{"data":[{"id":"anthropic-claude-5-opus","name":"claude-5-opus","display_name":"Claude Opus 5","description":"Anthropic's flagship Opus-tier LLM in the Claude 5 generation, supporting tool use, vision, reasoning, web search, and explicit caching for demanding agentic workflows.","creator":"anthropic","family":"claude","tier":"opus","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-05","training_data_cutoff":"2026-05","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-07-24","earliest_deprecation_date":"2027-01-24","deprecated":false,"has_pricing":true,"provider_count":11,"ids":["aihubmix/claude-opus-5","anthropic-claude-5-opus","anthropic.claude-opus-5","anthropic/claude-opus-5","anthropic/claude-opus-5:batch","apac.anthropic.claude-opus-5","au.anthropic.claude-opus-5","azure_ai/claude-opus-5","bedrock/us-gov-east-1/anthropic.claude-opus-5","bedrock/us-gov-west-1/anthropic.claude-opus-5","claude-opus-5","claude-opus-5-high","claude-opus-5-low","claude-opus-5-medium","claude-opus-5-xhigh","databricks/databricks-claude-opus-5","deepinfra/anthropic/claude-opus-5","eu.anthropic.claude-opus-5","github_copilot/claude-opus-5","global.anthropic.claude-opus-5","jp.anthropic.claude-opus-5","openrouter/anthropic/claude-opus-5","openrouter/anthropic/claude-opus-5:batch","perplexity/anthropic/claude-opus-5","publishers/google/models/claude-opus-5","us-gov.anthropic.claude-opus-5","us.anthropic.claude-opus-5","vertex_ai/claude-opus-5","vertex_ai/claude-opus-5@default"],"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":"anthropic-claude-5-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":5,"max_input_per_1m":6,"min_output_per_1m":25,"max_output_per_1m":30,"min_cache_read_per_1m":0.5,"min_cache_write_per_1m":6.25,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","azure_aifoundry","deepinfra","google_vertex_ai","openrouter","other/aihubmix","perplexity","vercel_ai_gateway"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-5-fable","name":"claude-5-fable","display_name":"Claude Fable 5","description":"A highly capable Claude LLM optimized for demanding reasoning and long-horizon agentic tasks, with vision, tool-use, and explicit-caching support.","creator":"anthropic","family":"claude","tier":"fable","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-06-09","earliest_deprecation_date":"2027-06-08","deprecated":false,"has_pricing":true,"provider_count":11,"ids":["aihubmix/claude-fable-5","anthropic-claude-5-fable","anthropic.claude-fable-5","anthropic/claude-fable-5","anthropic/claude-fable-5:batch","apac.anthropic.claude-fable-5","au.anthropic.claude-fable-5","azure_ai/claude-fable-5","claude-fable-5","claude-fable-5-opus-5-fallback","databricks/databricks-claude-fable-5","deepinfra/anthropic/claude-fable-5","eu.anthropic.claude-fable-5","github_copilot/claude-fable-5","global.anthropic.claude-fable-5","openrouter/anthropic/claude-fable-5","openrouter/anthropic/claude-fable-5:batch","perplexity/anthropic/claude-fable-5","publishers/anthropic/models/claude-fable-5","publishers/google/models/claude-fable-5","us.anthropic.claude-fable-5","vertex_ai/claude-fable-5","vertex_ai/claude-fable-5@default"],"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":"anthropic-claude-5-fable","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":10,"max_input_per_1m":12,"min_output_per_1m":50,"max_output_per_1m":60,"min_cache_read_per_1m":1,"min_cache_write_per_1m":12.5,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","azure_aifoundry","deepinfra","google_vertex_ai","openrouter","perplexity","vercel_ai_gateway"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-8-max","name":"qwen3-8-max","display_name":"Qwen3.8 Max","description":"A massive 2.4T-parameter MoE flagship LLM optimized for coding, knowledge work, and autonomous multi-day programming tasks with native visual understanding.","creator":"alibaba","family":"qwen","tier":"max","version":null,"type":"language","size_in_bn":null,"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":"2026-09-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3p8-max","aihubmix/qwen3.8-max","alibaba-qwen3-8-max","alibaba/qwen3.8-max","alibaba/qwen3.8-max-0902","dashscope/qwen3.8-max","deepinfra/Qwen/Qwen3.8-Max","fireworks_ai/accounts/fireworks/models/qwen3p8-max","fireworks_ai/qwen3p8-max","novita/qwen/qwen3.8-max","openrouter/qwen/qwen3.8-max","openrouter/qwen/qwen3.8-max-0902","qwen_ai_platform/qwen3.8-max","qwen/qwen3.8-max","Qwen/Qwen3.8-Max","qwen/qwen3.8-max-0902","qwen3-8-max","qwen3-8-max-0803","qwen3.8-max","qwen3.8-max-0902","qwencloud/qwen3.8-max","scx-ai/Qwen3.8-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-qwen3-8-max","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1.65,"max_input_per_1m":2,"min_output_per_1m":4.951,"max_output_per_1m":6,"min_cache_read_per_1m":0.169,"min_cache_write_per_1m":2.1125,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","other/scx-ai"],"provider_count":10},"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":"anthropic-claude-4-8-opus","name":"claude-4-8-opus","display_name":"Claude Opus 4.8","description":"A flagship Anthropic LLM in the Claude Opus tier at version 4.8, supporting adaptive reasoning, vision, tool use, file input, and web search across multiple geographic regions.","creator":"anthropic","family":"claude","tier":"opus","version":"4-8","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-05-28","earliest_deprecation_date":"2027-05-28","deprecated":false,"has_pricing":true,"provider_count":10,"ids":["anthropic-claude-4-8-opus","anthropic.claude-opus-4-8","anthropic/claude-opus-4-8","anthropic/claude-opus-4.8","anthropic/claude-opus-4.8:batch","apac.anthropic.claude-opus-4-8","au.anthropic.claude-opus-4-8","azure_ai/claude-opus-4-8","bedrock/us-gov-east-1/anthropic.claude-opus-4-8","bedrock/us-gov-west-1/anthropic.claude-opus-4-8","claude-opus-4-8","databricks/databricks-claude-opus-4-8","deepinfra/anthropic/claude-opus-4-8","eu.anthropic.claude-opus-4-8","github_copilot/claude-opus-4.8","github_copilot/claude-opus-4.8-fast","global.anthropic.claude-opus-4-8","jp.anthropic.claude-opus-4-8","openrouter/anthropic/claude-opus-4.8","openrouter/anthropic/claude-opus-4.8:batch","perplexity/anthropic/claude-opus-4-8","publishers/anthropic/models/claude-opus-4-8","publishers/google/models/claude-opus-4-8","us-gov.anthropic.claude-opus-4-8","us.anthropic.claude-opus-4-8","vertex_ai/claude-opus-4-8","vertex_ai/claude-opus-4-8@default"],"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":"anthropic-claude-4-8-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":5,"max_input_per_1m":6,"min_output_per_1m":25,"max_output_per_1m":30,"min_cache_read_per_1m":0.5,"min_cache_write_per_1m":6.25,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","azure_aifoundry","deepinfra","google_vertex_ai","openrouter","perplexity","vercel_ai_gateway"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-7-opus","name":"claude-4-7-opus","display_name":"Claude