{"data":[{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":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":"nvidia-nemotron-lightning-3-5","name":"nemotron-lightning-3-5","display_name":"Nemotron Lightning 3.5","description":"NVIDIA's fast open model targeting always-on agents and high-volume specialized tasks with strong agentic capability.","creator":"nvidia","family":"nemotron","tier":"","version":"3-5","type":"language","size_in_bn":31.578,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":262144,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-08-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","nemotron-3-5-lightning","nvidia-nemotron-lightning-3-5","nvidia/nemotron-3.5-lightning","nvidia/nemotron-3.5-lightning:free","nvidia/NVIDIA-Nemotron-3.5-Lightning","openrouter/nvidia/nemotron-3.5-lightning"],"hf_likes":120,"hf_downloads":15740,"hf_downloads_all_time":15740,"hf_trending_score":120,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"nvidia-nemotron-lightning-3-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.1,"min_output_per_1m":0.2,"max_output_per_1m":0.25,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":2},"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":"deepseek-v3-1-terminus","name":"deepseek-v3-1-terminus","display_name":"DeepSeek V3.1 Terminus","description":"An update to DeepSeek V3.1 that addresses language consistency and agent capability issues while preserving the model's core performance.","creator":"deepseek","family":"deepseek-v3","tier":"terminus","version":"3.1","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":"2025-03-31","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":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-09-22","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/deepseek-v3p1-terminus","deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-ai/DeepSeek-V3.1-Terminus","deepseek-v3-1-terminus","deepseek-v3-1-terminus-reasoning","deepseek/deepseek-v3.1-terminus","fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus","novita/deepseek/deepseek-v3.1-terminus"],"hf_likes":363,"hf_downloads":3879,"hf_downloads_all_time":180017,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-v3-1-terminus","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.27,"max_input_per_1m":0.56,"min_output_per_1m":0.95,"max_output_per_1m":1.68,"min_cache_read_per_1m":0.13,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","huggingface","novita","openrouter","vercel_ai_gateway"],"provider_count":6},"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":13,"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":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-r1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","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":13},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-coder-480b-a35b-instruct","name":"qwen3-coder-480b-a35b-instruct","display_name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen3's flagship agentic code model with 480B total and 35B activated parameters, excelling at autonomous programming, tool calling, and browser-use tasks.","creator":"alibaba","family":"qwen3_moe","tier":"","version":null,"type":"language","size_in_bn":480,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","alibaba-qwen3-coder-480b-a35b-instruct","deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct","novita/qwen/qwen3-coder-480b-a35b-instruct","qwen/qwen3-coder-480b-a35b-instruct","Qwen/Qwen3-Coder-480B-A35B-Instruct","qwen3-coder-480b-a35b-instruct","wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct"],"hf_likes":1325,"hf_downloads":57687,"hf_downloads_all_time":885858,"hf_trending_score":0.5,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-coder-480b-a35b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.22,"max_input_per_1m":100,"min_output_per_1m":1.3,"max_output_per_1m":150,"min_cache_read_per_1m":null,"min_cache_write_per_1m":0.022,"min_reasoning_per_1m":null,"cheapest_providers":["google_gemini","google_vertex_ai"],"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":"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":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-v3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","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":"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":"deepseek-r1-distill-qwen-32b","name":"deepseek-r1-distill-qwen-32b","display_name":"DeepSeek R1 Distill Qwen 32B","description":"A 32B Qwen-based model distilled from DeepSeek R1's reasoning capabilities, offering high-quality chain-of-thought performance at a mid-scale parameter count.