{"data":[{"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":"zhipu-glm-5-3-flash","name":"glm-5-3-flash","display_name":"GLM-5.3 Flash","description":"A native multimodal LLM optimized for efficient coding and long-horizon agent tasks, using a hybrid sparse and linear attention architecture to maintain accuracy over long contexts.","creator":"zhipu","family":"glm","tier":"flash","version":"5-3","type":"language","size_in_bn":321.323,"modalities":{"input":["image","text","video"],"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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-26","earliest_deprecation_date":"2098-12-31","deprecated":false,"has_pricing":true,"provider_count":15,"ids":["accounts/fireworks/models/glm-5p3-flash","aihubmix/glm-5.3-flash","azure_ai/FW-GLM-5.3-Flash","baseten/zai-org/GLM-5.3-Flash","databricks/databricks-glm-5-3-flash","fireworks_ai/accounts/fireworks/models/glm-5p3-flash","fireworks_ai/glm-5p3-flash","friendliai/zai-org/GLM-5.3-Flash","glm-5-3-flash","nebius/zai-org/GLM-5.3-Flash","openrouter/z-ai/glm-5.3-flash","openrouter/z-ai/glm-5.3-flash:batch","perplexity/perplexity/glm-5.3-flash","sail/zai-org/GLM-5.3-Flash","together_ai/zai-org/GLM-5.3-Flash","wandb/zai-org/GLM-5.3-Flash","z-ai/glm-5.3-flash","zai-org/glm-5.3-flash","zai-org/GLM-5.3-Flash","zai/glm-5.3-flash","zhipu-glm-5-3-flash"],"hf_likes":1107,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":1073,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-5-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.11,"max_input_per_1m":0.188,"min_output_per_1m":0.35,"max_output_per_1m":0.625,"min_cache_read_per_1m":0.02,"min_cache_write_per_1m":0.15001,"min_reasoning_per_1m":null,"cheapest_providers":["other/sail"],"provider_count":14},"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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-8-2-4t-a95b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":11,"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","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":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-v4-1-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.3,"min_output_per_1m":0.6,"max_output_per_1m":1.2,"min_cache_read_per_1m":0.006,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/sail"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-7-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":"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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-6-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-7-plus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"thinkingmachines-inkling","name":"inkling","display_name":"Inkling","description":"A 975B Mixture-of-Experts multimodal LLM with 41B active parameters from Thinking Machines Lab, supporting audio, vision, reasoning, and tool use as the first open-weights release from the creator.","creator":"thinkingmachines","family":"inkling_mm_model","tier":"","version":null,"type":"language","size_in_bn":952.378,"modalities":{"input":["audio","image","pdf","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":471859,"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":false,"adaptive_reasoning":false},"release_date":"2026-07-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/inkling","baseten/thinkingmachines/inkling","deepinfra/thinkingmachines/Inkling","fireworks_ai/accounts/fireworks/models/inkling","inkling","openrouter/thinkingmachines/inkling","thinkingmachines-inkling","thinkingmachines/inkling","thinkingmachines/Inkling","thinkingmachines/inkling:batch","together_ai/thinkingmachines/Inkling"],"hf_likes":858,"hf_downloads":4,"hf_downloads_all_time":4,"hf_trending_score":844,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"thinkingmachines-inkling","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.95,"max_input_per_1m":1,"min_output_per_1m":4.05,"max_output_per_1m":4.05,"min_cache_read_per_1m":0.16,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-9b","name":"qwen3-5-9b","display_name":"Qwen3.5 9B","description":"A 9B-parameter dense LLM from the Qwen3.5 series, offering a strong balance of capability and efficiency for general text generation