{"data":[{"id":"google-gemini-3-pro","name":"gemini-3-pro","display_name":"Gemini 3 Pro","description":"Google's pro-tier LLM in the Gemini 3 generation offering frontier multimodal reasoning, coding, and tool-use capabilities.","creator":"google","family":"gemini","tier":"pro","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["image"],"output":["text"]},"context_window":null,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["gemini-3-pro","gemini-3-pro-low","google-gemini-3-pro","replicate/google/gemini-3-pro"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"google-gemini-3-pro","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":4,"min_output_per_1m":12,"max_output_per_1m":18,"min_cache_read_per_1m":null,"min_cache_write_per_1m":0.2,"min_reasoning_per_1m":null,"cheapest_providers":["google_gemini","google_vertex_ai","replicate"],"provider_count":3},"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":null,"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","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":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":1.24999,"max_input_per_1m":1.5,"min_output_per_1m":9.99999,"max_output_per_1m":12,"min_cache_read_per_1m":0.125,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":9},"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":null,"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","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":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-5-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.24997,"max_input_per_1m":0.3,"min_output_per_1m":1.99997,"max_output_per_1m":2.4,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":8},"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","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":"2026-06-13 08:02:30","pricing":{"model_id":"anthropic-claude-4-5-sonnet","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":3.75,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":10},"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":21,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","cerebras/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sambanova/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.039,"max_input_per_1m":15,"min_output_per_1m":0.18,"max_output_per_1m":60,"min_cache_read_per_1m":0.075,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":21},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-o4-mini","name":"o4-mini","display_name":"o4 Mini","description":"A compact o-series reasoning model optimized for fast, cost-efficient performance in coding and visual tasks, with strong multimodal reasoning capabilities.","creator":"openai","family":"o","tier":"mini","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":200000,"max_output_tokens":100000,"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":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-04-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["azure/o4-mini","azure/o4-mini-2025-04-16","azure/us/o4-mini-2025-04-16","ft:o4-mini-2025-04-16","o4-mini","o4-mini-2025-04-16","openai-o4-mini","openai/o4-mini","replicate/openai/o4-mini","vercel_ai_gateway/openai/o4-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-o4-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":4,"min_output_per_1m":4,"max_output_per_1m":16,"min_cache_read_per_1m":0.275,"min_cache_write_per_1m":null,"min_reasoning_per_1m":4,"cheapest_providers":["replicate"],"provider_count":5},"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","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":"2026-06-13 08:02:30","pricing":{"model_id":"anthropic-claude-4-5-haiku","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":1.25,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","azure_aifoundry","google_vertex_ai","openrouter","replicate","vercel_ai_gateway"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-o1","name":"o1","display_name":"o1","description":"A reinforcement-learning-trained reasoning model that produces a long internal chain of thought before responding, excelling at complex multi-step problems across math, science, and