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-01-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","accounts/fireworks/models/deepseek-r1-distill-qwen-32b","cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-llm-r1-distill-qwen-32b","deepseek-r1-distill-qwen-32b","deepseek/deepseek-r1-distill-qwen-32b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","novita/deepseek/deepseek-r1-distill-qwen-32b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"hf_likes":1545,"hf_downloads":1046750,"hf_downloads_all_time":23929632,"hf_trending_score":3,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-r1-distill-qwen-32b","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":0.9,"min_output_per_1m":0.15,"max_output_per_1m":4.881,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":6},"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":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["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","scaleway/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":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-235b-a22b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.09,"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":11},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-72b-instruct","name":"qwen2-5-72b-instruct","display_name":"Qwen2.5 72B Instruct","description":"A 72-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, excelling at natural language understanding, summarization, and dialogue.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":72,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-09-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen2p5-72b-instruct","alibaba-qwen2-5-72b-instruct","deepinfra/Qwen/Qwen2.5-72B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct","huggingface-llm-qwen2-5-72b-instruct","hyperbolic/Qwen/Qwen2.5-72B-Instruct","nebius/Qwen/Qwen2.5-72B-Instruct","novita/qwen/qwen-2.5-72b-instruct","qwen/qwen-2.5-72b-instruct","Qwen/Qwen2.5-72B-Instruct","qwen2-5-72b-instruct","qwen2.5-72b-instruct"],"hf_likes":927,"hf_downloads":457915,"hf_downloads_all_time":5817981,"hf_trending_score":1,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen2-5-72b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":0.9,"min_output_per_1m":0.3,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","hyperbolic"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-1-70b-instruct","name":"llama-3-1-70b-instruct","display_name":"Llama 3.1 70B Instruct","description":"Meta's 70B instruction-tuned LLM with strong tool-use and multilingual capabilities, widely deployed across cloud regions for enterprise workloads.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":70,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["accounts/fireworks/models/llama-v3p1-70b-instruct","accounts/fireworks/models/llama-v3p1-70b-instruct-1b","azure_ai/Meta-Llama-3.1-70B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct","fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b","friendliai/meta-llama-3.1-70b-instruct","hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct","lambda_ai/llama3.1-70b-instruct-fp8","llama-3-1-instruct-70b","meta-llama-3-1-70b-instruct","meta-llama/llama-3.1-70b-instruct","meta-llama/Meta-Llama-3.1-70B-Instruct","meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","meta-textgeneration-llama-3-1-70b-instruct","meta-textgenerationneuron-llama-3-1-70b-instruct","meta.llama3-1-70b-instruct-v1:0","meta.llama3-1-70b-instruct-v1:0:128k","nebius/meta-llama/Meta-Llama-3.1-70B-Instruct","oci/meta.llama-3.1-70b-instruct","ovhcloud/Meta-Llama-3_1-70B-Instruct","perplexity/llama-3.1-70b-instruct","together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","us.meta.llama3-1-70b-instruct-v1:0","vertex_ai/meta/llama-3.1-70b-instruct-maas"],"hf_likes":907,"hf_downloads":737459,"hf_downloads_all_time":20735812,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"meta-llama-3-1-70b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":2.68,"min_output_per_1m":0.3,"max_output_per_1m":3.54,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic","lambda"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"nousresearch-hermes-3-llama-3-1-70b","name":"hermes-3-llama-3-1-70b","display_name":"Hermes 3 Llama 3.1 70B","description":"A 70B-parameter Llama 3.1-based LLM from Nous Research with Hermes 3 fine-tuning for improved agentic capabilities and long-context coherence.