{"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":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-8-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":20,"ids":["accounts/fireworks/models/glm-5p3","aihubmix/glm-5.3","azure_ai/FW-GLM-5.3","baseten/zai-org/GLM-5.3","coralbricks/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":"2026-10-13 08:04:31","pricing":{"model_id":"zhipu-glm-5-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.079,"max_input_per_1m":2.016,"min_output_per_1m":3.08,"max_output_per_1m":6.336,"min_cache_read_per_1m":0.059,"min_cache_write_per_1m":1.4,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":19},"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":"2026-10-13 08:04:31","pricing":{"model_id":"moonshot-kimi-k3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.73,"max_input_per_1m":3.6,"min_output_per_1m":12.5,"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-qwen3-8-2-4t-a95b","name":"qwen3-8-2-4t-a95b","display_name":"Qwen3.8 2.4T A95B","description":"A sparse mixture-of-experts LLM with 95 billion active parameters out of 2.4 trillion total, serving as the open-weight counterpart to Qwen3.8 Max.","creator":"alibaba","family":"qwen","tier":"","version":"8-2","type":"language","size_in_bn":2446.183,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":909000,"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":"2026-08-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/qwen3p8-2p4t-a95b","aihubmix/qwen3.8-2.4t-a95b","alibaba-qwen3-8-2-4t-a95b","alibaba/qwen3.8-2.4t-a95b","deepinfra/Qwen/Qwen3.8-2.4T-A95B","openrouter/qwen/qwen3.8-2.4t-a95b","openrouter/qwen/qwen3.8-2.4t-a95b:batch","qwen/qwen3.8-2.4t-a95b","Qwen/Qwen3.8-2.4T-A95B","qwen3-8-2-4t-a95b","qwen3.8-2.4t-a95b","together_ai/Qwen/Qwen3.8-2.4T-A95B"],"hf_likes":625,"hf_downloads":978,"hf_downloads_all_time":978,"hf_trending_score":616,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-8-2-4t-a95b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2,"min_output_per_1m":6,"max_output_per_1m":6,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen","deepinfra","huggingface","openrouter","other/aihubmix","together_ai","vercel_ai_gateway"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v4-1-flash","name":"deepseek-v4-1-flash","display_name":"DeepSeek V4.1 Flash Expires Exp","description":"A fast large language model in DeepSeek's V4.1 series, optimized for low-latency responses with tool-use and reasoning support.","creator":"deepseek","family":"v4","tier":"flash","version":"1","type":"language","size_in_bn":763.205,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1049000,"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":"DeepSeek","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-09-10","earliest_deprecation_date":"2026-12-15","deprecated":false,"has_pricing":true,"provider_count":12,"ids":["accounts/fireworks/models/deepseek-v4p1-flash","azure_ai/deepseek-v4.1-flash","azure_ai/FW-DeepSeek-V4.1-Flash","baseten/deepseek-ai/DeepSeek-V4.1-Flash","coralbricks/deepseek-v4.1-flash","deepseek-ai/DeepSeek-V4.1-Flash","deepseek-v4-1-flash","deepseek-v4-1-flash-non-reasoning","deepseek-v4.1-flash","deepseek/deepseek-v4.1-flash","deepseek/deepseek-v4.1-flash-expires-on-0910","deepseek/deepseek-v4.1-flash-z","fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash","fireworks_ai/deepseek-v4p1-flash","nebius/deepseek-ai/DeepSeek-V4.1-Flash","openrouter/deepseek/deepseek-v4.1-flash","openrouter/deepseek/deepseek-v4.1-flash:batch","prism/deepseek-v4.1-flash","sail/deepseek-ai/DeepSeek-V4.1-Flash","together_ai/deepseek-ai/DeepSeek-V4.1-Flash","wandb/deepseek-ai/DeepSeek-V4.1-Flash"],"hf_likes":1554,"hf_downloads":6,"hf_downloads_all_time":6,"hf_trending_score":1472,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"deepseek-v4-1-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.3,"min_output_per_1m":0.6,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.0054,"min_cache_write_per_1m":0.09,"min_reasoning_per_1m":null,"cheapest_providers":["other/coralbricks"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-8-27b","name":"qwen3-8-27b","display_name":"Qwen3.8 27B","description":"An open-weight dense vision-language model optimized for coding, professional workflows, research, multimodal interaction, and long-running agent tasks.