{"data":[{"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":21,"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","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/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","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":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.039,"max_input_per_1m":15,"min_output_per_1m":0.18,"max_output_per_1m":60,"min_cache_read_per_1m":0.075,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":21},"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":false,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":16,"ids":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/openai/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/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","replicateopenai/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":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-20b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.029,"max_input_per_1m":5,"min_output_per_1m":0.14,"max_output_per_1m":20,"min_cache_read_per_1m":0.0375,"min_cache_write_per_1m":0.007,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":16},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-3-70b-instruct","name":"llama-3-3-70b-instruct","display_name":"Llama 3.3 70B Instruct","description":"Meta's 70B instruction-tuned LLM from Llama 3.3, optimized for complex instruction-following and deployed across multiple cloud regions.","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":120000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama3","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":"2024-12-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":20,"ids":["accounts/fireworks/models/llama-v3p3-70b-instruct","azure_ai/Llama-3.3-70B-Instruct","crusoe/meta-llama/Llama-3.3-70B-Instruct","databricks/databricks-meta-llama-3-3-70b-instruct","deepinfra/meta-llama/Llama-3.3-70B-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct","gradient_ai/llama3.3-70b-instruct","groq/llama-3.3-70b-versatile","hyperbolic/meta-llama/Llama-3.3-70B-Instruct","lambda_ai/llama3.3-70b-instruct-fp8","llama-3-3-instruct-70b","llama-3.3-70b-instruct-maas","meta_llama/Llama-3.3-70B-Instruct","meta-llama-3-3-70b-instruct","meta-llama/llama-3.3-70b-instruct","meta-llama/llama-3.3-70b-instruct:free","meta-textgeneration-llama-3-3-70b-instruct","meta.llama3-3-70b-instruct-v1:0","meta.llama3-3-70b-instruct-v1:0:128k","nebius/meta-llama/Llama-3.3-70B-Instruct","novita/meta-llama/llama-3.3-70b-instruct","nscale/meta-llama/Llama-3.3-70B-Instruct","oci/meta.llama-3.3-70b-instruct","oci/meta.llama-3.3-70b-instruct-fp8-dynamic","ovhcloud/Meta-Llama-3_3-70B-Instruct","publishers/google/models/llama-3.3-70b-instruct-maas","publishers/meta/models/llama-3.3-70b-instruct-maas","sambanova/Meta-Llama-3.3-70B-Instruct","together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free","us.meta.llama3-3-70b-instruct-v1:0","wandb/meta-llama/Llama-3.3-70B-Instruct","watsonx/meta-llama/llama-3-3-70b-instruct"],"hf_likes":2731,"hf_downloads":496024,"hf_downloads_all_time":10779619,"hf_trending_score":1.5,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-3-70b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":71,"min_output_per_1m":0.2,"max_output_per_1m":71,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":20},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-1-8b-instruct","name":"llama-3-1-8b-instruct","display_name":"Llama 3.1 8B Instruct","description":"Meta's 8B instruction-tuned LLM optimized for fast, cost-effective deployment across multiple cloud regions with strong instruction-following performance.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":8,"modalities":{"input":["image","text"],"output":["text"]},"context_window":200000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama3","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":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":21,"ids":["@cf/meta/llama-3.1-8b-instruct","accounts/fireworks/models/full-llama-v3p1-8b-instruct-8b-fp8","accounts/fireworks/models/full-llama-v3p1-8b-instruct-8b-fp8-amd","accounts/fireworks/models/llama-v3p1-8b-instruct","azure_ai/Meta-Llama-3.1-8B-Instruct","databricks/databricks-meta-llama-3-1-8b-instruct","deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct","friendliai/meta-llama-3.1-8b-instruct","groq/llama-3.1-8b-instant","hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct","lambda_ai/llama3.1-8b-instruct","llama-3-1-instruct-8b","meta-llama-3-1-8b-instruct","meta-llama/llama-3.1-8b-instruct","meta-llama/Meta-Llama-3.1-8B-Instruct","meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","meta-textgeneration-llama-3-1-8b-instruct","meta-textgenerationneuron-llama-3-1-8b