Opus 4.7","description":"Anthropic's Claude 4.7 Opus model with adaptive reasoning at maximum effort, vision, and tool-use for complex enterprise tasks.","creator":"anthropic","family":"claude","tier":"opus","version":"4-7","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":346,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","minimal","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-04-16","earliest_deprecation_date":"2027-04-06","deprecated":false,"has_pricing":true,"provider_count":10,"ids":["anthropic-claude-4-7-opus","anthropic.claude-opus-4-7","anthropic/claude-opus-4-7","anthropic/claude-opus-4.7","anthropic/claude-opus-4.7:batch","apac.anthropic.claude-opus-4-7","au.anthropic.claude-opus-4-7","azure_ai/claude-opus-4-7","claude-opus-4-7","claude-opus-4-7-20260416","claude-opus-4-7-non-reasoning","databricks/databricks-claude-opus-4-7","deepinfra/anthropic/claude-opus-4-7","eu.anthropic.claude-opus-4-7","global.anthropic.claude-opus-4-7","jp.anthropic.claude-opus-4-7","openrouter/anthropic/claude-opus-4.7","openrouter/anthropic/claude-opus-4.7:batch","perplexity/anthropic/claude-opus-4-7","publishers/anthropic/models/claude-opus-4-7","publishers/google/models/claude-opus-4-7","us.anthropic.claude-opus-4-7","vertex_ai/claude-opus-4-7","vertex_ai/claude-opus-4-7@default"],"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":"anthropic-claude-4-7-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":5,"max_input_per_1m":6,"min_output_per_1m":25,"max_output_per_1m":30,"min_cache_read_per_1m":0.5,"min_cache_write_per_1m":6.25,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","azure_aifoundry","deepinfra","google_vertex_ai","openrouter","perplexity","vercel_ai_gateway"],"provider_count":10},"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":"google-gemini-3-7-flash","name":"gemini-3-7-flash","display_name":"Gemini 3.7 Flash","description":"A fast, efficient Gemini model at the 3.7 generation with multimodal capabilities including vision, tool use, and web search.","creator":"google","family":"gemini","tier":"flash","version":"3-7","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"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":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-13","earliest_deprecation_date":"2027-01-28","deprecated":false,"has_pricing":true,"provider_count":8,"ids":["aihubmix/gemini-3.7-flash","databricks/databricks-gemini-3-7-flash","deepinfra/google/gemini-3.7-flash","gemini-3-7-flash","gemini-3-7-flash-low","gemini-3-7-flash-medium","gemini-3.7-flash","gemini/gemini-3.7-flash","github_copilot/gemini-3.7-flash","google-gemini-3-7-flash","google/gemini-3.7-flash","google/gemini-3.7-flash:batch","openrouter/google/gemini-3.7-flash","openrouter/google/gemini-3.7-flash:batch","perplexity/google/gemini-3.7-flash","publishers/google/models/gemini-3.7-flash","vertex_ai/gemini-3.7-flash"],"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":"google-gemini-3-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.75,"max_input_per_1m":0.9,"min_output_per_1m":3.75,"max_output_per_1m":4.5,"min_cache_read_per_1m":0.075,"min_cache_write_per_1m":0.0416666667,"min_reasoning_per_1m":3.75,"cheapest_providers":["deepinfra","google_gemini","google_vertex_ai","openrouter","other/aihubmix","perplexity","vercel_ai_gateway"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-5-sonnet","name":"claude-5-sonnet","display_name":"Claude Sonnet 5","description":"A flagship-tier LLM from Anthropic featuring adaptive reasoning, vision, tool use, and web search capabilities for complex, multi-step tasks.","creator":"anthropic","family":"claude","tier":"sonnet","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2026-01","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","xhigh"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-06-30","earliest_deprecation_date":"2026-12-24","deprecated":false,"has_pricing":true,"provider_count":11,"ids":["aihubmix/claude-sonnet-5","anthropic-claude-5-sonnet","anthropic.claude-sonnet-5","anthropic/claude-sonnet-5","anthropic/claude-sonnet-5:batch","apac.anthropic.claude-sonnet-5","au.anthropic.claude-sonnet-5","azure_ai/claude-sonnet-5","bedrock/us-gov-east-1/anthropic.claude-sonnet-5","bedrock/us-gov-west-1/anthropic.claude-sonnet-5","claude-sonnet-5","claude-sonnet-5-high","claude-sonnet-5-low","claude-sonnet-5-medium","claude-sonnet-5-non-reasoning","claude-sonnet-5-xhigh","databricks/databricks-claude-sonnet-5","deepinfra/anthropic/claude-sonnet-5","eu.anthropic.claude-sonnet-5","github_copilot/claude-sonnet-5","global.anthropic.claude-sonnet-5","jp.anthropic.claude-sonnet-5","openrouter/anthropic/claude-sonnet-5","openrouter/anthropic/claude-sonnet-5:batch","perplexity/anthropic/claude-sonnet-5","publishers/google/models/claude-sonnet-5","us-gov.anthropic.claude-sonnet-5","us.anthropic.claude-sonnet-5","vertex_ai/claude-sonnet-5","vertex_ai/claude-sonnet-5@default"],"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":"anthropic-claude-5-sonnet","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":2.99999,"min_output_per_1m":10,"max_output_per_1m":15.00002,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":2.5,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","azure_aifoundry","deepinfra","google_vertex_ai","openrouter","other/aihubmix","perplexity","vercel_ai_gateway"],"provider_count":11},"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":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":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-8-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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-gemini-3-5-flash","name":"gemini-3-5-flash","display_name":"Gemini 