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-08-18","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","hermes-3-llama-3-1-70b","hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B","nousresearch-hermes-3-llama-3-1-70b","nousresearch/hermes-3-llama-3.1-70b","NousResearch/Hermes-3-Llama-3.1-70B"],"hf_likes":123,"hf_downloads":2494,"hf_downloads_all_time":179146,"hf_trending_score":1,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"nousresearch-hermes-3-llama-3-1-70b","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":0.7,"min_output_per_1m":0.3,"max_output_per_1m":0.7,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"microsoft-phi-4","name":"phi-4","display_name":"Phi-4","description":"A small language model from Microsoft trained on high-quality synthetic and curated datasets, excelling at reasoning and STEM tasks despite its compact size.","creator":"microsoft","family":"phi","tier":"","version":"4","type":"language","size_in_bn":14.66,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-01-10","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure_ai/Phi-4","deepinfra/microsoft/phi-4","microsoft-phi-4","microsoft/phi-4","phi-4","phi-4-mini","phi-4-multimodal","publishers/microsoft/models/phi4"],"hf_likes":2248,"hf_downloads":874552,"hf_downloads_all_time":11669853,"hf_trending_score":4,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"microsoft-phi-4","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.125,"min_output_per_1m":0.14,"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":["deepinfra","openrouter"],"provider_count":3},"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":true,"adaptive_reasoning":false},"release_date":"2024-04-23","earliest_deprecation_date":"2026-06-19","deprecated":false,"has_pricing":true,"provider_count":8,"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":"2026-08-14 08:03:18","pricing":{"model_id":"meta-llama-3-8b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.03,"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":8},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-528","name":"deepseek-r1-528","display_name":"DeepSeek R1 528","description":"The DeepSeek R1 0528 update, a reasoning-focused MoE LLM with improved chain-of-thought capabilities over the original R1 release.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":684.531,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":164000,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":["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":"2025-05-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["accounts/fireworks/models/deepseek-r1-0528","crusoe/deepseek-ai/DeepSeek-R1-0528","deepinfra/deepseek-ai/DeepSeek-R1-0528","deepseek-ai/DeepSeek-R1-0528","deepseek-llm-r1-0528","deepseek-r1-0528","deepseek-r1-0528-maas","deepseek-r1-528","deepseek/deepseek-r1-0528","fireworks_ai/accounts/fireworks/models/deepseek-r1-0528","hyperbolic/deepseek-ai/DeepSeek-R1-0528","lambda_ai/deepseek-r1-0528","nebius/deepseek-ai/DeepSeek-R1-0528","novita/deepseek/deepseek-r1-0528","openrouter/deepseek/deepseek-r1-0528","publishers/google/models/deepseek-r1-0528-maas","vertex_ai/deepseek-ai/deepseek-r1-0528-maas","wandb/deepseek-ai/DeepSeek-R1-0528"],"hf_likes":2445,"hf_downloads":707890,"hf_downloads_all_time":6472632,"hf_trending_score":1,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-r1-528","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":135,"min_output_per_1m":0.25,"max_output_per_1m":540,"min_cache_read_per_1m":0.35,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-528-turbo","name":"deepseek-r1-528-turbo","display_name":"DeepSeek R1 528 Turbo","description":"A turbo-speed variant of the DeepSeek R1 0528 reasoning model, optimized for fast inference while retaining strong chain-of-thought performance.","creator":"deepseek","family":"deepseek-r1","tier":"turbo","version":"1.0","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo","deepseek-ai/DeepSeek-R1-0528-Turbo","deepseek-r1-528-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-r1-528-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":1,"max_input_per_1m":1,"min_output_per_1m":3,"max_output_per_1m":3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-turbo","name":"deepseek-r1-turbo","display_name":"DeepSeek R1 Turbo","description":"A turbo-speed variant of DeepSeek R1 optimized for faster inference while preserving the model's strong mathematical and logical reasoning