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":27,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1000000,"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":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":"2026-08-14","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["@cf/qwen/qwen3.8-27b","accounts/fireworks/models/qwen3p8-27b","alibaba-qwen3-8-27b","alibaba/qwen3.8-27b","cerebras/qwen-3.8-27b","deepinfra/Qwen/Qwen3.8-27B","groq/qwen/qwen3.8-27b","huggingface-vlm-qwen3-8-27b","nebius/Qwen/Qwen3.8-27B","openrouter/qwen/qwen3.8-27b","openrouter/qwen/qwen3.8-27b:free","qwen/qwen3.8-27b","Qwen/Qwen3.8-27B","qwen3-8-27b","qwen3-8-27b-low","qwen3-8-27b-medium","qwen3-8-27b-non-reasoning","qwen3.8-27b","wandb/Qwen/Qwen3.8-27B"],"hf_likes":9338,"hf_downloads":2,"hf_downloads_all_time":2,"hf_trending_score":9013,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-8-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.99,"min_output_per_1m":1.49,"max_output_per_1m":4,"min_cache_read_per_1m":0.0198,"min_cache_write_per_1m":0.625,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":9},"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":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-7-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":"alibaba-qwen3-6-plus","name":"qwen3-6-plus","display_name":"Qwen3.6 Plus","description":"A Plus-tier Qwen3.6 closed model with reasoning, tool use, and vision capabilities, available exclusively through select infrastructure partners.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1000000,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen3p6-plus","alibaba-qwen3-6-plus","alibaba/qwen3.6-plus","openrouter/qwen/qwen3.6-plus","qwen/qwen3.6-plus","qwen3-6-plus","qwen3.6-plus","qwen3.6-plus-2026-04-02","together_ai/Qwen/Qwen3.6-Plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-6-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.325,"max_input_per_1m":0.5,"min_output_per_1m":1.95,"max_output_per_1m":3,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":0.40625,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-7-plus","name":"qwen3-7-plus","display_name":"Qwen3.7 Plus","description":"A cost-effective Qwen3.7-series LLM with strong vision-language, reasoning, and tool-use capabilities, optimized for balanced performance and efficiency.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":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":"2026-06-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3p7-plus","aihubmix/qwen3.7-plus","alibaba-qwen3-7-plus","alibaba/qwen3.7-plus","dashscope/qwen3.7-plus","fireworks_ai/accounts/fireworks/models/qwen3p7-plus","fireworks_ai/qwen3p7-plus","openrouter/qwen/qwen3.7-plus","qwen_ai_platform/qwen3.7-plus","qwen/qwen3.7-plus","qwen3-7-plus","qwen3.7-plus","qwen3.7-plus-2026-05-26","qwen3.7-plus-us","qwencloud/qwen3.7-plus","together_ai/Qwen/Qwen3.7-Plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-7-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.282,"max_input_per_1m":0.4,"min_output_per_1m":1.128,"max_output_per_1m":1.6,"min_cache_read_per_1m":0.0564,"min_cache_write_per_1m":0.3525,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":6},"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":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-5-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":"alibaba-qwen3-5-omni-plus","name":"qwen3-5-omni-plus","display_name":"Qwen3.5 Omni Plus","description":"A Plus-tier omni-modal Qwen3.5 model offering enhanced multimodal understanding across text, vision, and additional input modalities.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen3-5-omni-plus","qwen3-5-omni-plus","qwen3.5-omni-plus","qwen3.5-omni-plus-2026-03-15"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-5-omni-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":1.4,"max_input_per_1m":1.4,"min_output_per_1m":11,"max_output_per_1m":11,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"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":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-6-35b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-5-122b-a10b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":"alibaba-qwen3-5-omni-flash","name":"qwen3-5-omni-flash","display_name":"Qwen3.5 Omni Flash","description":"A Flash-speed omni-modal variant of the Qwen3.5 series, designed for fast multimodal understanding across text, vision, and other input types.","creator":"alibaba","family":"qwen","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen3-5-omni-flash","qwen3-5-omni-flash","qwen3.5-omni-flash","qwen3.5-omni-flash-2026-03-15"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-5-omni-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.4,"max_input_per_1m":0.4,"min_output_per_1m":3,"max_output_per_1m":3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"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":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-vl-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":"alibaba-qwen-turbo","name":"qwen-turbo","display_name":"Qwen Turbo","description":"A fast, cost-efficient Qwen LLM from Alibaba with a 1M context window suited for high-throughput simple