m2.1","bedrock/ap-south-1/minimax.minimax-m2.1","bedrock/ap-southeast-3/minimax.minimax-m2.1","bedrock/eu-central-1/minimax.minimax-m2.1","bedrock/eu-north-1/minimax.minimax-m2.1","bedrock/eu-south-1/minimax.minimax-m2.1","bedrock/eu-west-1/minimax.minimax-m2.1","bedrock/eu-west-2/minimax.minimax-m2.1","bedrock/sa-east-1/minimax.minimax-m2.1","bedrock/us-east-1/minimax.minimax-m2.1","bedrock/us-east-2/minimax.minimax-m2.1","bedrock/us-west-2/minimax.minimax-m2.1","fireworks_ai/accounts/fireworks/models/minimax-m2p1","fireworks_ai/minimax-m2p1","gmi/MiniMaxAI/MiniMax-M2.1","huggingface-llm-minimax-m2-1","minimax-m2-1","minimax.minimax-m2.1","minimax/minimax-m2.1","minimax/MiniMax-M2.1","novita/minimax/minimax-m2.1","openrouter/minimax/minimax-m2.1"],"hf_likes":1351,"hf_downloads":35651,"hf_downloads_all_time":408444,"hf_trending_score":3,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"minimax-m2-1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.3,"max_input_per_1m":0.3,"min_output_per_1m":1.2,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.375,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","fireworks_ai","gmi","huggingface","minimax","novita","openrouter","vercel_ai_gateway"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-35b-a3b","name":"qwen3-5-35b-a3b","display_name":"Qwen3.5 35B A3B","description":"An efficient Qwen3.5 MoE model with 35B total parameters and only 3B activated per token, offering strong performance at low inference cost.","creator":"alibaba","family":"qwen3_5_moe","tier":"","version":null,"type":"language","size_in_bn":35,"modalities":{"input":["image","text","video"],"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":"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":"2026-02-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen3p5-35b-a3b","alibaba-qwen3-5-35b-a3b","openrouter/qwen/qwen3.5-35b-a3b","qwen/qwen3.5-35b-a3b","Qwen/Qwen3.5-35B-A3B","qwen3-5-35b-a3b","qwen3-5-35b-a3b-non-reasoning","qwen3.5-35b-a3b"],"hf_likes":1392,"hf_downloads":3940049,"hf_downloads_all_time":6350856,"hf_trending_score":18,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-5-35b-a3b","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":1.25,"max_output_per_1m":2,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen","huggingface","openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-31b","name":"gemma-4-31b","display_name":"Gemma 4 31B","description":"Google DeepMind's 31B-parameter Gemma 4 open multimodal LLM, handling text and image inputs with text output.","creator":"google","family":"gemma","tier":"","version":"4","type":"language","size_in_bn":31,"modalities":{"input":["image","text"],"output":["text"]},"context_window":256000,"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":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["bedrock_mantle/google.gemma-4-31b","gemma-4-31b","gemma-4-31b-non-reasoning","google-gemma-4-31b"],"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-gemma-4-31b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.14,"max_input_per_1m":0.99,"min_output_per_1m":0.4,"max_output_per_1m":1.49,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m2","name":"minimax-m2","display_name":"MiniMax M2","description":"MiniMax's second-generation MoE language model with reasoning and tool-use capabilities, built for complex agentic and productivity workflows.","creator":"minimax","family":"mixtral","tier":"","version":null,"type":"language","size_in_bn":228.704,"modalities":{"input":["text"],"output":["text"]},"context_window":205000,"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":"2025-10-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/minimax-m2","fireworks_ai/accounts/fireworks/models/minimax-m2","huggingface-llm-minimax-m2","minimax-m2","minimax.minimax-m2","minimax/minimax-m2","minimax/MiniMax-M2","novita/minimax/minimax-m2","openrouter/minimax/minimax-m2"],"hf_likes":1491,"hf_downloads":69357,"hf_downloads_all_time":1925616,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"minimax-m2","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":0.3,"min_output_per_1m":1.02,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.03,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v3-2","name":"v3-2","display_name":"DeepSeek V3.2","description":"DeepSeek's V3.2 MoE LLM featuring implicit caching support and improved tool-use capabilities over the V3.1 