3.5 Flash","description":"A fast, efficient Gemini 3.5 model optimized for high-throughput tasks with support for reasoning, vision, tool use, and web search.","creator":"google","family":"gemini","tier":"flash","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-01-01","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-19","earliest_deprecation_date":"2027-05-19","deprecated":false,"has_pricing":true,"provider_count":8,"ids":["databricks/databricks-gemini-3-5-flash","deepinfra/google/gemini-3.5-flash","gemini-3-5-flash","gemini-3-5-flash-medium","gemini-3-5-flash-minimal","gemini-3.5-flash","gemini/gemini-3.5-flash","google-gemini-3-5-flash","google/gemini-3.5-flash","google/gemini-3.5-flash:batch","openrouter/google/gemini-3.5-flash","openrouter/google/gemini-3.5-flash:batch","perplexity/google/gemini-3.5-flash","publishers/google/models/gemini-3.5-flash","vertex_ai/gemini-3.5-flash"],"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":"google-gemini-3-5-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.75,"max_input_per_1m":1.87502,"min_output_per_1m":4.5,"max_output_per_1m":11.24998,"min_cache_read_per_1m":0.075,"min_cache_write_per_1m":0.0833333333,"min_reasoning_per_1m":9,"cheapest_providers":["google_vertex_ai"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-6-sonnet","name":"claude-4-6-sonnet","display_name":"Claude Sonnet 4.6","description":"A capable Claude 4.6 Sonnet model with reasoning, vision, and tool-use support for a wide range of applications.","creator":"anthropic","family":"claude","tier":"sonnet","version":"4-6","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":346,"output_vector_sizes":[],"knowledge_cutoff":"2025-08","training_data_cutoff":"2026-01","supported_reasoning_efforts":["default","minimal"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":true},"release_date":"2026-02-17","earliest_deprecation_date":"2027-02-10","deprecated":false,"has_pricing":true,"provider_count":10,"ids":["anthropic-claude-4-6-sonnet","anthropic.claude-sonnet-4-6","anthropic/claude-sonnet-4-6","anthropic/claude-sonnet-4.6","anthropic/claude-sonnet-4.6:batch","apac.anthropic.claude-sonnet-4-6","au.anthropic.claude-sonnet-4-6","azure_ai/claude-sonnet-4-6","claude-sonnet-4-6","claude-sonnet-4-6-adaptive","claude-sonnet-4-6-non-reasoning-low-effort","databricks/databricks-claude-sonnet-4-6","deepinfra/anthropic/claude-sonnet-4-6","eu.anthropic.claude-sonnet-4-6","global.anthropic.claude-sonnet-4-6","jp.anthropic.claude-sonnet-4-6","openrouter/anthropic/claude-sonnet-4.6","openrouter/anthropic/claude-sonnet-4.6:batch","perplexity/anthropic/claude-sonnet-4-6","publishers/anthropic/models/claude-sonnet-4-6","publishers/google/models/claude-sonnet-4-6","snowflake/claude-sonnet-4-6","us.anthropic.claude-sonnet-4-6","vertex_ai/claude-sonnet-4-6","vertex_ai/claude-sonnet-4-6@default"],"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":"anthropic-claude-4-6-sonnet","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":2.99999,"max_input_per_1m":3.6,"min_output_per_1m":15,"max_output_per_1m":18,"min_cache_read_per_1m":0.3,"min_cache_write_per_1m":3.74997,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":10},"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":"xiaomi-mimo-2-5-pro","name":"mimo-2-5-pro","display_name":"MiMo V2.5 Pro","description":"Xiaomi's flagship omnimodal LLM excelling in general agentic tasks, complex software engineering, and long-horizon reasoning benchmarks.","creator":"xiaomi","family":"mimo","tier":"","version":"2-5","type":"language","size_in_bn":1023.245,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1050000,"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":"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":"2026-04-22","earliest_deprecation_date":"2026-10-21","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["deepinfra/XiaomiMiMo/MiMo-V2.5-Pro","mimo-v2-5-pro","mimo-v2-5-pro-non-reasoning","novita/xiaomimimo/mimo-v2.5-pro","openrouter/xiaomi/mimo-v2.5-pro","xiaomi-mimo-2-5-pro","xiaomi/mimo-v2.5-pro","xiaomimimo/mimo-v2.5-pro","XiaomiMiMo/MiMo-V2.5-Pro"],"hf_likes":653,"hf_downloads":66027,"hf_downloads_all_time":128095,"hf_trending_score":34,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"xiaomi-mimo-2-5-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.435,"max_input_per_1m":1,"min_output_per_1m":0.87,"max_output_per_1m":3,"min_cache_read_per_1m":0.0036,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"tencent-hy-3","name":"hy-3","display_name":"Hy 3","description":"A preview-stage Hunyuan-series LLM from Tencent, identified by the compact 'Hy3' designation and targeting general-purpose text generation.","creator":"tencent","family":"hy","tier":"","version":"3","type":"language","size_in_bn":298.786,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":128000,"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":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":"2026-07-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["aihubmix/hy3","deepinfra/tencent/Hy3","hy3","novita/tencent/hy3","openrouter/tencent/hy3","tencent-hy-3","tencent/hy3","tencent/Hy3"],"hf_likes":860,"hf_downloads":14143,"hf_downloads_all_time":14143,"hf_trending_score":49,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"tencent-hy-3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.132,"max_input_per_1m":0.1562,"min_output_per_1m":0.528,"max_output_per_1m":0.6248,"min_cache_read_per_1m":0.033,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":5},"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-qwen3-5-27b","name":"qwen3-5-27b","display_name":"Qwen3.5 27B","description":"A 27B-parameter dense LLM from the Qwen3.5 series, offering strong general-purpose text generation and reasoning capabilities.","creator":"alibaba","family":"qwen3_5","tier":"","version":null,"type":"language","size_in_bn":27,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":81920,"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":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":"2026-02-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/qwen3p5-27b","alibaba-qwen3-5-27b","deepinfra/Qwen/Qwen3.5-27B","huggingface-vlm-qwen3-5-27b","novita/qwen/qwen3.5-27b","openrouter/qwen/qwen3.5-27b","qwen/qwen3.5-27b","Qwen/Qwen3.5-27B","qwen3-5-27b","qwen3-5-27b-non-reasoning","qwen3.5-27b"],"hf_likes":951,"hf_downloads":3247187,"hf_downloads_all_time":5302164,"hf_trending_score":27,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-5-27b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.26,"max_input_per_1m":0.3,"min_output_per_1m":2.4,"max_output_per_1m":2.