{"data":[{"id":"alibaba-qwen3-6-27b","name":"qwen3-6-27b","display_name":"Qwen3.6 27B","description":"A dense vision-language model in the Qwen3 series with 27B parameters, offering improvements in agentic coding, STEM reasoning, and multimodal inference over its predecessor.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":27,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-27","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3p6-27b","alibaba-qwen3-6-27b","alibaba/qwen3.6-27b","groq/qwen/qwen3.6-27b","huggingface-vlm-qwen3-6-27b","libertai/qwen3.6-27b","qwen/qwen3.6-27b","Qwen/Qwen3.6-27B","qwen3-6-27b","qwen3-6-27b-non-reasoning","qwen3.6-27b"],"hf_likes":1262,"hf_downloads":2772193,"hf_downloads_all_time":2772193,"hf_trending_score":117,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-6-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.6,"min_output_per_1m":0.5,"max_output_per_1m":3.6,"min_cache_read_per_1m":0.12,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/libertai"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":24,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","cerebras/gpt-oss-120b","cloudflare/@cf/openai/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","fireworks_ai/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sambanova/gpt-oss-120b","scaleway/openai/gpt-oss-120b","tensormesh/openai/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":15,"min_output_per_1m":0.17,"max_output_per_1m":60,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":23},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-20b","name":"gpt-oss-20b","display_name":"GPT OSS 20B","description":"A 20-billion-parameter open-weights GPT model from OpenAI suited for reasoning and tool-use tasks at a smaller, more efficient scale.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":20,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":18,"ids":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","cloudflare/@cf/openai/gpt-oss-20b","darkbloom/gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/openai/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-20b","fireworks_ai/gpt-oss-20b","gpt-oss-20b","gpt-oss-20b-low","gpt-oss-20b-maas","groq/openai/gpt-oss-20b","lemonade/gpt-oss-20b-mxfp4-GGUF","novita/openai/gpt-oss-20b","ollama/gpt-oss:20b-cloud","openai-gpt-oss-20b","openai-reasoning-gpt-oss-20b","openai.gpt-oss-20b-1:0","openai/gpt-oss-20b","openai/gpt-oss-20b:free","openrouter/openai/gpt-oss-20b","ovhcloud/gpt-oss-20b","publishers/google/models/gpt-oss-20b-maas","replicate/openai/gpt-oss-20b","replicateopenai/gpt-oss-20b","tensormesh/openai/gpt-oss-20b","together_ai/openai/gpt-oss-20b","vertex_ai/openai/gpt-oss-20b-maas","wandb/openai/gpt-oss-20b"],"hf_likes":4552,"hf_downloads":6455272,"hf_downloads_all_time":59707566,"hf_trending_score":12,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-20b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.0145,"max_input_per_1m":5,"min_output_per_1m":0.07,"max_output_per_1m":20,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.007,"min_reasoning_per_1m":null,"cheapest_providers":["other/darkbloom"],"provider_count":18},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-7b-instruct","name":"gemma-7b-instruct","display_name":"Gemma 7B IT","description":"Instruction-tuned 7B Gemma model fine-tuned for following natural language instructions in conversational and task-oriented settings.","creator":"google","family":"gemma","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/gemma-7b-it","anyscale/google/gemma-7b-it","fireworks_ai/accounts/fireworks/models/gemma-7b-it","google-gemma-7b-instruct","groq/gemma-7b-it","huggingface-llm-gemma-7b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemma-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.2,"min_output_per_1m":0.08,"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":["groq"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-20b-safeguard","name":"gpt-oss-20b-safeguard","display_name":"GPT OSS 20B Safeguard","description":"A safety-focused open-weights language model with 21B total parameters and 3.6B active parameters, trained to interpret custom safety policies, label content, and provide transparent safety reasoning.