{"data":[{"id":"alibaba-qwen3-8-max","name":"qwen3-8-max","display_name":"Qwen3.8 Max","description":"A massive 2.4T-parameter MoE flagship LLM optimized for coding, knowledge work, and autonomous multi-day programming tasks with native visual understanding.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-09-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3p8-max","aihubmix/qwen3.8-max","alibaba-qwen3-8-max","alibaba/qwen3.8-max","alibaba/qwen3.8-max-0902","dashscope/qwen3.8-max","deepinfra/Qwen/Qwen3.8-Max","fireworks_ai/accounts/fireworks/models/qwen3p8-max","fireworks_ai/qwen3p8-max","novita/qwen/qwen3.8-max","openrouter/qwen/qwen3.8-max","openrouter/qwen/qwen3.8-max-0902","qwen_ai_platform/qwen3.8-max","qwen/qwen3.8-max","Qwen/Qwen3.8-Max","qwen/qwen3.8-max-0902","qwen3-8-max","qwen3-8-max-0803","qwen3.8-max","qwen3.8-max-0902","qwencloud/qwen3.8-max","scx-ai/Qwen3.8-Max"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-8-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1.65,"max_input_per_1m":2,"min_output_per_1m":4.951,"max_output_per_1m":6,"min_cache_read_per_1m":0.169,"min_cache_write_per_1m":2.1125,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","other/scx-ai"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-3","name":"glm-5-3","display_name":"GLM-5.3","description":"Z AI's flagship reasoning LLM sharing its base with GLM-5.2, with targeted improvements for complex software engineering and agentic tasks.","creator":"zhipu","family":"glm","tier":"","version":"5-3","type":"language","size_in_bn":753.33,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1310720,"max_output_tokens":943718,"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":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-18","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":19,"ids":["accounts/fireworks/models/glm-5p3","aihubmix/glm-5.3","azure_ai/FW-GLM-5.3","baseten/zai-org/GLM-5.3","databricks/databricks-glm-5-3","fireworks_ai/accounts/fireworks/models/glm-5p3","fireworks_ai/glm-5p3","friendliai/zai-org/GLM-5.3","glm-5-3","glm-5-3-low","glm-5.3","global.zai.glm-5.3","huggingface-llm-glm-5-3","mistral/zai-glm-5-3","nebius/zai-org/GLM-5.3","novita/zai-org/glm-5.3","openrouter/z-ai/glm-5.3","openrouter/z-ai/glm-5.3:batch","perplexity/perplexity/glm-5.3","sail/zai-org/GLM-5.3","together_ai/zai-org/GLM-5.3","us.zai.glm-5.3","z-ai/glm-5.3","zai-glm-5-3","zai-org/glm-5.3","zai-org/GLM-5.3","zai.glm-5.3","zai/glm-5.3","zhipu-glm-5-3"],"hf_likes":1181,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":1143,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-5-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.079,"max_input_per_1m":1.75,"min_output_per_1m":3.08,"max_output_per_1m":5.5,"min_cache_read_per_1m":0.059,"min_cache_write_per_1m":1.4,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":18},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k3","name":"kimi-k3","display_name":"Kimi K3","description":"A flagship reasoning-capable multimodal LLM with 2.8 trillion parameters, built on Kimi Delta Attention (a hybrid linear attention mechanism) with native visual understanding and tool-use support.","creator":"moonshot","family":"kimi","tier":"","version":"k3","type":"language","size_in_bn":2779.932,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":943718,"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":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":18,"ids":["accounts/fireworks/models/kimi-k3","aihubmix/kimi-k3","azure_ai/FW-Kimi-K3","baseten/moonshotai/Kimi-K3","databricks/databricks-kimi-k3","deepinfra/moonshotai/Kimi-K3","fireworks_ai/accounts/fireworks/models/kimi-k3","fireworks_ai/kimi-k3","github_copilot/kimi-k3","global.moonshotai.kimi-k3","huggingface-vlm-kimi-k3","in.moonshotai.kimi-k3","kimi-k3","kimi-k3-low","moonshot-kimi-k3","moonshot/kimi-k3","moonshotai.kimi-k3","moonshotai/kimi-k3","moonshotai/Kimi-K3","nebius/moonshotai/Kimi-K3","novita/moonshotai/kimi-k3","openrouter/moonshotai/kimi-k3","perplexity/perplexity/kimi-k3","sail/moonshotai/Kimi-K3","together_ai/moonshotai/Kimi-K3","us.moonshotai.kimi-k3"],"hf_likes":7099,"hf_downloads":2850,"hf_downloads_all_time":2855,"hf_trending_score":6642,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"moonshot-kimi-k3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.73,"max_input_per_1m":3.6,"min_output_per_1m":10,"max_output_per_1m":18,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":2.99999,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":17},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-7-max","name":"qwen3-7-max","display_name":"Qwen3.7 Max","description":"A Mixture-of-Experts Qwen3 variant tuned for maximum capability, combining reasoning, vision, and multilingual performance in a high-throughput configuration.