coding.","creator":"openai","family":"o","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":200000,"max_output_tokens":100000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10","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":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-12-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["azure/eu/o1-2024-12-17","azure/o1","azure/o1-2024-12-17","azure/us/o1-2024-12-17","o1","o1-2024-12-17","openai-o1","openai/o1","openrouter/openai/o1","replicate/openai/o1","vercel_ai_gateway/openai/o1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-o1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":15,"max_input_per_1m":15,"min_output_per_1m":60,"max_output_per_1m":60,"min_cache_read_per_1m":7.5,"min_cache_write_per_1m":null,"min_reasoning_per_1m":60,"cheapest_providers":["azure_aifoundry","openai","openrouter","replicate","vercel_ai_gateway"],"provider_count":5},"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":null,"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","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":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-5-nano","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.04998,"max_input_per_1m":0.066,"min_output_per_1m":0.39998,"max_output_per_1m":0.48,"min_cache_read_per_1m":0.005,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["databricks"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-4-1","name":"gpt-4-1","display_name":"GPT-4.1","description":"An OpenAI LLM excelling at instruction following and tool calling with a 1M-token context window and low latency without a reasoning step.","creator":"openai","family":"gpt","tier":"","version":"4-1","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1047576,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"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":"2025-04-14","earliest_deprecation_date":"2026-11-04","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/gpt-4.1","azure/gpt-4.1-2025-04-14","azure/us/gpt-4.1-2025-04-14","ft:gpt-4.1-2025-04-14","github_copilot/gpt-4.1","github_copilot/gpt-4.1-2025-04-14","gpt-4-1","gpt-4.1","gpt-4.1-2025-04-14","openai-gpt-4-1","openai/gpt-4.1","openrouter/openai/gpt-4.1","replicate/openai/gpt-4.1","snowflake/openai-gpt-4.1","vercel_ai_gateway/openai/gpt-4.1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-4-1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2.4,"min_output_per_1m":8,"max_output_per_1m":9.6,"min_cache_read_per_1m":0.5,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","openai","openrouter","replicate","vercel_ai_gateway"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-20b","name":"gpt-oss-20b","display_name":"GPT OSS 20B","description":"A 20-billion-parameter open-weights GPT model from OpenAI suited for reasoning and tool-use tasks at a smaller, more efficient scale.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":20,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":16,"ids":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/openai/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-20b","gpt-oss-20b","gpt-oss-20b-low","gpt-oss-20b-maas","groq/openai/gpt-oss-20b","lemonade/gpt-oss-20b-mxfp4-GGUF","novita/openai/gpt-oss-20b","ollama/gpt-oss:20b-cloud","openai-gpt-oss-20b","openai-reasoning-gpt-oss-20b","openai.gpt-oss-20b-1:0","openai/gpt-oss-20b","openai/gpt-oss-20b:free","openrouter/openai/gpt-oss-20b","ovhcloud/gpt-oss-20b","publishers/google/models/gpt-oss-20b-maas","replicateopenai/gpt-oss-20b","together_ai/openai/gpt-oss-20b","vertex_ai/openai/gpt-oss-20b-maas","wandb/openai/gpt-oss-20b"],"hf_likes":4552,"hf_downloads":6455272,"hf_downloads_all_time":59707566,"hf_trending_score":12,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-20b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.029,"max_input_per_1m":5,"min_output_per_1m":0.14,"max_output_per_1m":20,"min_cache_read_per_1m":0.0375,"min_cache_write_per_1m":0.007,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":16},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-4-1-mini","name":"gpt-4-1-mini","display_name":"GPT-4.1 Mini","description":"A compact tier of GPT-4.1 that excels at instruction following and tool calling with a 1M-token context window and reduced cost.","creator":"openai","family":"gpt","tier":"mini","version":"4-1","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1047576,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"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":"2025-04-14","earliest_deprecation_date":"2026-11-04","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["azure/gpt-4.1-mini","azure/gpt-4.1-mini-2025-04-14","azure/us/gpt-4.1-mini-2025-04-14","ft:gpt-4.1-mini-2025-04-14","gpt-4-1-mini","gpt-4.1-mini","gpt-4.1-mini-2025-04-14","openai-gpt-4-1-mini","openai/gpt-4.1-mini","openrouter/openai/gpt-4.1-mini","replicate/openai/gpt-4.1-mini","vercel_ai_gateway/openai/gpt-4.1-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-4-1-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.4,"max_input_per_1m":0.4,"min_output_per_1m":1.6,"max_output_per_1m":1.6,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","openai","openrouter","replicate","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-o1-mini","name":"o1-mini","display_name":"o1 Mini","description":"A faster and more affordable variant of the o1 reasoning model, optimized for STEM tasks while maintaining strong chain-of-thought reasoning