generation.","creator":"deepseek","family":"deepseek-v3","tier":"","version":"3.2","type":"language","size_in_bn":685.397,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":163840,"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":"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":"2025-12-01","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":13,"ids":["accounts/fireworks/models/deepseek-v3p2","azure_ai/deepseek-v3.2","bedrock/ap-northeast-1/deepseek.v3.2","bedrock/ap-south-1/deepseek.v3.2","bedrock/ap-southeast-3/deepseek.v3.2","bedrock/eu-north-1/deepseek.v3.2","bedrock/sa-east-1/deepseek.v3.2","bedrock/us-east-1/deepseek.v3.2","bedrock/us-east-2/deepseek.v3.2","bedrock/us-west-2/deepseek.v3.2","deepseek-ai/DeepSeek-V3.2","deepseek-llm-deepseek-v3-2","deepseek-v3-2","deepseek-v3-2-251201","deepseek-v3-2-reasoning","deepseek-v3.2","deepseek-v3.2-maas","deepseek-v3.2685","deepseek.v3.2","deepseek/deepseek-v3.2","eu.deepseek.v3.2","fireworks_ai/accounts/fireworks/models/deepseek-v3p2","gmi/deepseek-ai/DeepSeek-V3.2","novita/deepseek/deepseek-v3.2","openrouter/deepseek/deepseek-v3.2","publishers/google/models/deepseek-v3.2-maas","sambanova/DeepSeek-V3.2","us.deepseek.v3.2","vertex_ai/deepseek-ai/deepseek-v3.2-maas"],"hf_likes":1413,"hf_downloads":10366446,"hf_downloads_all_time":11229842,"hf_trending_score":6,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-v3-2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.269,"max_input_per_1m":3,"min_output_per_1m":0.4,"max_output_per_1m":4.5,"min_cache_read_per_1m":0.028,"min_cache_write_per_1m":0.056,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita","openrouter"],"provider_count":13},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"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":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":24,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","cerebras/gpt-oss-120b","cloudflare/@cf/openai/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","fireworks_ai/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sambanova/gpt-oss-120b","scaleway/openai/gpt-oss-120b","tensormesh/openai/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-120b","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":15,"min_output_per_1m":0.17,"max_output_per_1m":60,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":23},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-7-flash","name":"glm-4-7-flash","display_name":"GLM-4.7 Flash","description":"A lightweight 30B-A3B MoE model from Z AI that balances strong performance with efficiency, optimized for fast inference and agentic tasks.","creator":"zhipu","family":"glm4_moe_lite","tier":"flash","version":"4-7","type":"language","size_in_bn":31.221,"modalities":{"input":["image","text"],"output":["text"]},"context_window":202752,"max_output_tokens":131000,"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":"2026-01-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/glm-4p7-flash","cloudflare/@cf/zai-org/glm-4.7-flash","glm-4-7-flash","glm-4-7-flash-non-reasoning","openrouter/z-ai/glm-4.7-flash","z-ai/glm-4.7-flash","zai-org/glm-4.7-flash","zai-org/GLM-4.7-Flash","zai.glm-4.7-flash","zai/glm-4.7-flash","zhipu-glm-4-7-flash"],"hf_likes":1708,"hf_downloads":682370,"hf_downloads_all_time":4269790,"hf_trending_score":4,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-4-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.07,"min_output_per_1m":0.4,"max_output_per_1m":0.4,"min_cache_read_per_1m":0.01,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-9b","name":"qwen3-5-9b","display_name":"Qwen3.5 9B","description":"A 9B-parameter dense LLM from the Qwen3.5 series, offering a strong balance of capability and efficiency for general text generation tasks.","creator":"alibaba","family":"qwen3_5","tier":"","version":null,"type":"language","size_in_bn":9,"modalities":{"input":["image","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":"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":"2026-03-10","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/qwen3p5-9b","alibaba-qwen3-5-9b","huggingface-vlm-qwen3-5-9b","qwen/qwen3.5-9b","Qwen/Qwen3.5-9B","qwen3-5-9b","qwen3-5-9b-non-reasoning"],"hf_likes":1315,"hf_downloads":6481835,"hf_downloads_all_time":9617908,"hf_trending_score":56,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-5-9b","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":0.17,"min_output_per_1m":0.15,"max_output_per_1m":0.25,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v3-1-terminus","name":"deepseek-v3-1-terminus","display_name":"DeepSeek V3.1 Terminus","description":"An update to DeepSeek V3.1 that addresses language consistency and agent capability issues while preserving the model's core