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-21","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/qwen3p7-max","alibaba-qwen3-7-max","alibaba/qwen3.7-max","dashscope/qwen3.7-max","deepinfra/Qwen/Qwen3.7-Max","novita/qwen/qwen3.7-max","openrouter/qwen/qwen3.7-max","qwen_ai_platform/qwen3.7-max","qwen/qwen3.7-max","Qwen/Qwen3.7-Max","qwen3-7-max","qwen3.7-max","qwen3.7-max-2026-05-17","qwen3.7-max-2026-05-20","qwen3.7-max-2026-06-08","qwen3.7-max-us","qwencloud/qwen3.7-max","together_ai/Qwen/Qwen3.7-Max"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-7-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1.25,"max_input_per_1m":2.5,"min_output_per_1m":3.75,"max_output_per_1m":7.5,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":1.84375,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":8},"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":524288,"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":"2026-05-31","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":13,"ids":["accounts/fireworks/models/minimax-m3","aihubmix/minimax-m3","azure_ai/FW-MiniMax-M3","deepinfra/MiniMaxAI/MiniMax-M3","fireworks_ai/accounts/fireworks/models/minimax-m3","fireworks_ai/minimax-m3","minimax-m3","minimax/minimax-m3","minimax/MiniMax-M3","minimax/minimax-m3-free","minimax/minimax-m3:batch","MiniMaxAI/MiniMax-M3","nebius/MiniMaxAI/MiniMax-M3","novita/minimax/minimax-m3","openrouter/minimax/minimax-m3","openrouter/minimax/minimax-m3:batch","tencent/minimax-m3","together_ai/MiniMaxAI/MiniMax-M3","wandb/MiniMaxAI/MiniMax-M3"],"hf_likes":320,"hf_downloads":442,"hf_downloads_all_time":442,"hf_trending_score":314,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"minimax-m3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.23,"max_input_per_1m":0.33,"min_output_per_1m":0.96,"max_output_per_1m":1.32,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/wandb"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-turbo","name":"glm-5-turbo","display_name":"GLM-5 Turbo","description":"A fast-inference variant of Z AI's GLM-5 model, deeply optimized for real-world agent workflows and OpenClaw-style agentic scenarios.","creator":"zhipu","family":"glm","tier":"","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":202800,"max_output_tokens":131100,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-03-15","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["glm-5-turbo","novita/zai-org/glm-5-turbo","openrouter/z-ai/glm-5-turbo","z-ai/glm-5-turbo","zai-org/glm-5-turbo","zai/glm-5-turbo","zhipu-glm-5-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-5-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1.2,"max_input_per_1m":1.2,"min_output_per_1m":4,"max_output_per_1m":4,"min_cache_read_per_1m":0.24,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita","openrouter","vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"xiaomi-mimo-2-5-pro","name":"mimo-2-5-pro","display_name":"MiMo V2.5 Pro","description":"Xiaomi's flagship omnimodal LLM excelling in general agentic tasks, complex software engineering, and long-horizon reasoning benchmarks.","creator":"xiaomi","family":"mimo","tier":"","version":"2-5","type":"language","size_in_bn":1023.245,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-22","earliest_deprecation_date":"2026-10-21","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["deepinfra/XiaomiMiMo/MiMo-V2.5-Pro","mimo-v2-5-pro","mimo-v2-5-pro-non-reasoning","novita/xiaomimimo/mimo-v2.5-pro","openrouter/xiaomi/mimo-v2.5-pro","xiaomi-mimo-2-5-pro","xiaomi/mimo-v2.5-pro","xiaomimimo/mimo-v2.5-pro","XiaomiMiMo/MiMo-V2.5-Pro"],"hf_likes":653,"hf_downloads":66027,"hf_downloads_all_time":128095,"hf_trending_score":34,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"xiaomi-mimo-2-5-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.435,"max_input_per_1m":1,"min_output_per_1m":0.87,"max_output_per_1m":3,"min_cache_read_per_1m":0.0036,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"tencent-hy-3","name":"hy-3","display_name":"Hy 3","description":"A preview-stage Hunyuan-series LLM from Tencent, identified by the compact 'Hy3' designation and targeting general-purpose text generation.","creator":"tencent","family":"hy","tier":"","version":"3","type":"language","size_in_bn":298.786,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-07-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["aihubmix/hy3","deepinfra/tencent/Hy3","hy3","novita/tencent/hy3","openrouter/tencent/hy3","tencent-hy-3","tencent/hy3","tencent/Hy3"],"hf_likes":860,"hf_downloads":14143,"hf_downloads_all_time":14143,"hf_trending_score":49,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"tencent-hy-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.132,"max_input_per_1m":0.1562,"min_output_per_1m":0.528,"max_output_per_1m":0.6248,"min_cache_read_per_1m":0.033,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5v-turbo","name":"glm-5v-turbo","display_name":"GLM-5V Turbo","description":"Z AI's first native multimodal agent foundation model, handling image, video, and text inputs for vision-based coding and long-horizon agentic tasks.","creator":"zhipu","family":"glm","tier":"","version":"5v","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text","video"],"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":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-04-01","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":4,"ids":["aihubmix/glm-5v-turbo","glm-5v-turbo","novita/zai-org/glm-5v-turbo","openrouter/z-ai/glm-5v-turbo","z-ai/glm-5v-turbo","zai-org/glm-5v-turbo","zai/glm-5v-turbo","zhipu-glm-5v-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-5v-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.7042,"max_input_per_1m":1.2,"min_output_per_1m":3.09848,"max_output_per_1m":4,"min_cache_read_per_1m":0.169008,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":4},"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":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":5,"ids":["accounts/fireworks/models/qwen3p5-27b","alibaba-qwen3-5-27b","deepinfra/Qwen/Qwen3.5-27B","huggingface-vlm-qwen3-5-27b","novita/qwen/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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-5-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.26,"max_input_per_1m":0.3,"min_output_per_1m":2.4,"max_output_per_1m":2.