tasks.","creator":"alibaba","family":"qwen","tier":"turbo","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","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":false,"adaptive_reasoning":false},"release_date":"2025-02-01","earliest_deprecation_date":"2026-05-13","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["alibaba-qwen-turbo","dashscope/qwen-turbo","dashscope/qwen-turbo-2024-11-01","dashscope/qwen-turbo-2025-04-28","dashscope/qwen-turbo-latest","qwen_ai_platform/qwen-turbo","qwen_ai_platform/qwen-turbo-2024-11-01","qwen_ai_platform/qwen-turbo-2025-04-28","qwen_ai_platform/qwen-turbo-latest","qwen-turbo","qwen-turbo-2024-09-19","qwen-turbo50","qwen/qwen-turbo","qwencloud/qwen-turbo","qwencloud/qwen-turbo-2024-11-01","qwencloud/qwen-turbo-2025-04-28","qwencloud/qwen-turbo-latest"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.05,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":0.5,"cheapest_providers":["alibaba_qwen","other/qwen-ai-platform","other/qwencloud"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-asr","name":"asr","display_name":"ASR","description":"A general-purpose automatic speech recognition model for converting spoken audio to text.","creator":"alibaba","family":"alibaba","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-asr","fun-asr","fun-asr-2025-08-25","fun-asr-2025-11-07"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-asr-flash","name":"asr-flash","display_name":"ASR Flash","description":"A fast-tier automatic speech recognition model optimized for low-latency transcription.","creator":"alibaba","family":"alibaba","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-asr-flash","fun-asr-flash-2026-06-15"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-asr-flash-8k-realtime","name":"asr-flash-8k-realtime","display_name":"ASR Flash 8K Realtime","description":"A real-time automatic speech recognition model with 8K audio sampling support and fast-tier processing.","creator":"alibaba","family":"alibaba","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-asr-flash-8k-realtime","fun-asr-flash-8k-realtime","fun-asr-flash-8k-realtime-2026-01-28"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-asr-mtl-realtime","name":"asr-mtl-realtime","display_name":"ASR MTL Realtime","description":"A real-time multilingual automatic speech recognition model for live multi-language transcription.","creator":"alibaba","family":"alibaba","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-asr-mtl-realtime","fun-asr-mtl-realtime","fun-asr-mtl-realtime-2025-12-10"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-asr-realtime","name":"asr-realtime","display_name":"ASR Realtime","description":"A real-time automatic speech recognition model designed for streaming audio transcription with low latency.","creator":"alibaba","family":"alibaba","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-asr-realtime","fun-asr-realtime","fun-asr-realtime-2025-09-15","fun-asr-realtime-2025-11-07","fun-asr-realtime-2026-02-28"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-coder","name":"coder","display_name":"Coder","description":"Alibaba's code-focused LLM designed for programming assistance, code generation, and software development tasks.","creator":"alibaba","family":"alibaba","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["alibaba-coder","dashscope/qwen-coder","qwen_ai_platform/qwen-coder","qwencloud/qwen-coder"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-coder","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.3,"max_input_per_1m":0.3,"min_output_per_1m":1.5,"max_output_per_1m":1.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen","other/qwen-ai-platform","other/qwencloud"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-cosyvoice-2","name":"cosyvoice-2","display_name":"CosyVoice 2","description":"A second-generation text-to-speech synthesis model from Alibaba featuring natural, expressive voice generation.","creator":"alibaba","family":"cosyvoice","tier":"","version":"2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-cosyvoice-2","cosyvoice-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-cosyvoice-2","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.286706,"max_input_per_1m":0.286706,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-cosyvoice-3-flash","name":"cosyvoice-3-flash","display_name":"CosyVoice 3 Flash","description":"A fast-tier CosyVoice 3 TTS model designed for efficient, low-latency voice generation.","creator":"alibaba","family":"cosyvoice","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-cosyvoice-3-flash","cosyvoice-v3-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-cosyvoice-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.13,"max_input_per_1m":0.13,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-cosyvoice-3-plus","name":"cosyvoice-3-plus","display_name":"CosyVoice 3 Plus","description":"A premium-tier CosyVoice 3 TTS model delivering high-quality, expressive speech synthesis.","creator":"alibaba","family":"cosyvoice","tier":"plus","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-cosyvoice-3-plus","cosyvoice-v3-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-cosyvoice-3-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.26,"max_input_per_1m":0.26,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-cosyvoice-3-5-flash","name":"cosyvoice-3-5-flash","display_name":"CosyVoice 