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","openrouter"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"inclusionai-ling-3-flash","name":"ling-3-flash","display_name":"InclusionAI Ling 3 Flash","description":"A 124B-parameter Mixture-of-Experts LLM with ~5.1B active parameters per token, optimized for token-efficient inference with reasoning and tool-use capabilities.","creator":"inclusionai","family":"bailing_hybrid","tier":"flash","version":"3","type":"language","size_in_bn":127.486,"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":["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":"2026-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/ling-3-flash","deepinfra/inclusionAI/Ling-3.0-flash","inclusionai-ling-3-flash","inclusionai/ling-3.0-flash","inclusionAI/Ling-3.0-flash","inclusionai/ling-3.0-flash-free","inclusionai/ling-3.0-flash:free","ling-3-0-flash","novita/inclusionai/ling-3.0-flash","openrouter/inclusionai/ling-3.0-flash"],"hf_likes":359,"hf_downloads":17020,"hf_downloads_all_time":17029,"hf_trending_score":23,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"inclusionai-ling-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":0.021,"max_input_per_1m":0.06,"min_output_per_1m":0.063,"max_output_per_1m":0.18,"min_cache_read_per_1m":0.0042,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"step-3-7-flash","name":"step-3-7-flash","display_name":"Step 3.7 Flash","description":"A high-efficiency multimodal Mixture-of-Experts LLM combining a large language backbone with a vision encoder for native image and video understanding.","creator":"step","family":"step","tier":"flash","version":"3-7","type":"language","size_in_bn":201.365,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":256000,"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":"2026-05-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["aihubmix/step-3.7-flash","deepinfra/stepfun-ai/Step-3.7-Flash","novita/stepfun/step-3.7-flash","openrouter/stepfun/step-3.7-flash","step-3-7-flash","stepfun-ai/Step-3.7-Flash","stepfun/step-3.7-flash"],"hf_likes":370,"hf_downloads":50187,"hf_downloads_all_time":50187,"hf_trending_score":51,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"step-3-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.22,"min_output_per_1m":1.15,"max_output_per_1m":1.32,"min_cache_read_per_1m":0.04,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","openrouter","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-6-35b-a3b","name":"qwen3-6-35b-a3b","display_name":"Qwen3.6 35B A3B","description":"Alibaba's flagship Qwen3.6 MoE model with 35B total parameters and 3B activated per token, built with 256 experts and direct community feedback integration.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":35,"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":"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":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-04-27","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":11,"ids":["accounts/fireworks/models/qwen3p6-35b-a3b","aihubmix/qwen3.6-35b-a3b","alibaba-qwen3-6-35b-a3b","deepinfra/Qwen/Qwen3.6-35B-A3B","huggingface-vlm-qwen3-6-35b-a3b","libertai/qwen3.6-35b-a3b","novita/qwen/qwen3.6-35b-a3b","openrouter/qwen/qwen3.6-35b-a3b","pinstripes/ps/qwen3.6-35b-a3b","qwen/qwen3.6-35b-a3b","Qwen/Qwen3.6-35B-A3B","qwen3-6-35b-a3b","qwen3-6-35b-a3b-non-reasoning","qwen3.6-35b-a3b","sail/Qwen/Qwen3.6-35B-A3B","scaleway/qwen/qwen3.6-35b-a3b","wandb/Qwen/Qwen3.6-35B-A3B"],"hf_likes":1495,"hf_downloads":1510129,"hf_downloads_all_time":1510129,"hf_trending_score":292,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-6-35b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.375,"min_output_per_1m":0.4,"max_output_per_1m":2.25,"min_cache_read_per_1m":0.02,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/sail"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-122b-a10b","name":"qwen3-5-122b-a10b","display_name":"Qwen3.5 122B A10B","description":"A large Qwen3.5 Mixture-of-Experts model with 122B total parameters and 10B activated per token, featuring a 262K token context window for complex reasoning tasks.","creator":"alibaba","family":"qwen3_5_moe","tier":"","version":null,"type":"language","size_in_bn":122,"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":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":true,"adaptive_reasoning":false},"release_date":"2026-02-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/qwen3p5-122b-a10b","aihubmix/qwen3.5-122b-a10b","alibaba-qwen3-5-122b-a10b","databricks/databricks-qwen35-122b-a10b","deepinfra/Qwen/Qwen3.5-122B-A10B","huggingface-llm-qwen3-5-122b-a10b","libertai/qwen3.5-122b-a10b","novita/qwen/qwen3.5-122b-a10b","openrouter/qwen/qwen3.5-122b-a10b","qwen/qwen3.5-122b-a10b","Qwen/Qwen3.5-122B-A10B","qwen3-5-122b-a10b","qwen3-5-122b-a10b-non-reasoning","qwen3.5-122b-a10b"],"hf_likes":523,"hf_downloads":906547,"hf_downloads_all_time":1516880,"hf_trending_score":8,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-5-122b-a10b","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":0.4,"min_output_per_1m":0.9008,"max_output_per_1m":3.2,"min_cache_read_per_1m":0.22001,"min_cache_write_per_1m":0.22001,"min_reasoning_per_1m":null,"cheapest_providers":["other/aihubmix"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-5-haiku","name":"claude-4-5-haiku","display_name":"Claude Haiku 4.5","description":"A fast, lightweight Claude 4.5 model with vision, file input, and tool-use support optimized for low-latency