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"inclusionai-ling-3-flash","name":"ling-3-flash","display_name":"InclusionAI Ling 3 Flash","description":"A 124B-parameter Mixture-of-Experts LLM with ~5.1B active parameters per token, optimized for token-efficient inference with reasoning and tool-use capabilities.","creator":"inclusionai","family":"bailing_hybrid","tier":"flash","version":"3","type":"language","size_in_bn":127.486,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":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":"2026-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/ling-3-flash","deepinfra/inclusionAI/Ling-3.0-flash","inclusionai-ling-3-flash","inclusionai/ling-3.0-flash","inclusionAI/Ling-3.0-flash","inclusionai/ling-3.0-flash-free","inclusionai/ling-3.0-flash:free","ling-3-0-flash","novita/inclusionai/ling-3.0-flash","openrouter/inclusionai/ling-3.0-flash"],"hf_likes":359,"hf_downloads":17020,"hf_downloads_all_time":17029,"hf_trending_score":23,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"inclusionai-ling-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.021,"max_input_per_1m":0.06,"min_output_per_1m":0.063,"max_output_per_1m":0.18,"min_cache_read_per_1m":0.0042,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"step-3-7-flash","name":"step-3-7-flash","display_name":"Step 3.7 Flash","description":"A high-efficiency multimodal Mixture-of-Experts LLM combining a large language backbone with a vision encoder for native image and video understanding.","creator":"step","family":"step","tier":"flash","version":"3-7","type":"language","size_in_bn":201.365,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":256000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"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":"2026-05-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["aihubmix/step-3.7-flash","deepinfra/stepfun-ai/Step-3.7-Flash","novita/stepfun/step-3.7-flash","openrouter/stepfun/step-3.7-flash","step-3-7-flash","stepfun-ai/Step-3.7-Flash","stepfun/step-3.7-flash"],"hf_likes":370,"hf_downloads":50187,"hf_downloads_all_time":50187,"hf_trending_score":51,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"step-3-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.22,"min_output_per_1m":1.15,"max_output_per_1m":1.32,"min_cache_read_per_1m":0.04,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","openrouter","vercel_ai_gateway"],"provider_count":5},"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":1000000,"max_output_tokens":176947,"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":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":7,"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":"2026-10-12 08:02:14","pricing":{"model_id":"minimax-m2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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","google_vertex_ai","minimax","novita","openrouter","vercel_ai_gateway"],"provider_count":7},"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":235929,"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":true,"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":11,"ids":["accounts/fireworks/models/qwen3p6-35b-a3b","aihubmix/qwen3.6-35b-a3b","alibaba-qwen3-6-35b-a3b","deepinfra/Qwen/Qwen3.6-35B-A3B","huggingface-vlm-qwen3-6-35b-a3b","libertai/qwen3.6-35b-a3b","novita/qwen/qwen3.6-35b-a3b","openrouter/qwen/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","sail/Qwen/Qwen3.6-35B-A3B","scaleway/qwen/qwen3.6-35b-a3b","wandb/Qwen/Qwen3.6-35B-A3B"],"hf_likes":1495,"hf_downloads":1510129,"hf_downloads_all_time":1510129,"hf_trending_score":292,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-6-35b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.375,"min_output_per_1m":0.4,"max_output_per_1m":2.25,"min_cache_read_per_1m":0.02,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/sail"],"provider_count":11},"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":235929,"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":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-02-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/qwen3p5-122b-a10b","aihubmix/qwen3.5-122b-a10b","alibaba-qwen3-5-122b-a10b","databricks/databricks-qwen35-122b-a10b","deepinfra/Qwen/Qwen3.5-122B-A10B","huggingface-llm-qwen3-5-122b-a10b","libertai/qwen3.5-122b-a10b","novita/qwen/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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-5-122b-a10b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1126,"max_input_per_1m":0.4,"min_output_per_1m":0.9008,"max_output_per_1m":3.2,"min_cache_read_per_1m":0.22001,"min_cache_write_per_1m":0.22001,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":8},"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":["kimi-k2","kimi-k2-0905","moonshot-kimi-k2","moonshotai/kimi-k2","moonshotai/kimi-k2-0905","novita/moonshotai/kimi-k2-0905","openrouter/moonshotai/kimi-k2","openrouter/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":"2026-10-12 