3.5 Flash","description":"A fast-tier variant of the CosyVoice 3.5 TTS model optimized for low-latency speech synthesis.","creator":"alibaba","family":"cosyvoice","tier":"flash","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-cosyvoice-3-5-flash","cosyvoice-v3.5-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-cosyvoice-3-5-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.116,"max_input_per_1m":0.116,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-cosyvoice-3-5-plus","name":"cosyvoice-3-5-plus","display_name":"CosyVoice 3.5 Plus","description":"An enhanced-tier CosyVoice 3.5 TTS model offering higher quality speech synthesis with richer expressiveness.","creator":"alibaba","family":"cosyvoice","tier":"plus","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-cosyvoice-3-5-plus","cosyvoice-v3.5-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-cosyvoice-3-5-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.22,"max_input_per_1m":0.22,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-deep-research","name":"deep-research","display_name":"Deep Research","description":"An Alibaba LLM designed for in-depth, multi-step research tasks requiring extended reasoning and information synthesis.","creator":"alibaba","family":"alibaba","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":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":["alibaba-deep-research","qwen-deep-research"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-deep-research","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":7.742,"max_input_per_1m":7.742,"min_output_per_1m":23.367,"max_output_per_1m":23.367,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-doc-turbo","name":"doc-turbo","display_name":"Doc Turbo","description":"A fast Alibaba LLM variant optimized for document understanding and processing tasks.","creator":"alibaba","family":"alibaba","tier":"turbo","version":null,"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":[],"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":["alibaba-doc-turbo","qwen-doc-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-doc-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.087,"max_input_per_1m":0.087,"min_output_per_1m":0.144,"max_output_per_1m":0.144,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-flash","name":"flash","display_name":"Flash","description":"A lightweight, high-speed Alibaba LLM tier designed for low-latency inference on everyday tasks.","creator":"alibaba","family":"alibaba","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":997952,"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":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":["alibaba-flash","dashscope/qwen-flash","dashscope/qwen-flash-2025-07-28","qwen_ai_platform/qwen-flash","qwen_ai_platform/qwen-flash-2025-07-28","qwen-flash","qwen-flash-2025-07-28","qwencloud/qwen-flash","qwencloud/qwen-flash-2025-07-28"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.05,"min_output_per_1m":0.4,"max_output_per_1m":0.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-5-2-fast-preview","name":"glm-5-2-fast-preview","display_name":"GLM-5.2 Fast Preview","description":"A fast-inference preview variant of Zhipu's GLM-5.2 large language model, optimized for reduced latency in conversational and reasoning tasks.","creator":"zhipu","family":"glm","tier":"","version":"5-2","type":"language","size_in_bn":null,"modalities":{"input":["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":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":2,"ids":["aihubmix/glm-5.2-fast-preview","glm-5.2-fast-preview","zhipu-glm-5-2-fast-preview"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"zhipu-glm-5-2-fast-preview","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":2.254,"max_input_per_1m":2.8,"min_output_per_1m":7.889,"max_output_per_1m":8.8,"min_cache_read_per_1m":0.5635,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-gte-2-rerank","name":"gte-2-rerank","display_name":"GTE 2 Rerank","description":"A second-generation reranking model from Alibaba's GTE (General Text Embeddings) family for improving search result relevance.","creator":"alibaba","family":"gte","tier":"","version":"2","type":"reranking","size_in_bn":null,"modalities":{"input":["text"],"output":[]},"context_window":null,"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":["alibaba-gte-2-rerank","gte-rerank-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-gte-2-rerank","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.115,"max_input_per_1m":0.115,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-math-plus","name":"math-plus","display_name":"Math Plus","description":"An Alibaba LLM variant specialized for mathematical reasoning and problem-solving with enhanced