abilities.","creator":"deepseek","family":"deepseek-r1","tier":"turbo","version":"1.0","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":64000,"max_output_tokens":16000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":false,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/deepseek-ai/DeepSeek-R1-Turbo","deepseek-r1-turbo","deepseek/deepseek-r1-turbo","novita/deepseek/deepseek-r1-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"deepseek-r1-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.7,"max_input_per_1m":1,"min_output_per_1m":2.5,"max_output_per_1m":3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","novita"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-12b-instruct","name":"gemma-3-12b-instruct","display_name":"Gemma 3 12B Instruct","description":"An instruction-tuned 12B Gemma 3 LLM supporting vision-language inputs and 128k context.","creator":"google","family":"gemma3_text","tier":"","version":"3","type":"language","size_in_bn":12,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-03-13","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["@cf/google/gemma-3-12b-it","accounts/fireworks/models/gemma-3-12b-it","crusoe/google/gemma-3-12b-it","deepinfra/google/gemma-3-12b-it","google-gemma-3-12b-instruct","google.gemma-3-12b-it","google/gemma-3-12b-it","google/gemma-3-12b-it:free","novita/google/gemma-3-12b-it"],"hf_likes":707,"hf_downloads":2516014,"hf_downloads_all_time":14080610,"hf_trending_score":2,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemma-3-12b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.345,"min_output_per_1m":0.1,"max_output_per_1m":0.556,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","novita","openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-27b-instruct","name":"gemma-3-27b-instruct","display_name":"Gemma 3 27B Instruct","description":"An instruction-tuned 27B Gemma 3 LLM with multimodal vision-language input and 128k context window.","creator":"google","family":"gemma3","tier":"","version":"3","type":"language","size_in_bn":27,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-03-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/gemma-3-27b-it","deepinfra/google/gemma-3-27b-it","fireworks_ai/accounts/fireworks/models/gemma-3-27b-it","gemini/gemma-3-27b-it","google-gemma-3-27b-instruct","google.gemma-3-27b-it","google/gemma-3-27b-it","google/gemma-3-27b-it:free","huggingface-vlm-gemma-3-27b-instruct","nebius/google/gemma-3-27b-it","novita/google/gemma-3-27b-it","scaleway/google/gemma-3-27b-it"],"hf_likes":1956,"hf_downloads":567671,"hf_downloads_all_time":12733530,"hf_trending_score":2,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemma-3-27b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.08,"max_input_per_1m":0.9,"min_output_per_1m":0.16,"max_output_per_1m":0.9,"min_cache_read_per_1m":0.04,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"google-gemma-3-4b-instruct","name":"gemma-3-4b-instruct","display_name":"Gemma 3 4B Instruct","description":"An instruction-tuned 4B Gemma 3 LLM supporting vision-language inputs for efficient multimodal tasks.","creator":"google","family":"gemma3_text","tier":"","version":"3","type":"language","size_in_bn":4,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-03-13","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/gemma-3-4b-it","deepinfra/google/gemma-3-4b-it","google-gemma-3-4b-instruct","google.gemma-3-4b-it","google/gemma-3-4b-it","google/gemma-3-4b-it:free","huggingface-vlm-gemma-3-4b-instruct","lemonade/Gemma-3-4b-it-GGUF"],"hf_likes":1313,"hf_downloads":2130064,"hf_downloads_all_time":17437981,"hf_trending_score":4,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"google-gemma-3-4b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.05,"min_output_per_1m":0.08,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["amazon_bedrock","deepinfra"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"sao10k-l3-lunaris-1-8b-turbo","name":"l3-lunaris-1-8b-turbo","display_name":"L3 Lunaris 1.8B Turbo","description":"A compact 1.8B Llama 3-based generalist and roleplay model from Sao10k, optimized for fast inference in the Lunaris series.","creator":"sao10k","family":"llama","tier":"","version":"1","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","sao10k-l3-lunaris-1-8b-turbo","Sao10K/L3-8B-Lunaris-v1-Turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"sao10k-l3-lunaris-1-8b-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.04,"min_output_per_1m":0.05,"max_output_per_1m":0.05,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"sao10k-l3-1-euryale-2-2-70b","name":"l3-1-euryale-2-2-70b","display_name":"L3.1 70B Euryale V2.2","description":"A 70B Llama 3.1-based creative roleplay model from Sao10k, focused on immersive character performance and narrative