{"data":[{"id":"openai-gpt-5-1","name":"gpt-5-1","display_name":"GPT-5.1","description":"OpenAI's flagship LLM for coding and agentic tasks with configurable reasoning effort levels, available via the Responses API.","creator":"openai","family":"gpt","tier":"","version":"5-1","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":409600,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-09","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal","none"],"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":"2025-11-13","earliest_deprecation_date":"2027-05-15","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-5.1","azure/global/gpt-5.1","azure/gpt-5.1","azure/gpt-5.1-2025-11-13","azure/us/gpt-5.1","databricks/databricks-gpt-5-1","github_copilot/gpt-5.1","gmi/openai/gpt-5.1","gpt-5-1","gpt-5-1-non-reasoning","gpt-5.1","gpt-5.1-2025-11-13","openai-gpt-5-1","openai/gpt-5.1","openai/gpt-5.1:batch","perplexity/openai/gpt-5.1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.625,"max_input_per_1m":1.5,"min_output_per_1m":5,"max_output_per_1m":12,"min_cache_read_per_1m":0.0625,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-5-opus","name":"claude-4-5-opus","display_name":"Claude Opus 4.5","description":"Anthropic's flagship Claude 4.5 model with top-tier reasoning, vision, and tool-use capabilities for complex tasks.","creator":"anthropic","family":"claude","tier":"opus","version":"4-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":409600,"max_output_tokens":64000,"tool_use_system_prompt_tokens":159,"output_vector_sizes":[],"knowledge_cutoff":"2025-05","training_data_cutoff":"2025-08","supported_reasoning_efforts":["default","minimal"],"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":"2025-11-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["anthropic-claude-4-5-opus","anthropic.claude-opus-4-5-20251101-v1:0","anthropic/claude-opus-4.5","anthropic/claude-opus-4.5:batch","azure_ai/claude-opus-4-5","claude-opus-4-5","claude-opus-4-5-20251101","claude-opus-4-5-thinking","claude-opus-4-5@20251101","databricks/databricks-claude-opus-4-5","eu.anthropic.claude-opus-4-5-20251101-v1:0","github_copilot/claude-opus-4.5","global.anthropic.claude-opus-4-5-20251101-v1:0","gmi/anthropic/claude-opus-4.5","openrouter/anthropic/claude-opus-4.5","perplexity/anthropic/claude-opus-4-5","publishers/anthropic/models/claude-opus-4-5","publishers/google/models/claude-opus-4-5","us.anthropic.claude-opus-4-5-20251101-v1:0","vercel_ai_gateway/anthropic/claude-opus-4.5","vertex_ai/claude-opus-4-5","vertex_ai/claude-opus-4-5@20251101"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-4-5-opus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.5,"max_input_per_1m":6,"min_output_per_1m":12.5,"max_output_per_1m":30,"min_cache_read_per_1m":0.25,"min_cache_write_per_1m":3.125,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5","name":"gpt-5","display_name":"GPT-5","description":"OpenAI's frontier LLM with integrated reasoning, vision, image generation, and tool-use capabilities designed for complex coding and agentic tasks.","creator":"openai","family":"gpt","tier":"","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":409600,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-09","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal"],"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":"2025-08-07","earliest_deprecation_date":"2026-12-11","deprecated":false,"has_pricing":true,"provider_count":9,"ids":["azure/eu/gpt-5-2025-08-07","azure/gpt-5","azure/gpt-5-2025-08-07","azure/us/gpt-5-2025-08-07","databricks/databricks-gpt-5","github_copilot/gpt-5","gmi/openai/gpt-5","gpt-5","gpt-5-2025-08-07","gpt-5-chatgpt","gpt-5-low","gpt-5-medium","gpt-5-minimal","oci/openai.gpt-5","openai-gpt-5","openai/gpt-5","openai/gpt-5:batch","openrouter/openai/gpt-5","replicate/openai/gpt-5","snowflake/openai-gpt-5"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.625,"max_input_per_1m":1.5,"min_output_per_1m":5,"max_output_per_1m":12,"min_cache_read_per_1m":0.0625,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-5-sonnet","name":"claude-4-5-sonnet","display_name":"Claude Sonnet 4.5","description":"A versatile Claude 4.5 model with strong reasoning, vision, and tool-use capabilities suited for a broad range of tasks.","creator":"anthropic","family":"claude","tier":"sonnet","version":"4-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":64000,"tool_use_system_prompt_tokens":346,"output_vector_sizes":[],"knowledge_cutoff":"2025-01","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":"2025-09-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["anthropic-claude-4-5-sonnet","anthropic.claude-sonnet-4-5-20250929-v1:0","anthropic/claude-sonnet-4.5","anthropic/claude-sonnet-4.5:batch","au.anthropic.claude-sonnet-4-5-20250929-v1:0","azure_ai/claude-sonnet-4-5","bedrock/us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0","bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0","bedrock/us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0","bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0","claude-4-5-sonnet","claude-4-5-sonnet-thinking","claude-sonnet-4-5","claude-sonnet-4-5-20250929","claude-sonnet-4-5-20250929-v1:0","claude-sonnet-4-5@20250929","databricks/databricks-claude-sonnet-4-5","eu.anthropic.claude-sonnet-4-5-20250929-v1:0","github_copilot/claude-sonnet-4.5","global.anthropic.claude-sonnet-4-5-20250929-v1:0","gmi/anthropic/claude-sonnet-4.5","jp.anthropic.claude-sonnet-4-5-20250929-v1:0","openrouter/anthropic/claude-sonnet-4.5","perplexity/anthropic/claude-sonnet-4-5","publishers/anthropic/models/claude-sonnet-4-5","publishers/google/models/claude-sonnet-4-5","replicate/anthropic/claude-4.5-sonnet","snowflake/claude-sonnet-4-5","us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0","us.anthropic.claude-sonnet-4-5-20250929-v1:0","vercel_ai_gateway/anthropic/claude-sonnet-4.5","vertex_ai/claude-sonnet-4-5","vertex_ai/claude-sonnet-4-5@20250929"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-4-5-sonnet","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.5,"max_input_per_1m":3.6,"min_output_per_1m":7.5,"max_output_per_1m":18,"min_cache_read_per_1m":0.15,"min_cache_write_per_1m":1.875,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-mini","name":"gpt-5-mini","display_name":"GPT-5 Mini","description":"A faster, cost-efficient variant of GPT-5 suited for well-defined tasks and high-volume, low-latency workloads with vision and tool-use support.","creator":"openai","family":"gpt","tier":"mini","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":"2024-05","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal"],"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":"2025-08-07","earliest_deprecation_date":"2026-12-11","deprecated":false,"has_pricing":true,"provider_count":8,"ids":["azure/eu/gpt-5-mini-2025-08-07","azure/gpt-5-mini","azure/gpt-5-mini-2025-08-07","azure/us/gpt-5-mini-2025-08-07","databricks/databricks-gpt-5-mini","github_copilot/gpt-5-mini","gpt-5-mini","gpt-5-mini-2025-08-07","gpt-5-mini-medium","gpt-5-mini-minimal","oci/openai.gpt-5-mini","openai-gpt-5-mini","openai/gpt-5-mini","openai/gpt-5-mini:batch","openrouter/openai/gpt-5-mini","perplexity/openai/gpt-5-mini","replicate/openai/gpt-5-mini","snowflake/openai-gpt-5-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.125,"max_input_per_1m":0.3,"min_output_per_1m":1,"max_output_per_1m":2.4,"min_cache_read_per_1m":0.0125,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"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":9,"ids":["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/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","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","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":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-4-5-haiku","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":1.2,"min_output_per_1m":2.5,"max_output_per_1m":6,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":0.625,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":24,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","cerebras/gpt-oss-120b","cloudflare/@cf/openai/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","fireworks_ai/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sambanova/gpt-oss-120b","scaleway/openai/gpt-oss-120b","tensormesh/openai/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":15,"min_output_per_1m":0.17,"max_output_per_1m":60,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":23},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-2-5-pro","name":"gemini-2-5-pro","display_name":"Gemini 2.5 Pro","description":"Google's most capable thinking model in the Gemini 2.5 family, excelling at complex reasoning, coding, and multimodal tasks with leading benchmark performance.","creator":"google","family":"gemini","tier":"pro","version":"2-5","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["audio","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":"2025-06-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["databricks/databricks-gemini-2-5-pro","deepinfra/google/gemini-2.5-pro","gemini-2-5-pro","gemini-2-5-pro-03-25","gemini-2-5-pro-05-06","gemini-2-5-pro-dec-2025","gemini-2.5-pro","gemini/gemini-2.5-pro","github_copilot/gemini-2.5-pro","google-gemini-2-5-pro","google/gemini-2.5-pro","google/gemini-2.5-pro:batch","oci/google.gemini-2.5-pro","openrouter/google/gemini-2.5-pro","perplexity/google/gemini-2.5-pro","publishers/google/models/gemini-2.5-pro","vercel_ai_gateway/google/gemini-2.5-pro"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemini-2-5-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.625,"max_input_per_1m":1.25,"min_output_per_1m":5,"max_output_per_1m":10,"min_cache_read_per_1m":0.125,"min_cache_write_per_1m":0.125,"min_reasoning_per_1m":5,"cheapest_providers":["openrouter"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-5-nano","name":"gpt-5-nano","display_name":"GPT-5 Nano","description":"The smallest and fastest GPT-5 tier, designed for summarization, classification, and other speed- and cost-sensitive workloads with vision and image-generation