{"data":[{"id":"alibaba-qwen3-8-27b","name":"qwen3-8-27b","display_name":"Qwen3.8 27B","description":"An open-weight dense vision-language model optimized for coding, professional workflows, research, multimodal interaction, and long-running agent tasks.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":27,"modalities":{"input":["image","pdf","text","video"],"output":["text"]},"context_window":1000000,"max_output_tokens":235929,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-14","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["@cf/qwen/qwen3.8-27b","accounts/fireworks/models/qwen3p8-27b","alibaba-qwen3-8-27b","alibaba/qwen3.8-27b","cerebras/qwen-3.8-27b","deepinfra/Qwen/Qwen3.8-27B","groq/qwen/qwen3.8-27b","huggingface-vlm-qwen3-8-27b","nebius/Qwen/Qwen3.8-27B","openrouter/qwen/qwen3.8-27b","openrouter/qwen/qwen3.8-27b:free","qwen/qwen3.8-27b","Qwen/Qwen3.8-27B","qwen3-8-27b","qwen3-8-27b-low","qwen3-8-27b-medium","qwen3-8-27b-non-reasoning","qwen3.8-27b","wandb/Qwen/Qwen3.8-27B"],"hf_likes":9338,"hf_downloads":2,"hf_downloads_all_time":2,"hf_trending_score":9013,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"alibaba-qwen3-8-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.99,"min_output_per_1m":1.49,"max_output_per_1m":4,"min_cache_read_per_1m":0.0198,"min_cache_write_per_1m":0.625,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-31b","name":"gemma-4-31b","display_name":"Gemma 4 31B","description":"Google DeepMind's 31B-parameter Gemma 4 open multimodal LLM, handling text and image inputs with text output.","creator":"google","family":"gemma","tier":"","version":"4","type":"language","size_in_bn":31,"modalities":{"input":["image","text"],"output":["text"]},"context_window":256000,"max_output_tokens":40960,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":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":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["bedrock_mantle/google.gemma-4-31b","bedrock_mantle/us-gov-west-1/google.gemma-4-31b","cerebras/gemma-4-31b","gemma-4-31b","gemma-4-31b-non-reasoning","google-gemma-4-31b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"google-gemma-4-31b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.14,"max_input_per_1m":0.99,"min_output_per_1m":0.4,"max_output_per_1m":1.49,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock"],"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":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":"2026-10-13 08:04:31","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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":"meta-llama-3-1-70b","name":"meta-llama-3-1-70b","display_name":"Llama 3.1 70B","description":"Meta's 70B pre-trained LLM in the Llama 3.1 series, balancing high capability with practical deployment costs and supporting tool-use tasks.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"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":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":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["cerebras/llama3.1-70b","meta-llama-3-1-70b","meta-textgeneration-llama-3-1-70b","meta-textgenerationneuron-llama-3-1-70b","meta/llama-3.1-70b","snowflake/llama3.1-70b","vercel_ai_gateway/meta/llama-3.1-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"meta-llama-3-1-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.36,"max_input_per_1m":0.72,"min_output_per_1m":0.36,"max_output_per_1m":0.72,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["snowflake"],"provider_count":3},"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":"2026-10-13 08:04:31","pricing":{"model_id":"meta-llama-3-1-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","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","name":"llama-3-3-70b","display_name":"Llama 3.3 70B","description":"Meta's 70B instruction-tuned LLM from the Llama 3.3 series, designed for high-performance conversational AI, content creation, and enterprise applications.","creator":"meta","family":"llama","tier":"","version":"3-3","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"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":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":"2024-12-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["cerebras/llama-3.3-70b","meta-llama-3-3-70b","meta/llama-3.3-70b","snowflake/llama3.3-70b","snowflake/snowflake-llama-3.3-70b","vercel_ai_gateway/meta/llama-3.3-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-13 08:04:31","pricing":{"model_id":"meta-llama-3-3-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-14","ingestion_date":"2026-10-13","summary":{"currency":"USD","min_input_per_1m":0.36,"max_input_per_1m":0.85,"min_output_per_1m":0.36,"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":["snowflake"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":6},"meta":{"updated_at":"2026-10-13","request_id":"8c9560c0-a61c-4285-a1e8-1bf37353dc00","execution_ms":11}}