capabilities.","creator":"openai","family":"o","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"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":3,"ids":["azure/eu/o1-mini-2024-09-12","azure/o1-mini","azure/o1-mini-2024-09-12","azure/us/o1-mini-2024-09-12","o1-mini","openai-o1-mini","replicate/openai/o1-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-o1-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":1.1,"max_input_per_1m":1.1,"min_output_per_1m":4.4,"max_output_per_1m":4.4,"min_cache_read_per_1m":0.55,"min_cache_write_per_1m":null,"min_reasoning_per_1m":4.4,"cheapest_providers":["azure_aifoundry","openai","replicate"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1","name":"r1","display_name":"DeepSeek R1","description":"DeepSeek's flagship reasoning-focused LLM with strong performance in mathematics, coding, and logical inference, comparable to leading closed-source models.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":684.531,"modalities":{"input":["text"],"output":["text"]},"context_window":163840,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","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":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-01-20","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":14,"ids":["accounts/fireworks/models/deepseek-r1","azure_ai/deepseek-r1","deepinfra/deepseek-ai/DeepSeek-R1","deepseek-llm-r1","deepseek-r1","deepseek-r1-0120","deepseek-r1-qwen3-8b","deepseek-r1685","deepseek-reasoner","deepseek.r1-v1:0","deepseek/deepseek-r1","deepseek/deepseek-reasoner","fireworks_ai/accounts/fireworks/models/deepseek-r1","hyperbolic/deepseek-ai/DeepSeek-R1","nebius/deepseek-ai/DeepSeek-R1","openrouter/deepseek/deepseek-r1","replicate/deepseek-ai/deepseek-r1","sambanova/DeepSeek-R1","snowflake/deepseek-r1","together_ai/deepseek-ai/DeepSeek-R1","us.deepseek.r1-v1:0","vercel_ai_gateway/deepseek/deepseek-r1"],"hf_likes":13288,"hf_downloads":4020320,"hf_downloads_all_time":20204112,"hf_trending_score":20,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"deepseek-r1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.28,"max_input_per_1m":5,"min_output_per_1m":0.4,"max_output_per_1m":10,"min_cache_read_per_1m":0.028,"min_cache_write_per_1m":null,"min_reasoning_per_1m":10,"cheapest_providers":["deepseek"],"provider_count":14},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-3-5-haiku","name":"claude-3-5-haiku","display_name":"Claude Haiku 3.5","description":"A fast, compact Claude model balancing speed and capability with support for vision, file input, and tool use.","creator":"anthropic","family":"claude","tier":"haiku","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":200000,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Claude","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":true,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-11-04","earliest_deprecation_date":"2026-06","deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-3-5-haiku","anthropic.claude-3-5-haiku-20241022-v1:0","anthropic/claude-3.5-haiku","bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0","claude-3-5-haiku","eu.anthropic.claude-3-5-haiku-20241022-v1:0","gradient_ai/anthropic-claude-3.5-haiku","heroku/claude-3-5-haiku","replicate/anthropic/claude-3.5-haiku","us.anthropic.claude-3-5-haiku-20241022-v1:0","vercel_ai_gateway/anthropic/claude-3.5-haiku","vertex_ai/claude-3-5-haiku","vertex_ai/claude-3-5-haiku@20241022"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"anthropic-claude-3-5-haiku","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.8,"max_input_per_1m":1,"min_output_per_1m":4,"max_output_per_1m":5,"min_cache_read_per_1m":0.08,"min_cache_write_per_1m":1,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","anthropic","gradient_ai","openrouter","vercel_ai_gateway"],"provider_count":7},"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","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":"2026-06-13 08:02:30","pricing":{"model_id":"google-gemini-2-5-flash","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":2.5,"cheapest_providers":["google_gemini","google_vertex_ai","oracle_oci"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-235b-a22b-instruct","name":"qwen3-235b-a22b-instruct","display_name":"Qwen3 235B A22B Instruct","description":"An instruction-tuned update of the Qwen3 235B A22B MoE model with significant improvements in instruction following, logical reasoning, and general capabilities.","creator":"alibaba","family":"qwen3_moe","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","alibaba-qwen3-235b-a22b-instruct","crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507","deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507","novita/qwen/qwen3-235b-a22b-instruct-2507","qwen/qwen3-235b-a22b-instruct-2507","Qwen/Qwen3-235B-A22B-Instruct-2507","qwen3-235b-a22b-instruct","qwen3-235b-a22b-instruct-2507","replicate/qwen/qwen3-235b-a22b-instruct-2507","wandb/Qwen/Qwen3-235B-A22B-Instruct-2507"],"hf_likes":773,"hf_downloads":150781,"hf_downloads_all_time":1182969,"hf_trending_score":1,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen3-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.09,"max_input_per_1m":10,"min_output_per_1m":0.58,"max_output_per_1m":10,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","huggingface","novita"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v3","name":"v3","display_name":"DeepSeek