support.","creator":"openai","family":"gpt","tier":"nano","version":"5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":5000000,"max_output_tokens":128000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-05","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal"],"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":"2025-08-07","earliest_deprecation_date":"2026-12-11","deprecated":false,"has_pricing":true,"provider_count":8,"ids":["azure/eu/gpt-5-nano-2025-08-07","azure/gpt-5-nano","azure/gpt-5-nano-2025-08-07","azure/us/gpt-5-nano-2025-08-07","databricks/databricks-gpt-5-nano","gpt-5-nano","gpt-5-nano-2025-08-07","gpt-5-nano-medium","gpt-5-nano-minimal","oci/openai.gpt-5-nano","openai-gpt-5-nano","openai/gpt-5-nano","openai/gpt-5-nano:batch","openrouter/openai/gpt-5-nano","replicate/openai/gpt-5-nano","snowflake/openai-gpt-5-nano"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-5-nano","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.025,"max_input_per_1m":0.066,"min_output_per_1m":0.2,"max_output_per_1m":0.48,"min_cache_read_per_1m":0.0025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-20b","name":"gpt-oss-20b","display_name":"GPT OSS 20B","description":"A 20-billion-parameter open-weights GPT model from OpenAI suited for reasoning and tool-use tasks at a smaller, more efficient scale.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":20,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":18,"ids":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","cloudflare/@cf/openai/gpt-oss-20b","darkbloom/gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/openai/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-20b","fireworks_ai/gpt-oss-20b","gpt-oss-20b","gpt-oss-20b-low","gpt-oss-20b-maas","groq/openai/gpt-oss-20b","lemonade/gpt-oss-20b-mxfp4-GGUF","novita/openai/gpt-oss-20b","ollama/gpt-oss:20b-cloud","openai-gpt-oss-20b","openai-reasoning-gpt-oss-20b","openai.gpt-oss-20b-1:0","openai/gpt-oss-20b","openai/gpt-oss-20b:free","openrouter/openai/gpt-oss-20b","ovhcloud/gpt-oss-20b","publishers/google/models/gpt-oss-20b-maas","replicate/openai/gpt-oss-20b","replicateopenai/gpt-oss-20b","tensormesh/openai/gpt-oss-20b","together_ai/openai/gpt-oss-20b","vertex_ai/openai/gpt-oss-20b-maas","wandb/openai/gpt-oss-20b"],"hf_likes":4552,"hf_downloads":6455272,"hf_downloads_all_time":59707566,"hf_trending_score":12,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"openai-gpt-oss-20b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.0145,"max_input_per_1m":5,"min_output_per_1m":0.07,"max_output_per_1m":20,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.007,"min_reasoning_per_1m":null,"cheapest_providers":["other/darkbloom"],"provider_count":18},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-4-maverick","name":"llama-4-maverick","display_name":"Llama 4 Maverick","description":"Meta's Llama 4 Maverick MoE LLM with 128 experts and 17B active parameters, delivering high-capacity multimodal language and vision understanding.","creator":"meta","family":"llama4","tier":"","version":"4","type":"language","size_in_bn":401.584,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1048576,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama4","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":"2025-04-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["databricks/databricks-llama-4-maverick","llama-4-maverick","meta-llama-4-maverick","meta-llama/llama-4-maverick","meta/llama-4-maverick","snowflake/llama4-maverick","vercel_ai_gateway/meta/llama-4-maverick"],"hf_likes":478,"hf_downloads":30421,"hf_downloads_all_time":554732,"hf_trending_score":1,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-llama-4-maverick","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":0.50001,"min_output_per_1m":0.485,"max_output_per_1m":1.50003,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["snowflake"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemini-2-5-flash","name":"gemini-2-5-flash","display_name":"Gemini 2.5 Flash","description":"A fast, cost-efficient Gemini 2.5 thinking model with strong reasoning, vision, and tool-use capabilities designed for high-throughput applications.","creator":"google","family":"gemini","tier":"flash","version":"2-5","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","pdf","text","video"],"output":["audio","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":"2025-06-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["databricks/databricks-gemini-2-5-flash","deepinfra/google/gemini-2.5-flash","gemini-2-5-flash","gemini-2-5-flash-04-2025","gemini-2-5-flash-dec-2025","gemini-2-5-flash-reasoning","gemini-2-5-flash-reasoning-04-2025","gemini-2.5-flash","gemini/gemini-2.5-flash","google_gemini-2-5-flash","google-gemini-2-5-flash","google/gemini-2.5-flash","google/gemini-2.5-flash:batch","oci/google.gemini-2.5-flash","openrouter/google/gemini-2.5-flash","perplexity/google/gemini-2.5-flash","publishers/google/models/gemini-2.5-flash","replicate/google/gemini-2.5-flash","vercel_ai_gateway/google/gemini-2.5-flash"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemini-2-5-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":2.5,"min_output_per_1m":0.6,"max_output_per_1m":3,"min_cache_read_per_1m":0.03,"min_cache_write_per_1m":0.03,"min_reasoning_per_1m":1.25,"cheapest_providers":["google_gemini","google_vertex_ai","openrouter","oracle_oci"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-12b","name":"gemma-3-12b","display_name":"Gemma 3 12B","description":"A 12-billion-parameter Gemma 3 open-weight LLM with multimodal vision-language input support.","creator":"google","family":"gemma","tier":"","version":"3","type":"language","size_in_bn":12,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":32000,"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":["databricks/databricks-gemma-3-12b","gemma-3-12b","google-gemma-3-12b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemma-3-12b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.15001,"max_input_per_1m":0.15001,"min_output_per_1m":0.50001,"max_output_per_1m":0.50001,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-70b-chat","name":"llama-2-70b-chat","display_name":"Llama 2 70B Chat","description":"A 70B Llama 2 model fine-tuned with RLHF for dialogue, providing high-quality conversational responses at the largest Llama 2 scale.