-instruct","meta.llama3-1-8b-instruct-v1:0","meta.llama3-1-8b-instruct-v1:0:128k","nebius/meta-llama/Meta-Llama-3.1-8B-Instruct","novita/meta-llama/llama-3.1-8b-instruct","nscale/meta-llama/Llama-3.1-8B-Instruct","oci/meta.llama-3.1-8b-instruct","ovhcloud/Llama-3.1-8B-Instruct","perplexity/llama-3.1-8b-instruct","sambanova/Meta-Llama-3.1-8B-Instruct","together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","us.meta.llama3-1-8b-instruct-v1:0","vertex_ai/meta/llama-3.1-8b-instruct-maas","wandb/meta-llama/Llama-3.1-8B-Instruct"],"hf_likes":5731,"hf_downloads":9306502,"hf_downloads_all_time":140394735,"hf_trending_score":24,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-1-8b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.02,"max_input_per_1m":22,"min_output_per_1m":0.03,"max_output_per_1m":22,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","nebius","novita","openrouter"],"provider_count":21},"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":"2026-06-13 08:02:30","pricing":{"model_id":"google-gemma-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":false,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2025-10-29","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":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-20b-safeguard","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":"moonshot-kimi-k2-instruct","name":"kimi-k2-instruct","display_name":"Kimi K2 Instruct","description":"The instruction-tuned version of Kimi K2, a 1T-parameter MoE LLM optimized for following user instructions and agentic tool-use tasks.","creator":"moonshot","family":"deepseek_v3","tier":"","version":"k2","type":"language","size_in_bn":1026.471,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":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":9,"ids":["accounts/fireworks/models/kimi-k2-instruct","accounts/fireworks/models/kimi-k2-instruct-0905","baseten/moonshotai/Kimi-K2-Instruct-0905","deepinfra/moonshotai/Kimi-K2-Instruct","deepinfra/moonshotai/Kimi-K2-Instruct-0905","fireworks_ai/accounts/fireworks/models/kimi-k2-instruct","fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905","groq/moonshotai/kimi-k2-instruct-0905","hyperbolic/moonshotai/Kimi-K2-Instruct","moonshot-kimi-k2-instruct","moonshotai/kimi-k2-instruct","novita/moonshotai/kimi-k2-instruct","together_ai/moonshotai/Kimi-K2-Instruct","together_ai/moonshotai/Kimi-K2-Instruct-0905","wandb/moonshotai/Kimi-K2-Instruct"],"hf_likes":2352,"hf_downloads":276135,"hf_downloads_all_time":2074036,"hf_trending_score":2,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"moonshot-kimi-k2-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":2,"min_output_per_1m":2,"max_output_per_1m":3,"min_cache_read_per_1m":0.4,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-4-17b-maverick-instruct","name":"llama-4-17b-maverick-instruct","display_name":"Llama 4 17B Maverick Instruct","description":"Meta's Llama 4 Maverick instruction-tuned MoE model with 17B active parameters, delivering high-performance multimodal text and image understanding.","creator":"meta","family":"llama","tier":"","version":"4","type":"language","size_in_bn":17,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08","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":9,"ids":["azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8","deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","groq/meta-llama/llama-4-maverick-17b-128e-instruct","lambda_ai/llama-4-maverick-17b-128e-instruct-fp8","llama-4-maverick-17b-128e-instruct-maas","meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8","meta-llama-4-17b-maverick-instruct","meta-llama/llama-4-maverick-17b-128e-instruct-fp8","meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","publishers/google/models/llama-4-maverick-17b-128e-instruct-maas","publishers/meta/models/llama-4-maverick-17b-128e-instruct-maas","sambanova/Llama-4-Maverick-17B-128E-Instruct","together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas","vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas"],"hf_likes":163,"hf_downloads":93997,"hf_downloads_all_time":1156723,"hf_trending_score":0,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-4-17b-maverick-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":1.41,"min_output_per_1m":0.1,"max_output_per_1m":1.