08:02:14","pricing":{"model_id":"moonshot-kimi-k2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"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":203000,"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":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/glm-4p7-flash","cloudflare/@cf/zai-org/glm-4.7-flash","deepinfra/zai-org/GLM-4.7-Flash","glm-4-7-flash","glm-4-7-flash-non-reasoning","novita/zai-org/glm-4.7-flash","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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":["deepinfra"],"provider_count":5},"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":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":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":"2026-10-12 08:02:14","pricing":{"model_id":"minimax-m1-80k","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"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":"2027-07-01","deprecated":false,"has_pricing":true,"provider_count":24,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/FW-GPT-OSS-120B","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b","bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b","bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0","bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0","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","nebius/openai/gpt-oss-120b","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","sail/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":"2026-10-12 08:02:14","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.8,"min_output_per_1m":0.17,"max_output_per_1m":0.8,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":0.15001,"min_reasoning_per_1m":null,"cheapest_providers":["other/wandb"],"provider_count":23},"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":3,"ids":["glm-4-6v","glm-4-6v-reasoning","novita/zai-org/glm-4.6v","openrouter/z-ai/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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-6v","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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"],"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","openrouter/z-ai/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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-5-air","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"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":9,"ids":["accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","alibaba-qwen3-vl-235b-a22b-instruct","alibaba/qwen3-vl-235b-a22b-instruct","bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct","dashscope/qwen3-vl-235b-a22b-instruct","deepinfra/Qwen/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","openrouter/qwen/qwen3-vl-235b-a22b-instruct","qwen_ai_platform/qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","qwen3-vl-235b-a22b-instruct","qwencloud/qwen3-vl-235b-a22b-instruct"],"hf_likes":383,"hf_downloads":947793,"hf_downloads_all_time":2172030,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-vl-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.53,"min_output_per_1m":0.88,"max_output_per_1m":2.66,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"nvidia-nemotron-nano-3-30b-a3b","name":"nvidia-nemotron-nano-3-30b-a3b","display_name":"Nemotron Nano 3 30B A3B","description":"A 30B-parameter hybrid MoE Nemotron Nano 3 model with 3B active parameters, combining Mamba-Transformer architecture for efficient reasoning and agentic tasks.","creator":"nvidia","family":"nemotron_h","tier":"","version":"3","type":"language","size_in_bn":30,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":235929,"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":"2025-12-14","earliest_deprecation_date":"2026-08-24","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/nemotron-nano-3-30b-a3b","deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","nemotron-3-nano-30b-a3b","novita/nvidia/nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b-reasoning","nvidia-nemotron-nano-3-30b-a3b","nvidia/nemotron-3-nano-30b-a3b","nvidia/Nemotron-3-Nano-30B-A3B","nvidia/nemotron-3-nano-30b-a3b:free","nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16","openrouter/nvidia/nemotron-3-nano-30b-a3b"],"hf_likes":767,"hf_downloads":1129029,"hf_downloads_all_time":6131226,"hf_trending_score":8,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"nvidia-nemotron-nano-3-30b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.06,"min_output_per_1m":0.2,"max_output_per_1m":0.24,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-qwen-32b","name":"deepseek-r1-distill-qwen-32b","display_name":"DeepSeek R1 Distill Qwen 32B","description":"A 32B Qwen-based model distilled from DeepSeek R1's reasoning capabilities, offering high-quality chain-of-thought performance at a mid-scale parameter count.