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["anyscale/meta-llama/Llama-2-70b-chat-hf","databricks/databricks-llama-2-70b-chat","fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat","llama-2-chat-70b","meta-llama-2-70b-chat","meta.llama2-70b-chat-v1","perplexity/llama-2-70b-chat","replicate/meta/llama-2-70b-chat","snowflake/llama2-70b-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-llama-2-70b-chat","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.50001,"max_input_per_1m":1.95,"min_output_per_1m":0.9,"max_output_per_1m":2.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"microsoft-bge-large-en","name":"bge-large-en","display_name":"BGE Large EN","description":"A large English text embedding model from the BGE family, optimized for retrieval and semantic similarity tasks.","creator":"microsoft","family":"embed","tier":"","version":null,"type":"embedding","size_in_bn":null,"modalities":{"input":["text"],"output":["embedding"]},"context_window":512,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[1024],"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":["databricks/databricks-bge-large-en","microsoft-bge-large-en"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"microsoft-bge-large-en","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.10003,"max_input_per_1m":0.10003,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-4-1-sonnet","name":"claude-4-1-sonnet","display_name":"Claude Sonnet 4.1","description":"A mid-tier Claude 4.1 model balancing strong reasoning and multimodal capabilities with efficient inference.","creator":"anthropic","family":"claude","tier":"sonnet","version":"4-1","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":200000,"max_output_tokens":64000,"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":true,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["anthropic-claude-4-1-sonnet","databricks/databricks-claude-sonnet-4-1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"anthropic-claude-4-1-sonnet","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":2.99999,"max_input_per_1m":2.99999,"min_output_per_1m":15.00002,"max_output_per_1m":15.00002,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-gte-large-en","name":"gte-large-en","display_name":"GTE Large EN","description":"An English-specialized large-size General Text Embeddings model from Alibaba for high-quality semantic similarity tasks.","creator":"alibaba","family":"embed","tier":"","version":null,"type":"embedding","size_in_bn":null,"modalities":{"input":["text"],"output":["embedding"]},"context_window":8192,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[1024],"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":["alibaba-gte-large-en","databricks/databricks-gte-large-en"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-gte-large-en","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.12999,"max_input_per_1m":0.12999,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"databricks-mpt-30b-instruct","name":"databricks-mpt-30b-instruct","display_name":"MPT 30B Instruct","description":"A 30B-parameter instruction-tuned LLM from Databricks based on the MPT architecture, optimized for following complex instructions.","creator":"databricks","family":"mpt","tier":"","version":null,"type":"language","size_in_bn":30,"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":["databricks-mpt-30b-instruct","databricks/databricks-mpt-30b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"databricks-mpt-30b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1.00002,"max_input_per_1m":1.00002,"min_output_per_1m":1.00002,"max_output_per_1m":1.00002,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"databricks-mpt-7b-instruct","name":"databricks-mpt-7b-instruct","display_name":"MPT 7B Instruct","description":"A 7B-parameter instruction-tuned LLM from Databricks based on the MPT architecture, designed for efficient instruction-following tasks.","creator":"databricks","family":"mpt","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":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":["databricks-mpt-7b-instruct","databricks/databricks-mpt-7b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"databricks-mpt-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.50001,"max_input_per_1m":0.50001,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":19},"meta":{"updated_at":"2026-08-14","request_id":"f9057fc9-a8a9-41a5-8e9c-905ddaa56e93","execution_ms":11}}