generation.","creator":"sao10k","family":"llama","tier":"","version":"2-2","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","novita/sao10k/l31-70b-euryale-v2.2","sao10k-l3-1-euryale-2-2-70b","Sao10K/L3.1-70B-Euryale-v2.2","sao10k/l31-70b-euryale-v2.2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"sao10k-l3-1-euryale-2-2-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.65,"max_input_per_1m":1.48,"min_output_per_1m":0.75,"max_output_per_1m":1.48,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"sao10k-l3-3-euryale-2-3-70b","name":"l3-3-euryale-2-3-70b","display_name":"L3.3 70B Euryale V2.3","description":"A 70B Llama 3.3-based creative roleplay model from Sao10k, representing the latest iteration of the Euryale fine-tune series.","creator":"sao10k","family":"llama","tier":"","version":"2-3","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["deepinfra/Sao10K/L3.3-70B-Euryale-v2.3","sao10k-l3-3-euryale-2-3-70b","Sao10K/L3.3-70B-Euryale-v2.3"],"hf_likes":83,"hf_downloads":50195,"hf_downloads_all_time":70669,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"sao10k-l3-3-euryale-2-3-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.65,"max_input_per_1m":0.65,"min_output_per_1m":0.75,"max_output_per_1m":0.75,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-3-70b-instruct-turbo","name":"llama-3-3-70b-instruct-turbo","display_name":"Llama 3.3 70B Instruct Turbo","description":"FP8-quantized turbo variant of Llama 3.3 70B Instruct, delivering significantly faster inference speeds with minimal accuracy trade-off.","creator":"meta","family":"llama","tier":"","version":"3-3","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":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":["deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","meta-llama-3-3-70b-instruct-turbo","meta-llama/Llama-3.3-70B-Instruct-Turbo","together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo"],"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-3-3-70b-instruct-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.13,"max_input_per_1m":1.04,"min_output_per_1m":0.39,"max_output_per_1m":1.04,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-small-24b-instruct","name":"mistral-small-24b-instruct","display_name":"Mistral Small 24B Instruct","description":"A 24B-parameter instruction-tuned LLM from Mistral, offering strong text generation performance in a compact model footprint.","creator":"mistral","family":"mistral","tier":"","version":null,"type":"language","size_in_bn":24,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-01-30","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/mistral-small-24b-instruct-2501","deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501","huggingface-llm-mistral-small-24B-Instruct-2501","mistral-small-24b-instruct","mistralai/mistral-small-24b-instruct-2501","mistralai/Mistral-Small-24B-Instruct-2501","together_ai/mistralai/Mistral-Small-24B-Instruct-2501"],"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":"mistral-small-24b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.9,"min_output_per_1m":0.08,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","openrouter"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-small-3-2-24b-instruct","name":"mistral-small-3-2-24b-instruct","display_name":"Mistral Small 3.2 24B Instruct","description":"A 24B-parameter instruction-tuned multimodal LLM representing the 3.2 update of Mistral's Small series with enhanced vision and text capabilities.","creator":"mistral","family":"mistral","tier":"","version":"3-2","type":"language","size_in_bn":24,"modalities":{"input":["image","text"],"output":["text"]},"context_window":256000,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","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":"2025-06-20","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","huggingface-vlm-mistral-small-3-2-24b-instruct-2506","mistral-small-3-2-24b-instruct","mistralai/mistral-small-3.2-24b-instruct","mistralai/Mistral-Small-3.2-24B-Instruct-2506","openrouter/mistralai/mistral-small-3.2-24b-instruct","ovhcloud/Mistral-Small-3.2-24B-Instruct-2506","scaleway/mistralai/mistral-small-3.2-24b-instruct-2506"],"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":"mistral-small-3-2-24b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.075,"max_input_per_1m":0.15,"min_output_per_1m":0.2,"max_output_per_1m":0.35,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"gryphe-mythomax-l2-13b","name":"mythomax-l2-13b","display_name":"MythoMax L2 13B","description":"A 13B Llama 2-based LLM fine-tuned via experimental tensor-merge techniques for strong performance in both creative storytelling and roleplay