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","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":"2025-01-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","accounts/fireworks/models/deepseek-r1-distill-qwen-32b","cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-llm-r1-distill-qwen-32b","deepseek-r1-distill-qwen-32b","deepseek/deepseek-r1-distill-qwen-32b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","novita/deepseek/deepseek-r1-distill-qwen-32b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"hf_likes":1545,"hf_downloads":1046750,"hf_downloads_all_time":23929632,"hf_trending_score":3,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-r1-distill-qwen-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.9,"min_output_per_1m":0.15,"max_output_per_1m":4.881,"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-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","deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","novita/qwen/qwen3-vl-30b-a3b-instruct","openrouter/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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-vl-30b-a3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.2,"min_output_per_1m":0.6,"max_output_per_1m":0.7,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","fireworks_ai","openrouter"],"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","openrouter/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","together_ai/Qwen/Qwen2.5-72B-Instruct"],"hf_likes":927,"hf_downloads":457915,"hf_downloads_all_time":5817981,"hf_trending_score":1,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen2-5-72b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":1.2,"min_output_per_1m":0.3,"max_output_per_1m":1.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":6},"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","openrouter/z-ai/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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-5v","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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-omni-30b-a3b-instruct","name":"qwen3-omni-30b-a3b-instruct","display_name":"Qwen3 Omni 30B A3B Instruct","description":"An end-to-end multilingual omni-modal LLM with 30B total and 3B activated parameters, natively processing text, images, audio, and video inputs.","creator":"alibaba","family":"qwen3_omni_moe","tier":"","version":null,"type":"language","size_in_bn":30,"modalities":{"input":["audio","image"],"output":["audio"]},"context_window":65536,"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":1,"ids":["accounts/fireworks/models/qwen3-omni-30b-a3b-instruct","alibaba-qwen3-omni-30b-a3b-instruct","novita/qwen/qwen3-omni-30b-a3b-instruct","qwen/qwen3-omni-30b-a3b-instruct","qwen3-omni-30b-a3b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-omni-30b-a3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.25,"max_input_per_1m":0.25,"min_output_per_1m":0.97,"max_output_per_1m":0.97,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"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":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-autoglm-9b-phone-multilingual","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"baichuan-m2-32b","name":"baichuan-m2-32b","display_name":"BaiChuan M2 32B","description":"A 32B medically-specialized reasoning LLM from Baichuan, trained with reinforcement learning on real-world medical question-answering tasks.","creator":"baichuan","family":"baichuan","tier":"","version":null,"type":"language","size_in_bn":32,"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":1,"ids":["baichuan-m2-32b","baichuan/baichuan-m2-32b","novita/baichuan/baichuan-m2-32b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baichuan-m2-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.07,"min_output_per_1m":0.07,"max_output_per_1m":0.07,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baai-bge-2-reranker-m3","name":"bge-2-reranker-m3","display_name":"BGE Reranker M3 2","description":"A multilingual reranking model from BAAI's BGE series, designed to re-score retrieved passages for improved search relevance.","creator":"baai","family":"rerank","tier":"","version":"2","type":"reranking","size_in_bn":null,"modalities":{"input":["text"],"output":[]},"context_window":8000,"max_output_tokens":8000,"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":1,"ids":["baai-bge-2-reranker-m3","novita/baai/bge-reranker-v2-m3"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baai-bge-2-reranker-m3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.01,"min_output_per_1m":0.01,"max_output_per_1m":0.01,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baai-bge-m3","name":"bge-m3","display_name":"BGE-M3","description":"A multilingual, multi-functionality, multi-granularity text embedding model supporting dense, sparse, and multi-vector retrieval.","creator":"baai","family":"embed","tier":"","version":null,"type":"embedding","size_in_bn":null,"modalities":{"input":["text"],"output":["embedding"]},"context_window":60000,"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":["@cf/baai/bge-m3","accounts/fireworks/models/bge-m3","baai-bge-m3","BAAI/bge-m3","huggingface-sentencesimilarity-bge-m3","libertai/bge-m3","novita/baai/bge-m3"],"hf_likes":2931,"hf_downloads":16521768,"hf_downloads_all_time":132322565,"hf_trending_score":17,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baai-bge-m3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.012,"min_output_per_1m":0.01,"max_output_per_1m":0.01,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita","other/libertai"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"baidu-cobuddy","name":"cobuddy","display_name":"CoBuddy","description":"A code generation LLM from Baidu optimized for coding tasks and AI agent scenarios, delivering targeted performance for software development workflows.","creator":"baidu","family":"baidu","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":false,"structured_outputs":false,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["baidu-cobuddy","baidu/cobuddy","novita/baidu/cobuddy"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baidu-cobuddy","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.28,"max_input_per_1m":0.28,"min_output_per_1m":1.13,"max_output_per_1m":1.13,"min_cache_read_per_1m":0.07,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-prover-2-671b","name":"deepseek-prover-2-671b","display_name":"DeepSeek