applications.","creator":"anthropic","family":"claude","tier":"haiku","version":"4-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":200000,"max_output_tokens":64000,"tool_use_system_prompt_tokens":346,"output_vector_sizes":[],"knowledge_cutoff":"2025-02","training_data_cutoff":"2025-07","supported_reasoning_efforts":["default"],"tokenizer":"Claude","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-10-15","earliest_deprecation_date":"2026-10-15","deprecated":false,"has_pricing":true,"provider_count":13,"ids":["aihubmix/claude-haiku-4-5","anthropic-claude-4-5-haiku","anthropic.claude-haiku-4-5-20251001-v1:0","anthropic.claude-haiku-4-5@20251001","anthropic/claude-haiku-4-5","anthropic/claude-haiku-4.5","anthropic/claude-haiku-4.5:batch","apac.anthropic.claude-haiku-4-5-20251001-v1:0","au.anthropic.claude-haiku-4-5-20251001-v1:0","azure_ai/claude-haiku-4-5","bedrock_mantle/anthropic.claude-haiku-4-5","bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0","bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0","claude-4-5-haiku","claude-4-5-haiku-reasoning","claude-haiku-4-5","claude-haiku-4-5-20251001","claude-haiku-4-5@20251001","databricks/databricks-claude-haiku-4-5","deepinfra/anthropic/claude-haiku-4-5","eu.anthropic.claude-haiku-4-5-20251001-v1:0","github_copilot/claude-haiku-4.5","global.anthropic.claude-haiku-4-5-20251001-v1:0","jp.anthropic.claude-haiku-4-5-20251001-v1:0","openrouter/anthropic/claude-haiku-4.5","openrouter/anthropic/claude-haiku-4.5:batch","perplexity/anthropic/claude-haiku-4-5","publishers/anthropic/models/claude-haiku-4-5","publishers/google/models/claude-haiku-4-5","replicate/anthropic/claude-4.5-haiku","snowflake/claude-haiku-4-5","us.anthropic.claude-haiku-4-5-20251001-v1:0","vercel_ai_gateway/anthropic/claude-haiku-4.5","vertex_ai/claude-haiku-4-5","vertex_ai/claude-haiku-4-5@20251001"],"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":"anthropic-claude-4-5-haiku","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":1.2,"min_output_per_1m":5,"max_output_per_1m":6,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":1.24999,"min_reasoning_per_1m":null,"cheapest_providers":["anthropic","azure_aifoundry","deepinfra","github_models","google_vertex_ai","openrouter","perplexity","replicate","vercel_ai_gateway"],"provider_count":13},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-7-flash","name":"glm-4-7-flash","display_name":"GLM-4.7 Flash","description":"A lightweight 30B-A3B MoE model from Z AI that balances strong performance with efficiency, optimized for fast inference and agentic tasks.","creator":"zhipu","family":"glm4_moe_lite","tier":"flash","version":"4-7","type":"language","size_in_bn":31.221,"modalities":{"input":["image","text"],"output":["text"]},"context_window":203000,"max_output_tokens":131000,"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":"2026-01-19","earliest_deprecation_date":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/glm-4p7-flash","cloudflare/@cf/zai-org/glm-4.7-flash","deepinfra/zai-org/GLM-4.7-Flash","glm-4-7-flash","glm-4-7-flash-non-reasoning","novita/zai-org/glm-4.7-flash","openrouter/z-ai/glm-4.7-flash","z-ai/glm-4.7-flash","zai-org/glm-4.7-flash","zai-org/GLM-4.7-Flash","zai.glm-4.7-flash","zai/glm-4.7-flash","zhipu-glm-4-7-flash"],"hf_likes":1708,"hf_downloads":682370,"hf_downloads_all_time":4269790,"hf_trending_score":4,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"zhipu-glm-4-7-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.07,"min_output_per_1m":0.4,"max_output_per_1m":0.4,"min_cache_read_per_1m":0.01,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":5},"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":"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":"2026-10-12 08:02:14","pricing":{"model_id":"nvidia-nemotron-lightning-3-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":"2026-10-12 08:02:14","pricing":{"model_id":"nvidia-nemotron-super-3-120b-a12b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":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-qwen3-vl-235b-a22b-instruct","name":"qwen3-vl-235b-a22b-instruct","display_name":"Qwen3 VL 235B A22B Instruct","description":"The flagship instruction-tuned vision-language MoE model in the Qwen3 series, with 235B total and 22B activated parameters for superior visual perception and reasoning.","creator":"alibaba","family":"qwen3_vl_moe","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":262144,"max_output_tokens":129024,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"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":true,"adaptive_reasoning":false},"release_date":"2025-09-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","alibaba-qwen3-vl-235b-a22b-instruct","alibaba/qwen3-vl-235b-a22b-instruct","bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct","dashscope/qwen3-vl-235b-a22b-instruct","deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct","gmi/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","novita/qwen/qwen3-vl-235b-a22b-instruct","openrouter/qwen/qwen3-vl-235b-a22b-instruct","qwen_ai_platform/qwen3-vl-235b-a22b-instruct","qwen/qwen3-vl-235b-a22b-instruct","Qwen/Qwen3-VL-235B-A22B-Instruct","qwen3-vl-235b-a22b-instruct","qwencloud/qwen3-vl-235b-a22b-instruct"],"hf_likes":383,"hf_downloads":947793,"hf_downloads_all_time":2172030,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-vl-235b-a22b-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":0.53,"min_output_per_1m":0.88,"max_output_per_1m":2.66,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":9},"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":"2026-10-12 08:02:14","pricing":{"model_id":"nvidia-nemotron-nano-3-30b-a3b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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-r1-distill-qwen-32b","name":"deepseek-r1-distill-qwen-32b","display_name":"DeepSeek R1 Distill Qwen 32B","description":"A 32B Qwen-based model distilled from DeepSeek R1's reasoning capabilities, offering high-quality chain-of-thought performance at a mid-scale parameter count.