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":20,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","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":"2025-10-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/gpt-oss-safeguard-20b","bedrock_mantle/openai.gpt-oss-safeguard-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-safeguard-20b","groq/openai/gpt-oss-safeguard-20b","openai-gpt-oss-20b-safeguard","openai.gpt-oss-safeguard-20b","openai/gpt-oss-safeguard-20b"],"hf_likes":212,"hf_downloads":55275,"hf_downloads_all_time":323598,"hf_trending_score":2,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-20b-safeguard","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.5,"min_output_per_1m":0.2,"max_output_per_1m":0.5,"min_cache_read_per_1m":0.037,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-prompt-guard-2-22m","name":"llama-prompt-guard-2-22m","display_name":"Llama Prompt Guard 2 22M","description":"A lightweight 22M-parameter classifier from Meta's Llama Prompt Guard 2 series, designed to detect prompt injection and jailbreak attempts in LLM inputs.","creator":"meta","family":"prompt-guard","tier":"","version":"2","type":"language","size_in_bn":0.022,"modalities":{"input":["text"],"output":["text"]},"context_window":512,"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":["groq/meta-llama/llama-prompt-guard-2-22m","meta-llama-prompt-guard-2-22m"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-llama-prompt-guard-2-22m","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.03,"min_output_per_1m":0.03,"max_output_per_1m":0.03,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["groq"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-prompt-guard-2-86m","name":"llama-prompt-guard-2-86m","display_name":"Llama Prompt Guard 2 86M","description":"An 86M-parameter safety classifier from Meta's Llama Prompt Guard 2 series, built to identify prompt injection and jailbreak attacks with higher capacity than the 22M variant.","creator":"meta","family":"prompt-guard","tier":"","version":"2","type":"language","size_in_bn":0.086,"modalities":{"input":["text"],"output":["text"]},"context_window":512,"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":["groq/meta-llama/llama-prompt-guard-2-86m","meta-llama-prompt-guard-2-86m"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-llama-prompt-guard-2-86m","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.04,"min_output_per_1m":0.04,"max_output_per_1m":0.04,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["groq"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"canopylabs-orpheus-1-english","name":"orpheus-1-english","display_name":"Orpheus 1 English","description":"An English-language speech synthesis model from Canopy Labs' Orpheus series, optimized for natural-sounding audio generation.","creator":"canopylabs","family":"orpheus","tier":"","version":"1","type":"text-to-speech","size_in_bn":null,"modalities":{"input":["text"],"output":["audio"]},"context_window":4000,"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":["canopylabs-orpheus-1-english","groq/canopylabs/orpheus-v1-english"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18"},{"id":"canopylabs-orpheus-arabic-saudi","name":"orpheus-arabic-saudi","display_name":"Orpheus Arabic Saudi","description":"A speech synthesis model from Canopy Labs' Orpheus series, specialized for Saudi Arabic dialect text-to-speech generation.","creator":"canopylabs","family":"orpheus","tier":"","version":null,"type":"text-to-speech","size_in_bn":null,"modalities":{"input":["text"],"output":["audio"]},"context_window":4000,"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":["canopylabs-orpheus-arabic-saudi","groq/canopylabs/orpheus-arabic-saudi"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18"},{"id":"openai-whisper-3-large","name":"whisper-3-large","display_name":"Whisper 3 Large","description":"The large-scale Whisper V3 ASR model delivering high-accuracy multilingual speech recognition and transcription.","creator":"openai","family":"whisper","tier":"","version":"3","type":"speech-to-text","size_in_bn":1.543,"modalities":{"input":["audio"],"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":["groq/whisper-large-v3","huggingface-asr-whisper-large-v3","openai-whisper-3-large","openai/whisper-large-v3","scaleway/openai/whisper-large-v3"],"hf_likes":5689,"hf_downloads":4962521,"hf_downloads_all_time":123200164,"hf_trending_score":21,"updated_at":"2026-08-14 08:03:18"},{"id":"openai-whisper-3-large-turbo","name":"whisper-3-large-turbo","display_name":"Whisper 3 Large Turbo","description":"A faster, distilled variant of Whisper Large V3 that maintains strong multilingual ASR accuracy with reduced inference latency.","creator":"openai","family":"whisper","tier":"","version":"3","type":"speech-to-text","size_in_bn":0.809,"modalities":{"input":["audio"],"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":3,"ids":["@cf/openai/whisper-large-v3-turbo","groq/whisper-large-v3-turbo","huggingface-asr-whisper-large-v3-turbo","openai-whisper-3-large-turbo","openai/whisper-large-v3-turbo","watsonx/whisper-large-v3-turbo"],"hf_likes":3012,"hf_downloads":7277395,"hf_downloads_all_time":83858224,"hf_trending_score":10,"updated_at":"2026-08-14 08:03:18"}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":11},"meta":{"updated_at":"2026-08-14","request_id":"b8e9589e-ee5b-4766-8803-9b892e9b36e2","execution_ms":11}}