{"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":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","tencent/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":"2026-10-14 08:02:40","pricing":{"model_id":"zhipu-glm-5-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","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","tencent/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":"2026-10-14 08:02:40","pricing":{"model_id":"moonshot-kimi-k3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":0.7,"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":"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","tencent/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":"2026-10-14 08:02:40","pricing":{"model_id":"zhipu-glm-5-3-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":0.036,"max_input_per_1m":0.188,"min_output_per_1m":0.35,"max_output_per_1m":0.9,"min_cache_read_per_1m":0.0108,"min_cache_write_per_1m":0.15001,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":14},"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":9,"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":"2026-10-14 08:02:40","pricing":{"model_id":"alibaba-qwen3-8-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","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":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":12,"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":"2026-10-14 08:02:40","pricing":{"model_id":"minimax-m3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","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":11},"providers":[],"regions":[],"region_info":{}}},{"id":"nvidia-nemotron-lightning-3-5","name":"nemotron-lightning-3-5","display_name":"Nemotron Lightning 3.5","description":"NVIDIA's fast open model targeting always-on agents and high-volume specialized tasks with strong agentic capability.","creator":"nvidia","family":"nemotron","tier":"","version":"3-5","type":"language","size_in_bn":31.578,"modalities":{"input":["text"],"output":["text"]},"context_window":1048576,"max_output_tokens":235929,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","nebius/nvidia/Nemotron-3_5-Lightning","nemotron-3-5-lightning","nvidia-nemotron-lightning-3-5","nvidia/nemotron-3.5-lightning","nvidia/nemotron-3.5-lightning:free","nvidia/NVIDIA-Nemotron-3.5-Lightning","openrouter/nvidia/nemotron-3.5-lightning"],"hf_likes":120,"hf_downloads":15740,"hf_downloads_all_time":15740,"hf_trending_score":120,"updated_at":"2026-10-14 08:02:40","pricing":{"model_id":"nvidia-nemotron-lightning-3-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.08,"min_output_per_1m":0.2,"max_output_per_1m":0.2,"min_cache_read_per_1m":0.01,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"nvidia-nemotron-super-3-120b-a12b","name":"nvidia-nemotron-super-3-120b-a12b","display_name":"Nemotron Super 3 120B A12B","description":"A 120B-parameter hybrid MoE Nemotron Super 3 model with 12B active parameters, optimized by NVIDIA for compute-efficient reasoning in specialized agentic systems.","creator":"nvidia","family":"nemotron_h","tier":"","version":"3","type":"language","size_in_bn":120,"modalities":{"input":["text"],"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":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-fp8","accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-nvfp4","deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","huggingface-llm-nvidia-nemotron-3-super-120b-a12b-bf16","nebius/nvidia/nemotron-3-super-120b-a12b","nvidia-nemotron-3-super-120b-a12b","nvidia-nemotron-super-3-120b-a12b","nvidia/nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b:free","nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","openrouter/nvidia/nemotron-3-super-120b-a12b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-14 08:02:40","pricing":{"model_id":"nvidia-nemotron-super-3-120b-a12b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":0.08,"max_input_per_1m":0.15,"min_output_per_1m":0.4,"max_output_per_1m":0.65,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"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":23,"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":"2026-10-14 08:02:40","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","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":22},"providers":[],"regions":[],"region_info":{}}},{"id":"nvidia-nemotron-nano-3-30b-a3b","name":"nvidia-nemotron-nano-3-30b-a3b","display_name":"Nemotron Nano 3 30B A3B","description":"A 30B-parameter hybrid MoE Nemotron Nano 3 model with 3B active parameters, combining Mamba-Transformer architecture for efficient reasoning and agentic tasks.","creator":"nvidia","family":"nemotron_h","tier":"","version":"3","type":"language","size_in_bn":30,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":235929,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-14","earliest_deprecation_date":"2026-08-24","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/nemotron-nano-3-30b-a3b","deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","nemotron-3-nano-30b-a3b","novita/nvidia/nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b-reasoning","nvidia-nemotron-nano-3-30b-a3b","nvidia/nemotron-3-nano-30b-a3b","nvidia/Nemotron-3-Nano-30B-A3B","nvidia/nemotron-3-nano-30b-a3b:free","nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16","openrouter/nvidia/nemotron-3-nano-30b-a3b"],"hf_likes":767,"hf_downloads":1129029,"hf_downloads_all_time":6131226,"hf_trending_score":8,"updated_at":"2026-10-14 08:02:40","pricing":{"model_id":"nvidia-nemotron-nano-3-30b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.06,"min_output_per_1m":0.2,"max_output_per_1m":0.24,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v4-4-1-flash","name":"deepseek-v4-4-1-flash","display_name":"DeepSeek V4.4.1 Flash","description":"A fast, lightweight variant of DeepSeek's V4 large language model line optimized for low-latency inference.","creator":"deepseek","family":"v4","tier":"flash","version":"4-1","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":["deepseek-v4-4-1-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-14 08:02:40"},{"id":"nousresearch-hermes-4-405b","name":"hermes-4-405b","display_name":"Hermes 4 405B","description":"A 405B-parameter hybrid reasoning LLM from Nous Research built on Llama 3.1, capable of deliberate internal reasoning or direct response generation.","creator":"nousresearch","family":"hermes","tier":"","version":null,"type":"language","size_in_bn":405,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":117964,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2025-08-26","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["nebius/NousResearch/Hermes-4-405B","nousresearch-hermes-4-405b","nousresearch/hermes-4-405b","openrouter/nousresearch/hermes-4-405b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-14 08:02:40","pricing":{"model_id":"nousresearch-hermes-4-405b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":1,"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":["openrouter"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"openbmb-minicpm-4-5-vl","name":"minicpm-4-5-vl","display_name":"MiniCPM-V 4.5 VL","description":"A vision-language variant of the MiniCPM 4.5 series, offering multimodal understanding in a compact, edge-deployable model.","creator":"openbmb","family":"minicpm","tier":"","version":"4-5","type":"language","size_in_bn":null,"modalities":{"input":["image","text"],"output":["text"]},"context_window":32000,"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":["nebius/openbmb/MiniCPM-V-4_5","openbmb-minicpm-4-5-vl"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-14 08:02:40"},{"id":"alibaba-qwen3-embedding-8b","name":"qwen3-embedding-8b","display_name":"Qwen3 Embedding 8B","description":"An 8B-parameter text embedding model from the Qwen3 series with strong multilingual capabilities and long-context support for retrieval and ranking tasks.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"embedding","size_in_bn":8,"modalities":{"input":["text"],"output":["embedding"]},"context_window":40960,"max_output_tokens":4096,"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":"2025-06-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3-embedding-8b","alibaba-qwen3-embedding-8b","alibaba/qwen3-embedding-8b","fireworks_ai/accounts/fireworks/models/qwen3-embedding-8b","llamagate/qwen3-embedding-8b","nebius/Qwen/Qwen3-Embedding-8B","novita/qwen/qwen3-embedding-8b","Qwen/Qwen3-Embedding-8B","scaleway/qwen/qwen3-embedding-8b"],"hf_likes":656,"hf_downloads":1900241,"hf_downloads_all_time":10616532,"hf_trending_score":9,"updated_at":"2026-10-14 08:02:40","pricing":{"model_id":"alibaba-qwen3-embedding-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-14","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.1,"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":["vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":13},"meta":{"updated_at":"2026-10-14","request_id":"092cb1b1-7520-4074-98ea-6b10c7676065","execution_ms":17}}