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","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":true,"adaptive_reasoning":false},"release_date":"2025-01-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","accounts/fireworks/models/deepseek-r1-distill-qwen-32b","cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-llm-r1-distill-qwen-32b","deepseek-r1-distill-qwen-32b","deepseek/deepseek-r1-distill-qwen-32b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","novita/deepseek/deepseek-r1-distill-qwen-32b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"hf_likes":1545,"hf_downloads":1046750,"hf_downloads_all_time":23929632,"hf_trending_score":3,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"deepseek-r1-distill-qwen-32b","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":0.9,"min_output_per_1m":0.15,"max_output_per_1m":4.881,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-vl-30b-a3b-instruct","name":"qwen3-vl-30b-a3b-instruct","display_name":"Qwen3 VL 30B A3B Instruct","description":"An instruction-tuned vision-language MoE model with 30B total and 3B activated parameters, offering strong multimodal understanding and generation capabilities.","creator":"alibaba","family":"qwen3_vl_moe","tier":"","version":null,"type":"language","size_in_bn":30,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","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":"2025-10-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","alibaba-qwen3-vl-30b-a3b-instruct","deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-vl-30b-a3b-instruct","novita/qwen/qwen3-vl-30b-a3b-instruct","openrouter/qwen/qwen3-vl-30b-a3b-instruct","qwen/qwen3-vl-30b-a3b-instruct","Qwen/Qwen3-VL-30B-A3B-Instruct","qwen3-vl-30b-a3b-instruct"],"hf_likes":562,"hf_downloads":2219395,"hf_downloads_all_time":14070852,"hf_trending_score":2,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"alibaba-qwen3-vl-30b-a3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.2,"min_output_per_1m":0.6,"max_output_per_1m":0.7,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","fireworks_ai","openrouter"],"provider_count":5},"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":"nousresearch-hermes-3-llama-3-1-70b","name":"hermes-3-llama-3-1-70b","display_name":"Hermes 3 Llama 3.1 70B","description":"A 70B-parameter Llama 3.1-based LLM from Nous Research with Hermes 3 fine-tuning for improved agentic capabilities and long-context coherence.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"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":"2024-08-18","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","hermes-3-llama-3-1-70b","hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B","nousresearch-hermes-3-llama-3-1-70b","nousresearch/hermes-3-llama-3.1-70b","NousResearch/Hermes-3-Llama-3.1-70B","openrouter/nousresearch/hermes-3-llama-3.1-70b"],"hf_likes":123,"hf_downloads":2494,"hf_downloads_all_time":179146,"hf_trending_score":1,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"nousresearch-hermes-3-llama-3-1-70b","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":0.7,"min_output_per_1m":0.3,"max_output_per_1m":0.7,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"microsoft-phi-4","name":"phi-4","display_name":"Phi-4","description":"A small language model from Microsoft trained on high-quality synthetic and curated datasets, excelling at reasoning and STEM tasks despite its compact size.","creator":"microsoft","family":"phi","tier":"","version":"4","type":"language","size_in_bn":14.66,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":"Other","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":"2025-01-10","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure_ai/Phi-4","deepinfra/microsoft/phi-4","microsoft-phi-4","microsoft/phi-4","openrouter/microsoft/phi-4","phi-4","phi-4-mini","phi-4-multimodal","publishers/microsoft/models/phi4"],"hf_likes":2248,"hf_downloads":874552,"hf_downloads_all_time":11669853,"hf_trending_score":4,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"microsoft-phi-4","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.07,"min_output_per_1m":0.14,"max_output_per_1m":0.14,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","openrouter"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-528-turbo","name":"deepseek-r1-528-turbo","display_name":"DeepSeek R1 528 Turbo","description":"A turbo-speed variant of the DeepSeek R1 0528 reasoning model, optimized for fast inference while retaining strong chain-of-thought performance.","creator":"deepseek","family":"deepseek-r1","tier":"turbo","version":"1.0","type":"language","size_in_bn":null,"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":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":["deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo","deepseek-ai/DeepSeek-R1-0528-Turbo","deepseek-r1-528-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":"deepseek-r1-528-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","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":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-turbo","name":"deepseek-r1-turbo","display_name":"DeepSeek R1 Turbo","description":"A turbo-speed variant of DeepSeek R1 optimized for faster inference while preserving the model's strong mathematical and logical reasoning abilities.","creator":"deepseek","family":"deepseek-r1","tier":"turbo","version":"1.0","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":64000,"max_output_tokens":16000,"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":["deepinfra/deepseek-ai/DeepSeek-R1-Turbo","deepseek-r1-turbo","deepseek/deepseek-r1-turbo","novita/deepseek/deepseek-r1-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":"deepseek-r1-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.7,"max_input_per_1m":1,"min_output_per_1m":2.5,"max_output_per_1m":3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-3-1-flash-lite","name":"gemini-3-1-flash-lite","display_name":"Gemini 3.1 Flash Lite","description":"A lightweight, cost-efficient variant of Gemini 3.1 Flash designed for high-throughput multimodal tasks at minimal