accuracy.","creator":"alibaba","family":"alibaba","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":3072,"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":["alibaba-math-plus","qwen-math-plus","qwen-math-plus-2024-08-16","qwen-math-plus-2024-09-19","qwen-math-plus-latest"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-math-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.574,"max_input_per_1m":0.574,"min_output_per_1m":1.721,"max_output_per_1m":1.721,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-mt-flash","name":"mt-flash","display_name":"MT Flash","description":"A fast-tier Alibaba machine translation model supporting multilingual translation with low latency.","creator":"alibaba","family":"alibaba","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":["alibaba-mt-flash","qwen-mt-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-mt-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.16,"max_input_per_1m":0.16,"min_output_per_1m":0.49,"max_output_per_1m":0.49,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-mt-lite","name":"mt-lite","display_name":"MT Lite","description":"A lightweight Alibaba machine translation model designed for efficient multilingual translation at reduced cost.","creator":"alibaba","family":"alibaba","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":["alibaba-mt-lite","qwen-mt-lite"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-mt-lite","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":0.12,"min_output_per_1m":0.36,"max_output_per_1m":0.36,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-mt-plus","name":"mt-plus","display_name":"MT Plus","description":"An enhanced Alibaba machine translation model built on Qwen foundations, supporting translation across 92 languages with strong quality.","creator":"alibaba","family":"alibaba","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":2,"ids":["alibaba-mt-plus","novita/qwen/qwen-mt-plus","qwen-mt-plus","qwen/qwen-mt-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-mt-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.25,"max_input_per_1m":2.46,"min_output_per_1m":0.75,"max_output_per_1m":7.37,"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":"alibaba-paraformer-2","name":"paraformer-2","display_name":"Paraformer 2","description":"A second-generation non-autoregressive ASR model offering fast and accurate speech recognition without sequential decoding.","creator":"alibaba","family":"paraformer","tier":"","version":"2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-paraformer-2","paraformer-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-paraformer-2-8k","name":"paraformer-2-8k","display_name":"Paraformer 2 8K","description":"A Paraformer 2 ASR model variant supporting 8K audio sampling rate for telephony and lower-quality audio inputs.","creator":"alibaba","family":"paraformer","tier":"","version":"2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-paraformer-2-8k","paraformer-8k-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-paraformer-2-realtime","name":"paraformer-2-realtime","display_name":"Paraformer 2 Realtime","description":"A real-time streaming variant of Paraformer 2 for low-latency live speech recognition.","creator":"alibaba","family":"paraformer","tier":"","version":"2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-paraformer-2-realtime","paraformer-realtime-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-paraformer-2-realtime-8k","name":"paraformer-2-realtime-8k","display_name":"Paraformer 2 Realtime 8K","description":"A real-time Paraformer 2 ASR model with 8K audio support for live telephony-grade speech transcription.","creator":"alibaba","family":"paraformer","tier":"","version":"2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-paraformer-2-realtime-8k","paraformer-realtime-8k-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-plus-character","name":"plus-character","display_name":"Plus Character","description":"An Alibaba LLM variant from the Plus tier with enhanced character-level or persona-driven conversational capabilities.","creator":"alibaba","family":"alibaba","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":4000,"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":["alibaba-plus-character","qwen-plus-character"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-plus-character","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":0.5,"min_output_per_1m":1.4,"max_output_per_1m":1.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-plus-character-ja","name":"plus-character-ja","display_name":"Plus Character JA","description":"A Japanese-language variant of Alibaba's Plus Character LLM, optimized for persona-driven Japanese conversation.","creator":"alibaba","family":"alibaba","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":512,"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":["alibaba-plus-character-ja","qwen-plus-character-ja"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-plus-character-ja","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":0.5,"min_output_per_1m":1.4,"max_output_per_1m":1.