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-4-17b-scout-instruct","name":"llama-4-17b-scout-instruct","display_name":"Llama 4 17B Scout Instruct","description":"Meta's Llama 4 Scout instruction-tuned MoE model with 17B active parameters, optimized for efficient multimodal inference with a lean expert configuration.","creator":"meta","family":"llama","tier":"","version":"4","type":"language","size_in_bn":17,"modalities":{"input":["image","text"],"output":["text"]},"context_window":10000000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08","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":12,"ids":["@cf/meta/llama-4-scout-17b-16e-instruct","azure_ai/Llama-4-Scout-17B-16E-Instruct","deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","groq/meta-llama/llama-4-scout-17b-16e-instruct","lambda_ai/llama-4-scout-17b-16e-instruct","llama-4-scout-17b-16e-instruct-maas","meta-llama-4-17b-scout-instruct","meta-llama/llama-4-scout-17b-16e-instruct","meta-llama/Llama-4-Scout-17B-16E-Instruct","novita/meta-llama/llama-4-scout-17b-16e-instruct","nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct","publishers/google/models/llama-4-scout-17b-16e-instruct-maas","sambanova/Llama-4-Scout-17B-16E-Instruct","together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct","vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas","vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas","wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct"],"hf_likes":1272,"hf_downloads":390765,"hf_downloads_all_time":5421895,"hf_trending_score":0.5,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-4-17b-scout-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":17,"min_output_per_1m":0.1,"max_output_per_1m":66,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llamaguard-4-12b","name":"llamaguard-4-12b","display_name":"LlamaGuard 4 12B","description":"A natively multimodal 12B safety classifier pruned from Llama 4 Scout, trained jointly on text and multiple images for comprehensive content moderation.","creator":"meta","family":"llama4","tier":"","version":"4","type":"language","size_in_bn":12,"modalities":{"input":["image","text"],"output":["text"]},"context_window":163840,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2025-04-30","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["deepinfra/meta-llama/Llama-Guard-4-12B","groq/meta-llama/llama-guard-4-12b","meta-llama/llama-guard-4-12b","meta-llama/Llama-Guard-4-12B","meta-llamaguard-4-12b"],"hf_likes":90,"hf_downloads":79129,"hf_downloads_all_time":788036,"hf_trending_score":1,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llamaguard-4-12b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.18,"max_input_per_1m":0.2,"min_output_per_1m":0.18,"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":["deepinfra","openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"playai-tts","name":"playai-tts","display_name":"PlayAI TTS","description":"A text-to-speech model from PlayAI offering natural-sounding voice synthesis for a range of conversational and content applications.","creator":"playai","family":"tts","tier":"","version":null,"type":"text-to-speech","size_in_bn":null,"modalities":{"input":["text"],"output":["audio"]},"context_window":10000,"max_output_tokens":10000,"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/playai-tts","playai-tts"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30"},{"id":"alibaba-qwen3-32b","name":"qwen3-32b","display_name":"Qwen3 32B","description":"A dense 32B-parameter LLM from the Qwen3 series with strong reasoning and tool-use capabilities, suitable for a wide range of language tasks.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":40960,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","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":"2025-04-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":15,"ids":["accounts/fireworks/models/qwen3-32b","alibaba-qwen3-32b","alibaba/qwen-3-32b","cerebras/qwen-3-32b","deepinfra/Qwen/Qwen3-32B","fireworks_ai/accounts/fireworks/models/qwen3-32b","gradient_ai/alibaba-qwen3-32b","groq/qwen/qwen3-32b","huggingface-reasoning-qwen3-32b","lambda_ai/qwen3-32b-fp8","nebius/Qwen/Qwen3-32B","novita/qwen/qwen3-32b-fp8","ovhcloud/Qwen3-32B","qwen.qwen3-32b-v1:0","qwen/qwen3-32b","Qwen/Qwen3-32B","qwen/qwen3-32b-fp8","qwen3-32b","qwen3-32b-instruct","qwen3-32b-instruct-reasoning","sambanova/Qwen3-32B","vercel_ai_gateway/alibaba/qwen-3-32b"],"hf_likes":685,"hf_downloads":2337650,"hf_downloads_all_time":26634596,"hf_trending_score":4,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen3-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.9,"min_output_per_1m":0.1,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":15},"providers":[],"regions":[],"region_info":{}}},{"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"],"hf_likes":5689,"hf_downloads":4962521,"hf_downloads_all_time":123200164,"hf_trending_score":21,"updated_at":"2026-06-13 08:02:30"},{"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":"2026-06-13 08:02:30"}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":14},"meta":{"updated_at":"2026-06-13","request_id":"116f934b-0f11-44eb-bc6c-7cb920e0c0a1","execution_ms":19}}