latency.","creator":"google","family":"gemini","tier":"flash-lite","version":"3-1","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["text"]},"context_window":1048576,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-01","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":true,"file_search":true,"url_context":true,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-05-07","earliest_deprecation_date":"2027-05-07","deprecated":false,"has_pricing":true,"provider_count":8,"ids":["databricks/databricks-gemini-3-1-flash-lite","deepinfra/google/gemini-3.1-flash-lite","gemini-3.1-flash-lite","gemini/gemini-3.1-flash-lite","google-gemini-3-1-flash-lite","google/gemini-3.1-flash-lite","google/gemini-3.1-flash-lite:batch","openrouter/google/gemini-3.1-flash-lite","openrouter/google/gemini-3.1-flash-lite:batch","perplexity/google/gemini-3.1-flash-lite","publishers/google/models/gemini-3.1-flash-lite","vertex_ai/gemini-3.1-flash-lite"],"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":"google-gemini-3-1-flash-lite","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.125,"max_input_per_1m":0.31248,"min_output_per_1m":0.75,"max_output_per_1m":1.87502,"min_cache_read_per_1m":0.012,"min_cache_write_per_1m":0.0833333333,"min_reasoning_per_1m":1.5,"cheapest_providers":["google_vertex_ai"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-3-1-pro","name":"gemini-3-1-pro","display_name":"Gemini 3.1 Pro","description":"Google's pro-tier LLM in the Gemini 3.1 generation offering high-capability multimodal reasoning, coding, and tool use.","creator":"google","family":"gemini","tier":"pro","version":"3-1","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","text","video"],"output":["text"]},"context_window":1048576,"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":null,"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":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["databricks/databricks-gemini-3-1-pro","deepinfra/google/gemini-3.1-pro","google-gemini-3-1-pro","google/gemini-3.1-pro"],"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":"google-gemini-3-1-pro","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":2.49998,"min_output_per_1m":12,"max_output_per_1m":15.00002,"min_cache_read_per_1m":0.24997,"min_cache_write_per_1m":2.49998,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-12b-instruct","name":"gemma-3-12b-instruct","display_name":"Gemma 3 12B Instruct","description":"An instruction-tuned 12B Gemma 3 LLM supporting vision-language inputs and 128k context.","creator":"google","family":"gemma3_text","tier":"","version":"3","type":"language","size_in_bn":12,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"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":"Gemini","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":"2025-03-13","earliest_deprecation_date":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["@cf/google/gemma-3-12b-it","accounts/fireworks/models/gemma-3-12b-it","crusoe/google/gemma-3-12b-it","deepinfra/google/gemma-3-12b-it","google-gemma-3-12b-instruct","google.gemma-3-12b-it","google/gemma-3-12b-it","google/gemma-3-12b-it:free","novita/google/gemma-3-12b-it","openrouter/google/gemma-3-12b-it"],"hf_likes":707,"hf_downloads":2516014,"hf_downloads_all_time":14080610,"hf_trending_score":2,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-gemma-3-12b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.345,"min_output_per_1m":0.1,"max_output_per_1m":0.556,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-4b-instruct","name":"gemma-3-4b-instruct","display_name":"Gemma 3 4B Instruct","description":"An instruction-tuned 4B Gemma 3 LLM supporting vision-language inputs for efficient multimodal tasks.","creator":"google","family":"gemma3_text","tier":"","version":"3","type":"language","size_in_bn":4,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"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":"Gemini","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":"2025-03-13","earliest_deprecation_date":"2027-03-30","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/gemma-3-4b-it","deepinfra/google/gemma-3-4b-it","google-gemma-3-4b-instruct","google.gemma-3-4b-it","google/gemma-3-4b-it","google/gemma-3-4b-it:free","huggingface-vlm-gemma-3-4b-instruct","lemonade/Gemma-3-4b-it-GGUF","openrouter/google/gemma-3-4b-it"],"hf_likes":1313,"hf_downloads":2130064,"hf_downloads_all_time":17437981,"hf_trending_score":4,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-gemma-3-4b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.05,"min_output_per_1m":0.08,"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":["amazon_bedrock"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-26b-a4b-instruct","name":"gemma-4-26b-a4b-instruct","display_name":"Gemma 4 26B A4B IT","description":"Instruction-tuned MoE variant of Gemma 4 with 26B total and 4B active parameters, supporting vision, tool use, and file input.","creator":"google","family":"gemma4","tier":"","version":"4","type":"language","size_in_bn":26,"modalities":{"input":["image","pdf","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":"Gemma","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":"2026-04-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["@cf/google/gemma-4-26b-a4b-it","accounts/fireworks/models/gemma-4-26b-a4b-it","aihubmix/gemma-4-26b-a4b-it","cloudflare/@cf/google/gemma-4-26b-a4b-it","deepinfra/google/gemma-4-26B-A4B-it","gemini/gemma-4-26b-a4b-it","gemma-4-26b-a4b-it-maas","google-gemma-4-26b-a4b-instruct","google/gemma-4-26b-a4b-it","google/gemma-4-26B-A4B-it","google/gemma-4-26b-a4b-it:free","huggingface-vlm-gemma-4-26b-a4b-it","novita/google/gemma-4-26b-a4b-it","openrouter/google/gemma-4-26b-a4b-it","openrouter/google/gemma-4-26b-a4b-it:free","publishers/google/models/gemma-4-26b-a4b-it-maas","scaleway/google/gemma-4-26b-a4b-it","vertex_ai/gemma-4-26b-a4b-it","vertex_ai/google/gemma-4-26b-a4b-it-maas","wandb/google/gemma-4-26B-A4B-it"],"hf_likes":751,"hf_downloads":3113602,"hf_downloads_all_time":3115675,"hf_trending_score":92,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"google-gemma-4-26b-a4b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.042,"max_input_per_1m":0.285,"min_output_per_1m":0.22,"max_output_per_1m":0.6,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-31b-it-turbo","name":"gemma-4-31b-it-turbo","display_name":"Gemma 4 31B IT Turbo","description":"A 31B instruction-tuned Gemma 4 model with a turbo serving profile for faster throughput in chat and task-completion workloads.","creator":"google","family":"gemma","tier":"","version":"4","type":"language","size_in_bn":31,"modalities":{"input":["image","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":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/google/gemma-4-31B-it-turbo","google-gemma-4-31b-it-turbo","google/gemma-4-31B-it-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":"google-gemma-4-31b-it-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.09,"max_input_per_1m":0.09,"min_output_per_1m":0.34,"max_output_per_1m":0.34,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-e4b-instruct","name":"gemma-4-e4b-instruct","display_name":"Gemma 