tasks.","creator":"alibaba","family":"qwen3_5","tier":"","version":null,"type":"language","size_in_bn":9,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":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":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-10","earliest_deprecation_date":"2026-10-21","deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen3p5-9b","alibaba-qwen3-5-9b","deepinfra/Qwen/Qwen3.5-9B","huggingface-vlm-qwen3-5-9b","openrouter/qwen/qwen3.5-9b","openrouter/qwen/qwen3.5-9b:batch","qwen/qwen3.5-9b","Qwen/Qwen3.5-9B","qwen3-5-9b","qwen3-5-9b-non-reasoning","together_ai/Qwen/Qwen3.5-9B"],"hf_likes":1315,"hf_downloads":6481835,"hf_downloads_all_time":9617908,"hf_trending_score":56,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-5-9b","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":0.17,"min_output_per_1m":0.15,"max_output_per_1m":0.25,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","openrouter"],"provider_count":4},"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":"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":"baai-bge-1-5-base-en","name":"bge-1-5-base-en","display_name":"BGE Base EN V1.5","description":"A base-size English text embedding model from BAAI's BGE series, optimized for sentence similarity and semantic search tasks.","creator":"baai","family":"embed","tier":"","version":"1-5","type":"embedding","size_in_bn":0.109,"modalities":{"input":["text"],"output":["embedding"]},"context_window":153600,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[768],"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":["@cf/baai/bge-base-en-v1.5","baai-bge-1-5-base-en","BAAI/bge-base-en-v1.5","huggingface-sentencesimilarity-bge-base-en-v1-5","huggingface-textembedding-bge-base-en-v1-5","together_ai/baai/bge-base-en-v1.5","together_ai/BAAI/bge-base-en-v1.5"],"hf_likes":411,"hf_downloads":6725168,"hf_downloads_all_time":519748129,"hf_trending_score":1,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"baai-bge-1-5-base-en","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.008,"max_input_per_1m":0.067,"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":["together_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k2-5-fp4","name":"kimi-k2-5-fp4","display_name":"Kimi K2.5 FP4","description":"A large language model in the Kimi K2 series quantized to FP4 precision for reduced memory footprint and faster inference.","creator":"moonshot","family":"kimi","tier":"","version":"k2-5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"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":["moonshot-kimi-k2-5-fp4","together_ai/moonshotai/Kimi-K2.5-fp4"],"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":"moonshot-kimi-k2-5-fp4","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":0.5,"min_output_per_1m":2.8,"max_output_per_1m":2.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-1-8b","name":"meta-llama-3-1-8b","display_name":"Llama 3.1 8B","description":"Meta's compact 8B pre-trained LLM in the Llama 3.1 series, offering efficient on-device or low-cost inference with tool-use support.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"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":false,"adaptive_reasoning":false},"release_date":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["cerebras/llama3.1-8b","llamagate/llama-3.1-8b","meta-llama-3-1-8b","meta-textgeneration-llama-3-1-8b","meta-textgenerationneuron-llama-3-1-8b","meta/llama-3.1-8b","snowflake/llama3.1-8b","together_ai/meta-llama/Meta-Llama-3.1-8B","vercel_ai_gateway/meta/llama-3.1-8b"],"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":"meta-llama-3-1-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.22,"min_output_per_1m":0.05,"max_output_per_1m":0.22,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/llamagate"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-3-70b-instruct-turbo","name":"llama-3-3-70b-instruct-turbo","display_name":"Llama 3.3 70B Instruct Turbo","description":"FP8-quantized turbo variant of Llama 3.3 70B Instruct, delivering significantly faster inference speeds with minimal accuracy trade-off.","creator":"meta","family":"llama","tier":"","version":"3-3","type":"language","size_in_bn":70,"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":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":"2026-10-22","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","meta-llama-3-3-70b-instruct-turbo","meta-llama/Llama-3.3-70B-Instruct-Turbo","together_ai/meta-llama/Llama-3.3-70B-Instruct-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":"meta-llama-3-3-70b-instruct-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":1.04,"min_output_per_1m":0.32,"max_output_per_1m":1.04,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-ministral-3-14b-instruct","name":"ministral-3-14b-instruct","display_name":"Ministral 3 14B Instruct","description":"The