performance.","creator":"deepseek","family":"deepseek-v3","tier":"terminus","version":"3.1","type":"language","size_in_bn":684.531,"modalities":{"input":["text"],"output":["text"]},"context_window":163840,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-09-22","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/deepseek-v3p1-terminus","deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-v3-1-terminus","deepseek-v3-1-terminus-reasoning","deepseek/deepseek-v3.1-terminus","fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus","novita/deepseek/deepseek-v3.1-terminus"],"hf_likes":363,"hf_downloads":3879,"hf_downloads_all_time":180017,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-v3-1-terminus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.27,"max_input_per_1m":0.56,"min_output_per_1m":0.95,"max_output_per_1m":1.68,"min_cache_read_per_1m":0.13,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","huggingface","novita","openrouter","vercel_ai_gateway"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-coder-next","name":"qwen3-coder-next","display_name":"Qwen3 Coder Next","description":"A next-generation Qwen3 coding model with enhanced reasoning and tool-use capabilities for advanced agentic programming tasks.","creator":"alibaba","family":"qwen3_next","tier":"","version":null,"type":"language","size_in_bn":79.674,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":8192,"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":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":"2026-02-04","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["alibaba-qwen3-coder-next","alibaba/qwen3-coder-next","bedrock/ap-northeast-1/qwen.qwen3-coder-next","bedrock/ap-south-1/qwen.qwen3-coder-next","bedrock/ap-southeast-3/qwen.qwen3-coder-next","bedrock/eu-central-1/qwen.qwen3-coder-next","bedrock/eu-south-1/qwen.qwen3-coder-next","bedrock/eu-west-1/qwen.qwen3-coder-next","bedrock/eu-west-2/qwen.qwen3-coder-next","bedrock/sa-east-1/qwen.qwen3-coder-next","bedrock/us-east-1/qwen.qwen3-coder-next","bedrock/us-east-2/qwen.qwen3-coder-next","bedrock/us-west-2/qwen.qwen3-coder-next","huggingface-reasoning-qwen3-coder-next","qwen.qwen3-coder-next","qwen/qwen3-coder-next","qwen3-coder-next"],"hf_likes":1313,"hf_downloads":646521,"hf_downloads_all_time":2269042,"hf_trending_score":28,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-coder-next","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":0.5,"min_output_per_1m":0.8,"max_output_per_1m":1.5,"min_cache_read_per_1m":0.07,"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","name":"kimi-k2","display_name":"Kimi K2","description":"A large-scale mixture-of-experts LLM with 1 trillion total parameters and 32B active parameters, trained with the Muon optimizer for strong agentic and tool-use performance.","creator":"moonshot","family":"kimi_k2","tier":"","version":"k2","type":"language","size_in_bn":1058.589,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":262144,"max_output_tokens":100352,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-12-31","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":"2025-07-11","earliest_deprecation_date":"2026-05-14","deprecated":false,"has_pricing":true,"provider_count":4,"ids":["a-x-k2","accounts/fireworks/models/kimi-k2p6","kimi-k2","kimi-k2-0905","kimi-k2-6","moonshot-kimi-k2","moonshotai/kimi-k2","moonshotai/kimi-k2-0905","moonshotai/kimi-k2.6","novita/moonshotai/kimi-k2-0905","vercel_ai_gateway/moonshotai/kimi-k2"],"hf_likes":145,"hf_downloads":423,"hf_downloads_all_time":423,"hf_trending_score":145,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"moonshot-kimi-k2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.57,"max_input_per_1m":0.6,"min_output_per_1m":2.3,"max_output_per_1m":2.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-coder-480b-a35b-instruct","name":"qwen3-coder-480b-a35b-instruct","display_name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen3's flagship agentic code model with 480B total and 35B activated parameters, excelling at autonomous programming, tool calling, and browser-use tasks.","creator":"alibaba","family":"qwen3_moe","tier":"","version":null,"type":"language","size_in_bn":480,"modalities":{"input":["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":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","alibaba-qwen3-coder-480b-a35b-instruct","deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","novita/qwen/qwen3-coder-480b-a35b-instruct","qwen/qwen3-coder-480b-a35b-instruct","Qwen/Qwen3-Coder-480B-A35B-Instruct","qwen3-coder-480b-a35b-instruct","wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct"],"hf_likes":1325,"hf_downloads":57687,"hf_downloads_all_time":885858,"hf_trending_score":0.5,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-coder-480b-a35b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.22,"max_input_per_1m":100,"min_output_per_1m":1.3,"max_output_per_1m":150,"min_cache_read_per_1m":null,"min_cache_write_per_1m":0.022,"min_reasoning_per_1m":null,"cheapest_providers":["google_gemini","google_vertex_ai"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"minimax-m1-80k","name":"minimax-m1-80k","display_name":"MiniMax M1 80k","description":"A long-context variant of MiniMax's open-weight hybrid MoE reasoning model supporting 80,000-token windows for extended document and multi-turn tasks.","creator":"minimax","family":"m1","tier":"","version":null,"type":"language","size_in_bn":456.09,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":40000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/minimax-m1-80k","fireworks_ai/accounts/fireworks/models/minimax-m1-80k","minimax-m1-80k","minimaxai/minimax-m1-80k","novita/minimaxai/minimax-m1-80k"],"hf_likes":691,"hf_downloads":743,"hf_downloads_all_time":101977,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"minimax-m1-80k","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":0.55,"min_output_per_1m":0.1,"max_output_per_1m":2.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-5-air","name":"glm-4-5-air","display_name":"GLM-4.5 Air","description":"A compact MoE variant of GLM-4.5 from Z AI, offering a lighter architecture while retaining strong agentic reasoning and tool-use performance.","creator":"zhipu","family":"glm4_moe","tier":"air","version":"4-5","type":"language","size_in_bn":110.469,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":98304,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-12-31","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":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-07-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/glm-4p5-air","fireworks_ai/accounts/fireworks/models/glm-4p5-air","glm-4-5-air","novita/zai-org/glm-4.5-air","pinstripes/ps/glm-4.5-air","vercel_ai_gateway/zai/glm-4.5-air","z-ai/glm-4.5-air","z-ai/glm-4.5-air:free","zai-org/glm-4.5-air","zai/glm-4.5-air","zhipu-glm-4-5-air"],"hf_likes":599,"hf_downloads":389697,"hf_downloads_all_time":3025118,"hf_trending_score":2,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-4-5-air","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.125,"max_input_per_1m":0.22,"min_output_per_1m":0.45,"max_output_per_1m":1.1,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/pinstripes"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-20b","name":"gpt-oss-20b","display_name":"GPT OSS 20B","description":"A 20-billion-parameter open-weights GPT model from OpenAI suited for reasoning and tool-use tasks at a smaller, more efficient scale.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":20,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"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":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":18,"ids":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","cloudflare/@cf/openai/gpt-oss-20b","darkbloom/gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/openai/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-20b","fireworks_ai/gpt-oss-20b","gpt-oss-20b","gpt-oss-20b-low","gpt-oss-20b-maas","groq/openai/gpt-oss-20b","lemonade/gpt-oss-20b-mxfp4-GGUF","novita/openai/gpt-oss-20b","ollama/gpt-oss:20b-cloud","openai-gpt-oss-20b","openai-reasoning-gpt-oss-20b","openai.gpt-oss-20b-1:0","openai/gpt-oss-20b","openai/gpt-oss-20b:free","openrouter/openai/gpt-oss-20b","ovhcloud/gpt-oss-20b","publishers/google/models/gpt-oss-20b-maas","replicate/openai/gpt-oss-20b","replicateopenai/gpt-oss-20b","tensormesh/openai/gpt-oss-20b","together_ai/openai/gpt-oss-20b","vertex_ai/openai/gpt-oss-20b-maas","wandb/openai/gpt-oss-20b"],"hf_likes":4552,"hf_downloads":6455272,"hf_downloads_all_time":59707566,"hf_trending_score":12,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-20b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.0145,"max_input_per_1m":5,"min_output_per_1m":0.07,"max_output_per_1m":20,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.007,"min_reasoning_per_1m":null,"cheapest_providers":["other/darkbloom"],"provider_count":18},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-vl-235b-a22b-instruct","name":"qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","description":"The flagship instruction-tuned vision-language MoE model in the Qwen3 series, with 235B total and 22B activated parameters for superior visual perception and reasoning.","creator":"alibaba","family":"qwen3_vl_moe","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":262144,"max_output_tokens":129024,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"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":"2025-09-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","alibaba-qwen3-vl-235b-a22b-instruct","alibaba/qwen3-vl-235b-a22b-instruct","dashscope/qwen3-vl-235b-a22b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","novita/qwen/qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","qwen3-vl-235b-a22b-instruct"],"hf_likes":383,"hf_downloads":947793,"hf_downloads_all_time":2172030,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-vl-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.22,"max_input_per_1m":0.4,"min_output_per_1m":0.88,"max_output_per_1m":1.