V3","description":"DeepSeek's third-generation MoE LLM with 671B total parameters (37B activated per token), excelling at coding, reasoning, and tool use.","creator":"deepseek","family":"deepseek-v3","tier":"","version":"3.0","type":"language","size_in_bn":684.531,"modalities":{"input":["image","text"],"output":["text"]},"context_window":163840,"max_output_tokens":81920,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","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":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-12-26","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":11,"ids":["accounts/fireworks/models/deepseek-v3","azure_ai/deepseek-v3","deepinfra/deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3","deepseek-chat","deepseek-v3","deepseek.v3-v1:0","deepseek/deepseek_v3","deepseek/deepseek-chat","deepseek/deepseek-v3","fireworks_ai/accounts/fireworks/models/deepseek-v3","hyperbolic/deepseek-ai/DeepSeek-V3","nebius/deepseek-ai/DeepSeek-V3","openrouter/deepseek/deepseek-chat","replicate/deepseek-ai/deepseek-v3","together_ai/deepseek-ai/DeepSeek-V3","vercel_ai_gateway/deepseek/deepseek-v3"],"hf_likes":4056,"hf_downloads":882009,"hf_downloads_all_time":15156328,"hf_trending_score":4,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"deepseek-v3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":1.45,"min_output_per_1m":0.2,"max_output_per_1m":4.56,"min_cache_read_per_1m":0.028,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"anthropic-claude-3-5-sonnet","name":"claude-3-5-sonnet","display_name":"Claude Sonnet 3.5","description":"A mid-tier Claude model offering strong reasoning and instruction-following across text and multimodal tasks.","creator":"anthropic","family":"claude","tier":"sonnet","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1000000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":159,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"web_search":false,"computer_use":true,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-06-20","earliest_deprecation_date":"2026-07","deprecated":false,"has_pricing":true,"provider_count":7,"ids":["anthropic-claude-3-5-sonnet","anthropic.claude-3-5-sonnet-20240620-v1:0","anthropic.claude-3-5-sonnet-20241022-v2:0","apac.anthropic.claude-3-5-sonnet-20240620-v1:0","apac.anthropic.claude-3-5-sonnet-20241022-v2:0","bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0","bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0","bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0","claude-35-sonnet","claude-35-sonnet-june-24","eu.anthropic.claude-3-5-sonnet-20240620-v1:0","eu.anthropic.claude-3-5-sonnet-20241022-v2:0","gradient_ai/anthropic-claude-3.5-sonnet","heroku/claude-3-5-sonnet-latest","openrouter/anthropic/claude-3.5-sonnet","replicate/anthropic/claude-3.5-sonnet","snowflake/claude-3-5-sonnet","us.anthropic.claude-3-5-sonnet-20240620-v1:0","vercel_ai_gateway/anthropic/claude-3-5-sonnet","vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022","vercel_ai_gateway/anthropic/claude-3.5-sonnet","vertex_ai/claude-3-5-sonnet","vertex_ai/claude-3-5-sonnet@20240620"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"anthropic-claude-3-5-sonnet","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":3,"max_input_per_1m":3.75,"min_output_per_1m":15,"max_output_per_1m":18.75,"min_cache_read_per_1m":0.3,"min_cache_write_per_1m":3.75,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","google_vertex_ai","gradient_ai","openrouter","snowflake","vercel_ai_gateway"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-4-1-nano","name":"gpt-4-1-nano","display_name":"GPT-4.1 Nano","description":"The smallest tier of GPT-4.1, optimized for ultra-low latency instruction following and tool calling with a 1M-token context window.","creator":"openai","family":"gpt","tier":"nano","version":"4-1","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":1047576,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"GPT","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":"2025-04-14","earliest_deprecation_date":"2026-11-04","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["azure/gpt-4.1-nano","azure/gpt-4.1-nano-2025-04-14","azure/us/gpt-4.1-nano-2025-04-14","ft:gpt-4.1-nano-2025-04-14","gpt-4-1-nano","gpt-4.1-nano","gpt-4.1-nano-2025-04-14","openai-gpt-4-1-nano","openai/gpt-4.1-nano","openrouter/openai/gpt-4.1-nano","replicate/openai/gpt-4.1-nano","vercel_ai_gateway/openai/gpt-4.1-nano"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-4-1-nano","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.1,"min_output_per_1m":0.4,"max_output_per_1m":0.4,"min_cache_read_per_1m":0.025,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","openai","openrouter","replicate","vercel_ai_gateway"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-4o-mini","name":"gpt-4o-mini","display_name":"GPT-4o