Prover V2 671B","description":"A 671B Mixture-of-Experts LLM specialized in mathematical theorem proving using Lean 4, representing DeepSeek's largest open-source formal reasoning model.","creator":"deepseek","family":"deepseek-prover","tier":"","version":"2.0","type":"language","size_in_bn":671,"modalities":{"input":["text"],"output":["text"]},"context_window":160000,"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":1,"ids":["deepseek-prover-2-671b","deepseek/deepseek-prover-v2-671b","novita/deepseek/deepseek-prover-v2-671b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-prover-2-671b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.7,"max_input_per_1m":0.7,"min_output_per_1m":2.5,"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":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-528b-qwen3-8b","name":"deepseek-r1-528b-qwen3-8b","display_name":"DeepSeek R1 528B Qwen3 8B","description":"A high-performance reasoning model distilled from DeepSeek R1 0528 into the Qwen3 8B base, combining R1's chain-of-thought optimization with a compact 8B architecture.","creator":"deepseek","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":528,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":32000,"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":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":1,"ids":["deepseek-r1-528b-qwen3-8b","deepseek/deepseek-r1-0528-qwen3-8b","novita/deepseek/deepseek-r1-0528-qwen3-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-r1-528b-qwen3-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.06,"min_output_per_1m":0.09,"max_output_per_1m":0.09,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-turbo","name":"deepseek-r1-turbo","display_name":"DeepSeek R1 Turbo","description":"A turbo-speed variant of DeepSeek R1 optimized for faster inference while preserving the model's strong mathematical and logical reasoning abilities.","creator":"deepseek","family":"deepseek-r1","tier":"turbo","version":"1.0","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":64000,"max_output_tokens":16000,"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":3,"ids":["deepinfra/deepseek-ai/DeepSeek-R1-Turbo","deepseek-r1-turbo","deepseek/deepseek-r1-turbo","novita/deepseek/deepseek-r1-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-r1-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.7,"max_input_per_1m":1,"min_output_per_1m":2.5,"max_output_per_1m":3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v3-community","name":"v3-community","display_name":"DeepSeek V3 Community","description":"A community-accessible variant of DeepSeek's V3 large language model, offering the same powerful mixture-of-experts architecture for general-purpose reasoning and generation tasks.","creator":"deepseek","family":"v3","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":64000,"max_output_tokens":8000,"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":1,"ids":["deepseek-v3-community","deepseek/deepseek-r1/community","deepseek/deepseek-v3/community","novita/deepseek/deepseek-r1/community","novita/deepseek/deepseek-v3/community"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-v3-community","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.89,"max_input_per_1m":4,"min_output_per_1m":0.89,"max_output_per_1m":4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v3-turbo","name":"deepseek-v3-turbo","display_name":"DeepSeek V3 Turbo","description":"A turbo-speed variant of DeepSeek V3 optimized for faster inference, pre-trained on nearly 15 trillion tokens with strong coding and instruction-following abilities.","creator":"deepseek","family":"deepseek-v3","tier":"turbo","version":"3.0","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":64000,"max_output_tokens":16000,"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":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":1,"ids":["deepseek-v3-turbo","deepseek/deepseek-v3-turbo","novita/deepseek/deepseek-v3-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-v3-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.4,"max_input_per_1m":0.4,"min_output_per_1m":1.3,"max_output_per_1m":1.3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-ocr","name":"deepseek-ocr","display_name":"DeepSeek-OCR","description":"A multimodal OCR model that compresses long document contexts via optical 2D mapping, combining a DeepEncoder with a compact MoE language model.","creator":"deepseek","family":"deepseek-ocr","tier":"","version":null,"type":"image-to-text","size_in_bn":3.336,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":8192,"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":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":"2026-10-21","deprecated":false,"has_pricing":true,"provider_count":2,"ids":["deepseek-ai/DeepSeek-OCR","deepseek-ocr","deepseek-ocr-maas","deepseek/deepseek-ocr","novita/deepseek/deepseek-ocr","publishers/google/models/deepseek-ocr-maas","vertex_ai/deepseek-ai/deepseek-ocr-maas"],"hf_likes":3218,"hf_downloads":2082348,"hf_downloads_all_time":22155059,"hf_trending_score":3,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-ocr","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.3,"min_output_per_1m":0.03,"max_output_per_1m":1.