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-6v","name":"glm-4-6v","display_name":"GLM-4.6V","description":"A multimodal MoE vision-language model from Z AI in the GLM-V family, supporting vision, file input, and scalable reinforcement learning-based reasoning.","creator":"zhipu","family":"glm4v_moe","tier":"","version":"4-6v","type":"language","size_in_bn":107.711,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":131072,"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":"2025-12-08","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["glm-4-6v","glm-4-6v-reasoning","novita/zai-org/glm-4.6v","z-ai/glm-4.6v","zai-org/glm-4.6v","zai-org/GLM-4.6V","zai/glm-4.6v","zhipu-glm-4-6v"],"hf_likes":390,"hf_downloads":6998,"hf_downloads_all_time":405792,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-4-6v","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":0.3,"min_output_per_1m":0.9,"max_output_per_1m":0.9,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita","openrouter","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-235b-a22b-instruct","name":"qwen3-235b-a22b-instruct","display_name":"Qwen3 235B A22B Instruct","description":"An instruction-tuned update of the Qwen3 235B A22B MoE model with significant improvements in instruction following, logical reasoning, and general capabilities.","creator":"alibaba","family":"qwen3_moe","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["text"],"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":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","alibaba-qwen3-235b-a22b-instruct","crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507","deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","novita/qwen/qwen3-235b-a22b-instruct-2507","qwen/qwen3-235b-a22b-instruct-2507","Qwen/Qwen3-235B-A22B-Instruct-2507","qwen3-235b-a22b-instruct","qwen3-235b-a22b-instruct-2507","replicate/qwen/qwen3-235b-a22b-instruct-2507","scaleway/qwen/qwen3-235b-a22b-instruct-2507","wandb/Qwen/Qwen3-235B-A22B-Instruct-2507"],"hf_likes":773,"hf_downloads":150781,"hf_downloads_all_time":1182969,"hf_trending_score":1,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.09,"max_input_per_1m":10,"min_output_per_1m":0.58,"max_output_per_1m":10,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","huggingface","novita"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-vl-30b-a3b-instruct","name":"qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","description":"An instruction-tuned vision-language MoE model with 30B total and 3B activated parameters, offering strong multimodal understanding and generation capabilities.","creator":"alibaba","family":"qwen3_vl_moe","tier":"","version":null,"type":"language","size_in_bn":30,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":"2025-10-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","alibaba-qwen3-vl-30b-a3b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","novita/qwen/qwen3-vl-30b-a3b-instruct","qwen/qwen3-vl-30b-a3b-instruct","Qwen/Qwen3-VL-30B-A3B-Instruct","qwen3-vl-30b-a3b-instruct"],"hf_likes":562,"hf_downloads":2219395,"hf_downloads_all_time":14070852,"hf_trending_score":2,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-vl-30b-a3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.13,"max_input_per_1m":0.2,"min_output_per_1m":0.52,"max_output_per_1m":0.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-qwen-14b","name":"deepseek-r1-distill-qwen-14b","display_name":"DeepSeek R1 Distill Qwen 14B","description":"A 14B Qwen-based model distilled from DeepSeek R1, balancing strong reasoning performance with moderate computational requirements.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":14,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":null,"capabilities":{"function_calling":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/deepseek-r1-distill-qwen-14b","deepseek-llm-r1-distill-qwen-14b","deepseek-r1-distill-qwen-14b","deepseek/deepseek-r1-distill-qwen-14b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b","novita/deepseek/deepseek-r1-distill-qwen-14b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"],"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":"deepseek-r1-distill-qwen-14b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.2,"min_output_per_1m":0.07,"max_output_per_1m":0.431,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-72b-instruct","name":"qwen2-5-72b-instruct","display_name":"Qwen2.5 72B Instruct","description":"A 72-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, excelling at natural language understanding, summarization, and dialogue.