mini","description":"A fast, cost-efficient small LLM in the GPT-4o family that accepts text and image inputs, ideal for focused tasks and fine-tuning.","creator":"openai","family":"gpt","tier":"mini","version":"4o","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"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":"2024-07-18","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-4o-mini-2024-07-18","azure/global-standard/gpt-4o-mini","azure/gpt-4o-mini","azure/gpt-4o-mini-2024-07-18","azure/us/gpt-4o-mini-2024-07-18","ft:gpt-4o-mini-2024-07-18","github_copilot/gpt-4o-mini","github_copilot/gpt-4o-mini-2024-07-18","gmi/openai/gpt-4o-mini","gpt-4o-mini","gpt-4o-mini-2024-07-18","gpt-4o-mini-realtime-dec-2024","gradient_ai/openai-gpt-4o-mini","openai-gpt-4o-mini","openai/gpt-4o-mini","openai/gpt-4o-mini-2024-07-18","replicate/openai/gpt-4o-mini","vercel_ai_gateway/openai/gpt-4o-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-4o-mini","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":0.075,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","gmi","openai","openrouter","replicate","vercel_ai_gateway"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-7b-chat","name":"llama-2-7b-chat","display_name":"Llama 2 7B Chat","description":"A 7B Llama 2 model fine-tuned with RLHF for dialogue use cases, offering an efficient and accessible conversational LLM.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":7,"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":4,"ids":["@cf/meta/llama-2-7b-chat-fp16","accounts/fireworks/models/llama-v2-7b-chat","anyscale/meta-llama/Llama-2-7b-chat-hf","cloudflare/@cf/meta/llama-2-7b-chat-fp16","cloudflare/@cf/meta/llama-2-7b-chat-int8","fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat","llama-2-chat-7b","meta-llama-2-7b-chat","replicate/meta/llama-2-7b-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-2-7b-chat","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.556,"min_output_per_1m":0.15,"max_output_per_1m":6.667,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["replicate"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-70b-instruct","name":"llama-3-70b-instruct","display_name":"Llama 3 70B Instruct","description":"Meta's 70B instruction-tuned LLM from the Llama 3 generation, widely used for enterprise conversational AI and complex instruction-following tasks.","creator":"meta","family":"llama","tier":"","version":"3","type":"language","size_in_bn":70,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":131072,"max_output_tokens":8192,"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":"2024-04-18","earliest_deprecation_date":"2026-06-19","deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/llama-v3-70b-instruct","accounts/fireworks/models/llama-v3-70b-instruct-hf","accounts/fireworks/models/llama-v3-70b-instruct-v2","anyscale/meta-llama/Meta-Llama-3-70B-Instruct","azure_ai/Meta-Llama-3-70B-Instruct","bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0","bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0","bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0","bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0","bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0","bedrock/us-east-1/meta.llama3-70b-instruct-v1:0","bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0","bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0","bedrock/us-west-1/meta.llama3-70b-instruct-v1:0","databricks/databricks-meta-llama-3-70b-instruct","fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct","fireworks_ai/accounts/fireworks/models/llama-v3-70b-instruct-hf","hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct","llama-3-instruct-70b","meta-llama-3-70b-instruct","meta-llama/llama-3-70b-instruct","meta-textgeneration-llama-3-70b-instruct","meta-textgenerationneuron-llama-3-70b-instruct","meta.llama3-70b-instruct-v1:0","novita/meta-llama/llama-3-70b-instruct","openrouter/meta-llama/llama-3-70b-instruct","replicate/meta/llama-3-70b-instruct","vertex_ai/meta/llama3-70b-instruct-maas"],"hf_likes":1510,"hf_downloads":44220,"hf_downloads_all_time":5966217,"hf_trending_score":1,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-70b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":2.65,"min_output_per_1m":0.3,"max_output_per_1m":3.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-13b-chat","name":"llama-2-13b-chat","display_name":"Llama 2 13B Chat","description":"A 13B Llama 2 model fine-tuned with RLHF for dialogue use cases, optimized for helpful and safe conversational interactions.