4 E4B Instruct","description":"An instruction-tuned, efficiency-optimized 4B-class variant of Gemma 4 designed for on-device and resource-constrained deployments.","creator":"google","family":"gemma","tier":"","version":"4","type":"language","size_in_bn":null,"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":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"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":1,"ids":["deepinfra/google/gemma-4-E4B-it","google-gemma-4-e4b-instruct","google/gemma-4-E4B-it","huggingface-vlm-gemma-4-e4b-it"],"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":"google-gemma-4-e4b-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":0.02,"min_output_per_1m":0.1,"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":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-4-ultra-31b-instruct","name":"gemma-4-ultra-31b-instruct","display_name":"Gemma 4 Ultra 31B Instruct","description":"An ultra-speed instruction-tuned variant of the Gemma 4 31B model, optimized for high-throughput inference.","creator":"google","family":"gemma","tier":"ultra","version":"4","type":"language","size_in_bn":31,"modalities":{"input":["image","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":["default"],"tokenizer":null,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/google/gemma-4-31B-it-Ultra","google-gemma-4-ultra-31b-instruct","google/gemma-4-31B-it-Ultra"],"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":"google-gemma-4-ultra-31b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.27,"max_input_per_1m":0.27,"min_output_per_1m":0.76,"max_output_per_1m":0.76,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-120b-turbo","name":"gpt-oss-120b-turbo","display_name":"GPT OSS 120B Turbo","description":"A turbo-speed configuration of the 120B open-weights GPT model optimized for high-throughput reasoning tasks requiring faster inference.","creator":"openai","family":"gpt","tier":"","version":null,"type":"language","size_in_bn":120,"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":["default"],"tokenizer":null,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/openai/gpt-oss-120b-Turbo","openai-gpt-oss-120b-turbo","openai/gpt-oss-120b-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":"openai-gpt-oss-120b-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.15,"min_output_per_1m":0.6,"max_output_per_1m":0.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-ultra-120b","name":"gpt-oss-ultra-120b","display_name":"GPT OSS Ultra 120B","description":"An ultra-fast open-weight 120B LLM variant in the GPT OSS series, optimized for high-speed inference at large scale.","creator":"openai","family":"gpt","tier":"ultra","version":null,"type":"language","size_in_bn":120,"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":["default"],"tokenizer":null,"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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/openai/gpt-oss-120b-Ultra","openai-gpt-oss-ultra-120b","openai/gpt-oss-120b-Ultra"],"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":"openai-gpt-oss-ultra-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.95,"max_output_per_1m":0.95,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"sao10k-l3-lunaris-1-8b-turbo","name":"l3-lunaris-1-8b-turbo","display_name":"L3 Lunaris 1.8B Turbo","description":"A compact 1.8B Llama 3-based generalist and roleplay model from Sao10k, optimized for fast inference in the Lunaris series.","creator":"sao10k","family":"llama","tier":"","version":"1","type":"language","size_in_bn":8,"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":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":["deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","sao10k-l3-lunaris-1-8b-turbo","Sao10K/L3-8B-Lunaris-v1-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":"sao10k-l3-lunaris-1-8b-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.04,"min_output_per_1m":0.05,"max_output_per_1m":0.05,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"sao10k-l3-1-euryale-2-2-70b","name":"l3-1-euryale-2-2-70b","display_name":"L3.1 70B Euryale V2.2","description":"A 70B Llama 3.1-based creative roleplay model from Sao10k, focused on immersive character performance and narrative generation.","creator":"sao10k","family":"llama","tier":"","version":"2-2","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":true,"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":["deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","novita/sao10k/l31-70b-euryale-v2.2","sao10k-l3-1-euryale-2-2-70b","Sao10K/L3.1-70B-Euryale-v2.2","sao10k/l31-70b-euryale-v2.2"],"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":"sao10k-l3-1-euryale-2-2-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.85,"max_input_per_1m":1.48,"min_output_per_1m":0.85,"max_output_per_1m":1.48,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"sao10k-l3-3-euryale-2-3-70b","name":"l3-3-euryale-2-3-70b","display_name":"L3.3 70B Euryale V2.3","description":"A 70B Llama 3.3-based creative roleplay model from Sao10k, representing the latest iteration of the Euryale fine-tune series.","creator":"sao10k","family":"llama","tier":"","version":"2-3","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":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":["deepinfra/Sao10K/L3.3-70B-Euryale-v2.3","sao10k-l3-3-euryale-2-3-70b","Sao10K/L3.3-70B-Euryale-v2.3"],"hf_likes":83,"hf_downloads":50195,"hf_downloads_all_time":70669,"hf_trending_score":0,"updated_at":"2026-10-12 08:02:14","pricing":{"model_id":"sao10k-l3-3-euryale-2-3-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-10-13","ingestion_date":"2026-10-12","summary":{"currency":"USD","min_input_per_1m":0.65,"max_input_per_1m":0.65,"min_output_per_1m":0.75,"max_output_per_1m":0.75,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":66},"meta":{"updated_at":"2026-10-12","request_id":"5d456d37-09d8-4482-a9cb-f932093a1e04","execution_ms":19}}