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-ocr-2","name":"deepseek-ocr-2","display_name":"DeepSeek-OCR 2","description":"An upgraded multimodal document recognition model from DeepSeek AI featuring the DeepEncoder V2 architecture for improved document understanding.","creator":"deepseek","family":"ocr","tier":"","version":"2","type":"image-to-text","size_in_bn":null,"modalities":{"input":["image","text"],"output":["text"]},"context_window":8192,"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":1,"ids":["deepseek-ocr-2","deepseek/deepseek-ocr-2","novita/deepseek/deepseek-ocr-2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-ocr-2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.03,"min_output_per_1m":0.03,"max_output_per_1m":0.03,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baidu-ernie-4-5-21b-a3b","name":"ernie-4-5-21b-a3b","display_name":"ERNIE 4.5 21B A3B","description":"A 21B-parameter Mixture-of-Experts LLM from Baidu with 3B active parameters per token, featuring multimodal heterogeneous architecture for cross-modal knowledge fusion.","creator":"baidu","family":"ernie4_5_moe","tier":"","version":"4-5","type":"language","size_in_bn":21,"modalities":{"input":["text"],"output":["text"]},"context_window":120000,"max_output_tokens":8000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"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":"2025-08-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["baidu-ernie-4-5-21b-a3b","baidu/ernie-4.5-21b-a3b","baidu/ernie-4.5-21B-a3b","novita/baidu/ernie-4.5-21B-a3b"],"hf_likes":169,"hf_downloads":37286,"hf_downloads_all_time":501103,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baidu-ernie-4-5-21b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.07,"min_output_per_1m":0.28,"max_output_per_1m":0.28,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baidu-ernie-4-5-21b-a3b-thinking","name":"ernie-4-5-21b-a3b-thinking","display_name":"ERNIE 4.5 21B A3B Thinking","description":"A reasoning-focused MoE LLM from Baidu with 21B total and 3B active parameters, enhanced for complex multi-step reasoning tasks.","creator":"baidu","family":"ernie","tier":"","version":"4-5","type":"language","size_in_bn":21,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":"Other","capabilities":{"function_calling":false,"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":"2025-10-09","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["baidu-ernie-4-5-21b-a3b-thinking","baidu/ernie-4.5-21b-a3b-thinking","baidu/ernie-4.5-21B-a3b-thinking","novita/baidu/ernie-4.5-21B-a3b-thinking"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baidu-ernie-4-5-21b-a3b-thinking","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.07,"min_output_per_1m":0.28,"max_output_per_1m":0.28,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baidu-ernie-4-5-300b-a47b-paddle","name":"ernie-4-5-300b-a47b-paddle","display_name":"ERNIE 4.5 300B A47B Paddle","description":"A PaddlePaddle-optimized 300B MoE LLM from Baidu with multimodal heterogeneous architecture for cross-modal knowledge fusion.","creator":"baidu","family":"ernie","tier":"","version":"4-5","type":"language","size_in_bn":300,"modalities":{"input":["text"],"output":["text"]},"context_window":123000,"max_output_tokens":12000,"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":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":1,"ids":["baidu-ernie-4-5-300b-a47b-paddle","baidu/ernie-4.5-300b-a47b-paddle","novita/baidu/ernie-4.5-300b-a47b-paddle"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baidu-ernie-4-5-300b-a47b-paddle","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.28,"max_input_per_1m":0.28,"min_output_per_1m":1.1,"max_output_per_1m":1.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baidu-ernie-vl-4-5-28b-a3b","name":"ernie-vl-4-5-28b-a3b","display_name":"ERNIE 4.5 VL 28B A3B","description":"A 28B multimodal MoE vision-language model from Baidu with 3B active parameters per token, enabling cross-modal understanding and generation.","creator":"baidu","family":"ernie4_5_moe_vl","tier":"","version":"4-5","type":"language","size_in_bn":28,"modalities":{"input":["image","text"],"output":["text"]},"context_window":30000,"max_output_tokens":8000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","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":"2025-08-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["baidu-ernie-vl-4-5-28b-a3b","baidu/ernie-4.5-vl-28b-a3b","novita/baidu/ernie-4.5-vl-28b-a3b"],"hf_likes":101,"hf_downloads":70108,"hf_downloads_all_time":802331,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baidu-ernie-vl-4-5-28b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.14,"max_input_per_1m":0.14,"min_output_per_1m":0.56,"max_output_per_1m":0.56,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"baidu-ernie-vl-4-5-28b-a3b-thinking","name":"ernie-vl-4-5-28b-a3b-thinking","display_name":"ERNIE 4.5 VL 28B A3B Thinking","description":"A reasoning-enhanced multimodal MoE model from Baidu built on ERNIE-4.5-VL-28B-A3B, delivering improved performance on complex visual reasoning