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":13,"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":4,"ids":["accounts/fireworks/models/llama-v2-13b-chat","anyscale/meta-llama/Llama-2-13b-chat-hf","fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat","llama-2-chat-13b","meta-llama-2-13b-chat","meta.llama2-13b-chat-v1","replicate/meta/llama-2-13b-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-2-13b-chat","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.75,"min_output_per_1m":0.2,"max_output_per_1m":1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["replicate"],"provider_count":4},"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":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-2-70b-chat","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","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":"ibm-granite-3-3-8b-instruct","name":"granite-3-3-8b-instruct","display_name":"Granite 3.3 8B Instruct","description":"IBM's 8B-parameter Granite 3.3 instruction model offering improved reasoning and enterprise task performance in a mid-size open-weight package.","creator":"ibm","family":"granite","tier":"","version":"3-3","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":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":["granite-3-3-8b-instruct","ibm-granite-3-3-8b-instruct","replicate/ibm-granite/granite-3.3-8b-instruct","watsonx/ibm/granite-3-3-8b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"ibm-granite-3-3-8b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"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":["replicate"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-8b-instruct","name":"llama-3-8b-instruct","display_name":"Llama 3 8B Instruct","description":"Meta's 8B instruction-tuned LLM from the Llama 3 generation, offering fast and cost-effective instruction-following across diverse tasks.","creator":"meta","family":"llama","tier":"","version":"3","type":"language","size_in_bn":8,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":32000,"max_output_tokens":8192,"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":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-04-18","earliest_deprecation_date":"2026-06-19","deprecated":false,"has_pricing":true,"provider_count":9,"ids":["@cf/meta/llama-3-8b-instruct","accounts/fireworks/models/llama-v3-8b-instruct","accounts/fireworks/models/llama-v3-8b-instruct-hf","accounts/fireworks/models/llama-v3-8b-instruct-v0","anyscale/meta-llama/Meta-Llama-3-8B-Instruct","bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0","bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0","bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0","bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0","bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0","bedrock/us-west-1/meta.llama3-8b-instruct-v1:0","deepinfra/meta-llama/Meta-Llama-3-8B-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf","gradient_ai/llama3-8b-instruct","huggingface-llm-gradientai-llama-3-8B-instruct-262k","huggingface-llm-llama-3-8b-instruct-gradient","llama-3-instruct-8b","meta-llama-3-8b-instruct","meta-llama/llama-3-8b-instruct","meta-llama/Meta-Llama-3-8B-Instruct","meta-textgeneration-llama-3-8b-instruct","meta-textgenerationneuron-llama-3-8b-instruct","meta.llama3-8b-instruct-v1:0","novita/meta-llama/llama-3-8b-instruct","replicate/meta/llama-3-8b-instruct","vertex_ai/meta/llama3-8b-instruct-maas"],"hf_likes":4486,"hf_downloads":1342402,"hf_downloads_all_time":40122839,"hf_trending_score":1.5,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-8b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.3,"min_output_per_1m":0.04,"max_output_per_1m":0.827,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-13b","name":"meta-llama-2-13b","display_name":"Llama 2 13B","description":"A 13B parameter pretrained Llama 2 base model for text generation, offering a balance between capability and computational efficiency.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":13,"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":2,"ids":["accounts/fireworks/models/llama-v2-13b","fireworks_ai/accounts/fireworks/models/llama-v2-13b","meta-llama-2-13b","meta-textgeneration-llama-2-13b","meta-textgeneration-llama-2-13b-f","meta-textgenerationneuron-llama-2-13b","ollama/llama2:13b","replicate/meta/llama-2-13b","sagemaker/meta-textgeneration-llama-2-13b","sagemaker/meta-textgeneration-llama-2-13b-f"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-2-13b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"max_output_per_1m":0.