instruction-tuned 14B variant of Mistral AI's Ministral 3 family, featuring a vision encoder for multimodal task handling.","creator":"mistral","family":"ministral3","tier":"","version":"3","type":"language","size_in_bn":14,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/ministral-3-14b-instruct-2512","fireworks_ai/accounts/fireworks/models/ministral-3-14b-instruct-2512","huggingface-llm-ministral-3-14b-instruct-2512","huggingface-vlm-ministral-3-14b-instruct-2512-bf16","mistral-ministral-3-14b-instruct","mistral.ministral-3-14b-instruct","together_ai/mistralai/Ministral-3-14B-Instruct-2512"],"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":"mistral-ministral-3-14b-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":0.2,"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":null,"cheapest_providers":["amazon_bedrock","fireworks_ai","together_ai"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-1-5b-instruct","name":"qwen2-1-5b-instruct","display_name":"Qwen2 1.5B Instruct","description":"A 1.5B instruction-tuned model from Alibaba's Qwen2 series for efficient instruction-following in resource-constrained environments.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":1.5,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"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-qwen2-1-5b-instruct","huggingface-llm-qwen2-1-5b-instruct","together_ai/arize-ai/qwen-2-1.5b-instruct","together_ai/Qwen/Qwen2-1.5B-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-qwen2-1-5b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.02,"max_input_per_1m":0.1,"min_output_per_1m":0.02,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-14b-instruct","name":"qwen2-5-14b-instruct","display_name":"Qwen2.5 14B Instruct","description":"A 14B instruction-tuned model from Alibaba's Qwen2.5 series for capable and efficient instruction-following across diverse tasks.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":14,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/qwen-v2p5-14b-instruct","accounts/fireworks/models/qwen2p5-14b-instruct","alibaba-qwen2-5-14b-instruct","fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct","huggingface-llm-qwen2-5-14b-instruct","qwen2.5-14b-instruct","together_ai/Qwen/Qwen2.5-14B-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-qwen2-5-14b-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":0.8,"min_output_per_1m":0.2,"max_output_per_1m":0.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-turbo-7b-instruct","name":"qwen2-5-turbo-7b-instruct","display_name":"Qwen2.5 Turbo 7B Instruct","description":"A 7-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 Turbo tier, balancing speed and quality for high-throughput text generation.","creator":"alibaba","family":"qwen","tier":"turbo","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"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":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":["alibaba-qwen2-5-turbo-7b-instruct","together_ai/Qwen/Qwen2.5-7B-Instruct-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":"alibaba-qwen2-5-turbo-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.3,"max_input_per_1m":0.3,"min_output_per_1m":0.3,"max_output_per_1m":0.3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-8-flash","name":"qwen3-8-flash","display_name":"Qwen3.8 Flash","description":"A multimodal mixture-of-experts LLM previewing Alibaba's next-generation architecture, activating only a fraction of its large parameter count per token for efficient reasoning and tool use.","creator":"alibaba","family":"qwen","tier":"flash","version":null,"type":"language","size_in_bn":180,"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":"2026-08-26","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["aihubmix/qwen3.8-flash","alibaba-qwen3-8-flash","alibaba/qwen3.8-flash","dashscope/qwen3.8-flash","openrouter/qwen/qwen3.8-flash","qwen_ai_platform/qwen3.8-flash","qwen/qwen3.8-flash","Qwen/Qwen3.8-Flash","qwen3.8-flash","together_ai/Qwen/Qwen3.8-Flash"],"hf_likes":5376,"hf_downloads":706052,"hf_downloads_all_time":706052,"hf_trending_score":228,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-8-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.1126,"max_input_per_1m":0.15,"min_output_per_1m":0.380025,"max_output_per_1m":0.47,"min_cache_read_per_1m":0.014075,"min_cache_write_per_1m":0.175937,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":22},"meta":{"updated_at":"2026-10-12","request_id":"c79c6bf9-5298-4f26-92a7-aa51289e976a","execution_ms":16}}