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen-audio-3-flash-asr","name":"qwen-audio-3-flash-asr","display_name":"Qwen Audio 3 Flash ASR","description":"A speech recognition model from the Qwen Audio series optimized for fast automatic speech-to-text transcription.","creator":"alibaba","family":"qwen","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-audio-3-flash-asr","qwen-audio-3.0-asr-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-qwen-audio-3-flash-asr-filetrans","name":"qwen-audio-3-flash-asr-filetrans","display_name":"Qwen Audio 3 Flash ASR Filetrans","description":"A file-based transcription variant of the Qwen Audio ASR model tailored for batch audio file processing.","creator":"alibaba","family":"qwen","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-audio-3-flash-asr-filetrans","qwen-audio-3.0-asr-flash-filetrans"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-qwen-audio-3-flash-asr-streaming","name":"qwen-audio-3-flash-asr-streaming","display_name":"Qwen Audio 3 Flash ASR Streaming","description":"A streaming automatic speech recognition variant of the Qwen Audio model designed for real-time transcription.","creator":"alibaba","family":"qwen","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-audio-3-flash-asr-streaming","qwen-audio-3.0-asr-flash-streaming"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31"},{"id":"alibaba-qwen-audio-3-flash-realtime","name":"qwen-audio-3-flash-realtime","display_name":"Qwen Audio 3 Flash Realtime","description":"A real-time audio language model in the Qwen3 family, optimized for low-latency streaming audio understanding and interaction.","creator":"alibaba","family":"qwen","tier":"flash","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-audio-3-flash-realtime","qwen-audio-3.0-realtime-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen-audio-3-flash-realtime","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.23,"max_input_per_1m":0.23,"min_output_per_1m":0.93,"max_output_per_1m":0.93,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen-audio-3-plus-realtime","name":"qwen-audio-3-plus-realtime","display_name":"Qwen Audio 3 Plus Realtime","description":"A higher-capability real-time audio model in the Qwen3 family, designed for streaming audio comprehension with improved quality over the Flash tier.","creator":"alibaba","family":"qwen","tier":"plus","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-audio-3-plus-realtime","qwen-audio-3.0-realtime-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen-audio-3-plus-realtime","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.8,"max_input_per_1m":0.8,"min_output_per_1m":6.4,"max_output_per_1m":6.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen-audio-3-1-plus-realtime","name":"qwen-audio-3-1-plus-realtime","display_name":"Qwen Audio 3.1 Plus Realtime","description":"A real-time audio-language model from the Qwen series designed for low-latency multimodal speech understanding and generation.","creator":"alibaba","family":"qwen","tier":"plus","version":"3-1","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-audio-3-1-plus-realtime","qwen-audio-3.1-realtime-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen-audio-3-1-plus-realtime","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.8,"max_input_per_1m":0.8,"min_output_per_1m":6.4,"max_output_per_1m":6.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen-flash-character","name":"qwen-flash-character","display_name":"Qwen Flash Character","description":"A fast-tier Qwen LLM variant specialized for character-based roleplay and conversational persona tasks.","creator":"alibaba","family":"qwen","tier":"flash","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["alibaba-qwen-flash-character","qwen-flash-character"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen-flash-character","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.05,"min_output_per_1m":0.4,"max_output_per_1m":0.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen-max","name":"qwen-max","display_name":"Qwen Max","description":"Alibaba's highest-performance Qwen LLM, a large-scale MoE model excelling at complex multi-step reasoning tasks.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":30720,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","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":false,"adaptive_reasoning":false},"release_date":"2025-02-01","earliest_deprecation_date":"2026-05-13","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["alibaba-qwen-max","dashscope/qwen-max","qwen_ai_platform/qwen-max","qwen-max","qwen-max50","qwen/qwen-max","qwencloud/qwen-max"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":1.6,"max_input_per_1m":1.6,"min_output_per_1m":6.4,"max_output_per_1m":6.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["alibaba_qwen","other/qwen-ai-platform","other/qwencloud"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":84},"meta":{"updated_at":"2026-10-13","request_id":"7fbae74c-82d4-4704-92d4-fe85aa0c0875","execution_ms":18}}