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["replicate"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-70b","name":"meta-llama-2-70b","display_name":"Llama 2 70B","description":"The largest pretrained Llama 2 base model at 70B parameters, delivering strong text generation performance across a wide range of language tasks.","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":2,"ids":["accounts/fireworks/models/llama-v2-70b","fireworks_ai/accounts/fireworks/models/llama-v2-70b","meta-llama-2-70b","meta-textgeneration-llama-2-70b","meta-textgeneration-llama-2-70b-f","meta-textgenerationneuron-llama-2-70b","ollama/llama2:70b","replicate/meta/llama-2-70b","sagemaker/meta-textgeneration-llama-2-70b","sagemaker/meta-textgeneration-llama-2-70b-b-f"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-2-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.65,"min_output_per_1m":0.1,"max_output_per_1m":2.75,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-2-7b","name":"meta-llama-2-7b","display_name":"Llama 2 7B","description":"The smallest pretrained Llama 2 base model at 7B parameters, suitable for efficient text generation and fine-tuning on downstream tasks.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":7,"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":2,"ids":["accounts/fireworks/models/llama-v2-7b","fireworks_ai/accounts/fireworks/models/llama-v2-7b","meta-llama-2-7b","meta-textgeneration-llama-2-7b","meta-textgeneration-llama-2-7b-f","meta-textgenerationneuron-llama-2-7b","ollama/llama2:7b","replicate/meta/llama-2-7b","sagemaker/meta-textgeneration-llama-2-7b","sagemaker/meta-textgeneration-llama-2-7b-f"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-2-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"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":["replicate"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-70b","name":"meta-llama-3-70b","display_name":"Llama 3 70B","description":"Meta's 70B pre-trained LLM from the Llama 3 generation, offering strong general-purpose text generation and reasoning capabilities.","creator":"meta","family":"llama","tier":"","version":"3","type":"language","size_in_bn":70,"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":3,"ids":["meta-llama-3-70b","meta-textgeneration-llama-3-70b","meta-textgenerationneuron-llama-3-70b","ollama/llama3:70b","replicate/meta/llama-3-70b","snowflake/llama3-70b","vercel_ai_gateway/meta/llama-3-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.59,"max_input_per_1m":2.42,"min_output_per_1m":0.79,"max_output_per_1m":2.75,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-8b","name":"meta-llama-3-8b","display_name":"Llama 3 8B","description":"Meta's compact 8B pre-trained LLM from the Llama 3 generation, suitable for efficient on-device and low-cost cloud inference.","creator":"meta","family":"llama","tier":"","version":"3","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":4,"ids":["accounts/fireworks/models/llama-v3-8b","fireworks_ai/accounts/fireworks/models/llama-v3-8b","meta-llama-3-8b","meta-textgeneration-llama-3-8b","meta-textgenerationneuron-llama-3-8b","ollama/llama3:8b","replicate/meta/llama-3-8b","snowflake/llama3-8b","vercel_ai_gateway/meta/llama-3-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.38,"min_output_per_1m":0.08,"max_output_per_1m":0.38,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["replicate","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-7b","name":"7b","display_name":"Mistral 7B","description":"Mistral AI's foundational 7B-parameter base language model known for strong performance relative to its compact size.","creator":"mistral","family":"mistral","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"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":5,"ids":["accounts/fireworks/models/hermes-2-pro-mistral-7b","accounts/fireworks/models/mistral-7b","accounts/fireworks/models/mistral-7b-v0p2","accounts/fireworks/models/openhermes-2-mistral-7b","accounts/fireworks/models/openhermes-2p5-mistral-7b","fireworks_ai/accounts/fireworks/models/hermes-2-pro-mistral-7b","fireworks_ai/accounts/fireworks/models/mistral-7b","fireworks_ai/accounts/fireworks/models/mistral-7b-v0p2","fireworks_ai/accounts/fireworks/models/openhermes-2-mistral-7b","fireworks_ai/accounts/fireworks/models/openhermes-2p5-mistral-7b","huggingface-llm-dolphin-2-2-1-mistral-7b","huggingface-llm-mistral-7b","huggingface-llm-teknium-openhermes-2-mistral-7b","huggingface-llmneuron-mistral-7b","llamagate/mistral-7b-v0.3","mistral-7b","mistral/open-mistral-7b","replicate/mistralai/mistral-7b-v0.1","snowflake/mistral-7b","teknium/openhermes-2.5-mistral-7b"],"hf_likes":900,"hf_downloads":6234,"hf_downloads_all_time":3856208,"hf_trending_score":3,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"mistral-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.25,"min_output_per_1m":0.1,"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":["replicate"],"provider_count":5},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":33},"meta":{"updated_at":"2026-06-13","request_id":"6e37a6ce-ea10-4369-ac90-4dad28fc5029","execution_ms":11}}