tasks.","creator":"baidu","family":"ernie","tier":"","version":"4-5","type":"language","size_in_bn":28,"modalities":{"input":["image"],"output":["text"]},"context_window":131072,"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":1,"ids":["baidu-ernie-vl-4-5-28b-a3b-thinking","baidu/ernie-4.5-vl-28b-a3b-thinking","novita/baidu/ernie-4.5-vl-28b-a3b-thinking"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baidu-ernie-vl-4-5-28b-a3b-thinking","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.39,"max_input_per_1m":0.39,"min_output_per_1m":0.39,"max_output_per_1m":0.39,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-12b-instruct","name":"gemma-3-12b-instruct","display_name":"Gemma 3 12B Instruct","description":"An instruction-tuned 12B Gemma 3 LLM supporting vision-language inputs and 128k context.","creator":"google","family":"gemma3_text","tier":"","version":"3","type":"language","size_in_bn":12,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Gemini","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":"2025-03-13","earliest_deprecation_date":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["@cf/google/gemma-3-12b-it","accounts/fireworks/models/gemma-3-12b-it","crusoe/google/gemma-3-12b-it","deepinfra/google/gemma-3-12b-it","google-gemma-3-12b-instruct","google.gemma-3-12b-it","google/gemma-3-12b-it","google/gemma-3-12b-it:free","novita/google/gemma-3-12b-it","openrouter/google/gemma-3-12b-it"],"hf_likes":707,"hf_downloads":2516014,"hf_downloads_all_time":14080610,"hf_trending_score":2,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-gemma-3-12b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.345,"min_output_per_1m":0.1,"max_output_per_1m":0.556,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-26b-a4b-instruct","name":"gemma-4-26b-a4b-instruct","display_name":"Gemma 4 26B A4B IT","description":"Instruction-tuned MoE variant of Gemma 4 with 26B total and 4B active parameters, supporting vision, tool use, and file input.","creator":"google","family":"gemma4","tier":"","version":"4","type":"language","size_in_bn":26,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":235929,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemma","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":"2026-04-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["@cf/google/gemma-4-26b-a4b-it","accounts/fireworks/models/gemma-4-26b-a4b-it","aihubmix/gemma-4-26b-a4b-it","cloudflare/@cf/google/gemma-4-26b-a4b-it","deepinfra/google/gemma-4-26B-A4B-it","gemini/gemma-4-26b-a4b-it","gemma-4-26b-a4b-it-maas","google-gemma-4-26b-a4b-instruct","google/gemma-4-26b-a4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-26b-a4b-it:free","huggingface-vlm-gemma-4-26b-a4b-it","novita/google/gemma-4-26b-a4b-it","openrouter/google/gemma-4-26b-a4b-it","openrouter/google/gemma-4-26b-a4b-it:free","publishers/google/models/gemma-4-26b-a4b-it-maas","scaleway/google/gemma-4-26b-a4b-it","vertex_ai/gemma-4-26b-a4b-it","vertex_ai/google/gemma-4-26b-a4b-it-maas","wandb/google/gemma-4-26B-A4B-it"],"hf_likes":751,"hf_downloads":3113602,"hf_downloads_all_time":3115675,"hf_trending_score":92,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-gemma-4-26b-a4b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.042,"max_input_per_1m":0.285,"min_output_per_1m":0.22,"max_output_per_1m":0.6,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-32b","name":"glm-4-32b","display_name":"GLM-4 32B","description":"A cost-effective 32B foundation LLM in the GLM-4 series with strong capabilities in tool use, online search, and code-related tasks.","creator":"zhipu","family":"glm","tier":"","version":"4","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","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":"2025-07-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["novita/thudm/glm-4-32b-0414","thudm/glm-4-32b-0414","z-ai/glm-4-32b","zai/glm-4-32b-0414-128k","zhipu-glm-4-32b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":1.66,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["z_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-7-h","name":"glm-4-7-h","display_name":"GLM-4.7 H","description":"Z.AI's flagship GLM-4.7 H model with major upgrades in advanced coding capabilities and reliable multi-step reasoning, designed for complex agentic workflows.","creator":"zhipu","family":"glm","tier":"","version":"4-7","type":"language","size_in_bn":null,"modalities":{"input":["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":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["novita/zai-org/glm-4.7-h","zai-org/glm-4.7-h","zhipu-glm-4-7-h"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-7-h","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":0.6,"min_output_per_1m":2.2,"max_output_per_1m":2.2,"min_cache_read_per_1m":0.11,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"inclusionai-ling-3-flash-fast","name":"ling-3-flash-fast","display_name":"InclusionAI Ling 3 Flash Fast","description":"A high-throughput variant of the 124B-parameter Ling 3.0 Flash MoE model, optimized for token-efficient production-scale agentic inference.","creator":"inclusionai","family":"inclusionai","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["inclusionai-ling-3-flash-fast","inclusionai/ling-3.0-flash-fast","novita/inclusionai/ling-3.0-flash-fast"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"inclusionai-ling-3-flash-fast","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.06,"min_output_per_1m":0.18,"max_output_per_1m":0.18,"min_cache_read_per_1m":0.012,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["novita"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":71},"meta":{"updated_at":"2026-10-12","request_id":"f93f5edc-9b6e-4267-a836-7ece5beea517","execution_ms":17}}