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":72,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":"2024-09-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen2p5-72b-instruct","alibaba-qwen2-5-72b-instruct","deepinfra/Qwen/Qwen2.5-72B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct","huggingface-llm-qwen2-5-72b-instruct","hyperbolic/Qwen/Qwen2.5-72B-Instruct","nebius/Qwen/Qwen2.5-72B-Instruct","novita/qwen/qwen-2.5-72b-instruct","qwen/qwen-2.5-72b-instruct","Qwen/Qwen2.5-72B-Instruct","qwen2-5-72b-instruct","qwen2.5-72b-instruct"],"hf_likes":927,"hf_downloads":457915,"hf_downloads_all_time":5817981,"hf_trending_score":1,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen2-5-72b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":0.9,"min_output_per_1m":0.3,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","hyperbolic"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-coder-32b-instruct","name":"qwen2-5-coder-32b-instruct","display_name":"Qwen2.5 Coder 32B Instruct","description":"A 32-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, excelling at code generation, debugging, and explanation across many programming languages.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":"2024-11-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["@cf/qwen/qwen2.5-coder-32b-instruct","accounts/fireworks/models/qwen2p5-coder-32b-instruct","accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","alibaba-qwen2-5-coder-32b-instruct","cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","huggingface-llm-qwen2-5-coder-32b-instruct","hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct","lambda_ai/qwen25-coder-32b-instruct","nscale/Qwen/Qwen2.5-Coder-32B-Instruct","openrouter/qwen/qwen-2.5-coder-32b-instruct","ovhcloud/Qwen2.5-Coder-32B-Instruct","qwen/qwen-2.5-coder-32b-instruct","qwen2-5-coder-32b-instruct","qwen2.5-coder-32b-instruct"],"hf_likes":2008,"hf_downloads":1257495,"hf_downloads_all_time":5998607,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen2-5-coder-32b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.9,"min_output_per_1m":0.1,"max_output_per_1m":1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-5v","name":"glm-4-5v","display_name":"GLM-4.5V","description":"A multimodal MoE vision-language model from Z AI based on GLM-4.5 Air, delivering strong visual reasoning and tool-use performance.","creator":"zhipu","family":"glm4v_moe","tier":"","version":"4-5v","type":"language","size_in_bn":107.711,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-12-31","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":false,"adaptive_reasoning":false},"release_date":"2025-08-11","earliest_deprecation_date":"2026-12-31","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/glm-4p5v","fireworks_ai/accounts/fireworks/models/glm-4p5v","glm-4-5v","glm-4-5v-reasoning","novita/zai-org/glm-4.5v","z-ai/glm-4.5v","zai-org/glm-4.5v","zai/glm-4.5v","zhipu-glm-4-5v"],"hf_likes":717,"hf_downloads":44600,"hf_downloads_all_time":417587,"hf_trending_score":2,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-glm-4-5v","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":1.2,"min_output_per_1m":1.2,"max_output_per_1m":1.8,"min_cache_read_per_1m":0.11,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita","openrouter","vercel_ai_gateway","z_ai"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-4b-instruct","name":"qwen3-4b-instruct","display_name":"Qwen3 4B Instruct","description":"An instruction-tuned 4B Qwen3 model offering efficient text generation and reasoning in a small parameter footprint.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":4,"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":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/qwen3-4b-instruct-2507","alibaba-qwen3-4b-instruct","fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507","huggingface-reasoning-qwen3-4b-instruct-2507","lemonade/Qwen3-4B-Instruct-2507-GGUF","qwen3-4b-2507-instruct","qwen3-4b-2507-instruct-reasoning","qwen3-4b-instruct","qwen3-4b-instruct-reasoning"],"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-qwen3-4b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.2,"min_output_per_1m":0.03,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-llama-8b","name":"deepseek-r1-distill-llama-8b","display_name":"DeepSeek R1 Distill Llama 8B","description":"A compact 8B Llama-based model distilled from DeepSeek R1, delivering strong reasoning performance in a lightweight architecture.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/deepseek-r1-distill-llama-8b","deepseek-llm-r1-distill-llama-8b","deepseek-r1-distill-llama-8b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b","nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B"],"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":"deepseek-r1-distill-llama-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.025,"max_input_per_1m":0.2,"min_output_per_1m":0.025,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-coder-7b-instruct","name":"qwen2-5-coder-7b-instruct","display_name":"Qwen2.5 Coder 7B Instruct","description":"A 7-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, designed for responsive code generation and developer assistance.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen2p5-coder-7b-instruct","alibaba-qwen2-5-coder-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct","huggingface-llm-qwen2-5-coder-7b-instruct","nscale/Qwen/Qwen2.5-Coder-7B-Instruct","qwen2-5-coder-7b-instruct","qwen2.5-coder-7b-instruct"],"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-qwen2-5-coder-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.2,"min_output_per_1m":0.03,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","nscale"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-mixtral-8x22b-instruct","name":"mistral-mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","description":"The instruction-tuned version of Mistral AI's Mixtral 8x22B MoE model, optimized for following complex instructions and multi-turn dialogue.","creator":"mistral","family":"mixtral","tier":"","version":null,"type":"language","size_in_bn":22,"modalities":{"input":["text"],"output":["text"]},"context_window":65536,"max_output_tokens":2048,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-01-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":"2024-04-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/mixtral-8x22b-instruct","anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf","huggingface-llm-mistralai-mixtral-8x22B-instruct-v0-1","mistral-8x22b-instruct","mistral-mixtral-8x22b-instruct","mistral/mixtral-8x22b-instruct","mistralai/mixtral-8x22b-instruct","nscale/mistralai/mixtral-8x22b-instruct-v0.1","ollama/mixtral-8x22B-Instruct-v0.1","openrouter/mistralai/mixtral-8x22b-instruct","vercel_ai_gateway/mistral/mixtral-8x22b-instruct"],"hf_likes":748,"hf_downloads":28279,"hf_downloads_all_time":6052030,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"mistral-mixtral-8x22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":2,"min_output_per_1m":0.6,"max_output_per_1m":6,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-autoglm-9b-phone-multilingual","name":"autoglm-9b-phone-multilingual","display_name":"AutoGLM Phone 9B Multilingual","description":"A 9B multilingual mobile agent model built on AutoGLM that understands smartphone screens via multimodal perception and executes automated operations.","creator":"zhipu","family":"autoglm","tier":"","version":null,"type":"language","size_in_bn":9,"modalities":{"input":["image"],"output":["text"]},"context_window":65536,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["novita/zai-org/autoglm-phone-9b-multilingual","zai-org/autoglm-phone-9b-multilingual","zhipu-autoglm-9b-phone-multilingual"],"hf_likes":233,"hf_downloads":1494,"hf_downloads_all_time":45330,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"zhipu-autoglm-9b-phone-multilingual","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.035,"max_input_per_1m":0.035,"min_output_per_1m":0.138,"max_output_per_1m":0.138,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepcogito-cogito-2-1-671b","name":"cogito-2-1-671b","display_name":"Cogito V2.1 671B","description":"A massive 671B-parameter mixture-of-experts LLM from Deep Cogito trained with self-play reinforcement learning, matching frontier closed and open model performance.","creator":"deepcogito","family":"cogito","tier":"","version":"2-1","type":"language","size_in_bn":671,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"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":false,"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":"2025-11-13","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["deepcogito-cogito-2-1-671b","deepcogito/cogito-v2.1-671b"],"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":"deepcogito-cogito-2-1-671b","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":1.25,"max_output_per_1m":1.25,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","openrouter"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":78},"meta":{"updated_at":"2026-08-14","request_id":"9ca247bc-c531-4329-9b19-332ed24399ff","execution_ms":10}}