scenarios.","creator":"gryphe","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama2","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":"2023-07-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/mythomax-l2-13b","deepinfra/Gryphe/MythoMax-L2-13b","fireworks_ai/accounts/fireworks/models/mythomax-l2-13b","gryphe-mythomax-l2-13b","gryphe/mythomax-l2-13b","Gryphe/MythoMax-L2-13b","novita/gryphe/mythomax-l2-13b","openrouter/gryphe/mythomax-l2-13b"],"hf_likes":377,"hf_downloads":1784,"hf_downloads_all_time":728893,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"gryphe-mythomax-l2-13b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.2,"min_output_per_1m":0.06,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-nemo-instruct","name":"mistral-nemo-instruct","display_name":"Nemo Instruct (24.07)","description":"Instruction-tuned variant of the Mistral Nemo 12B model, designed for multilingual conversational and task-following applications.","creator":"mistral","family":"mistral","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":512,"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":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/mistral-nemo-instruct-2407","deepinfra/mistralai/Mistral-Nemo-Instruct-2407","fireworks_ai/accounts/fireworks/models/mistral-nemo-instruct-2407","gradient_ai/mistral-nemo-instruct-2407","huggingface-llm-mistral-nemo-instruct-2407","mistral-nemo-instruct","mistralai/Mistral-Nemo-Instruct-2407","nebius/mistralai/Mistral-Nemo-Instruct-2407","ovhcloud/Mistral-Nemo-Instruct-2407"],"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":"mistral-nemo-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.02,"max_input_per_1m":0.3,"min_output_per_1m":0.04,"max_output_per_1m":0.3,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"allenai-olmocr-7b","name":"olmocr-7b","display_name":"OLMoCR 7B","description":"A 7B document OCR model from the Allen Institute for AI, designed to extract and structure text from complex PDF documents with high fidelity.","creator":"allenai","family":"olmocr","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":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":["allenai-olmocr-7b","deepinfra/allenai/olmOCR-7B-0725-FP8"],"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":"allenai-olmocr-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.27,"max_input_per_1m":0.27,"min_output_per_1m":1.5,"max_output_per_1m":1.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-7b-instruct","name":"qwen2-5-7b-instruct","display_name":"Qwen2.5 7B Instruct","description":"A 7-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, optimized for responsive text generation and instruction following.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-10-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen2p5-7b-instruct","alibaba-qwen2-5-7b-instruct","deepinfra/Qwen/Qwen2.5-7B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct","huggingface-llm-qwen2-5-7b-instruct","novita/qwen/qwen2.5-7b-instruct","qwen/qwen-2.5-7b-instruct","qwen/qwen2.5-7b-instruct","qwen2.5-7b-instruct"],"hf_likes":1217,"hf_downloads":12284868,"hf_downloads_all_time":119351105,"hf_trending_score":9,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen2-5-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.04,"max_input_per_1m":0.2,"min_output_per_1m":0.07,"max_output_per_1m":0.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-vl-32b-instruct","name":"qwen2-5-vl-32b-instruct","display_name":"Qwen2.5 VL 32B Instruct","description":"A 32-billion-parameter multimodal vision-language LLM from Alibaba's Qwen2.5-VL series, capable of understanding and reasoning over both images and text.","creator":"alibaba","family":"qwen2_5_vl","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["image"],"output":["text"]},"context_window":128000,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/qwen2p5-vl-32b-instruct","alibaba-qwen2-5-vl-32b-instruct","deepinfra/Qwen/Qwen2.5-VL-32B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-vl-32b-instruct","qwen2.5-vl-32b-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":"alibaba-qwen2-5-vl-32b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.9,"min_output_per_1m":0.6,"max_output_per_1m":0.9,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-14b","name":"qwen3-14b","display_name":"Qwen3 14B","description":"A 14-billion-parameter LLM from Alibaba's Qwen3 series with strong reasoning and tool-use capabilities for complex instruction-following tasks.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":14,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-04-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3-14b","alibaba-qwen3-14b","alibaba/qwen-3-14b","deepinfra/Qwen/Qwen3-14B","fireworks_ai/accounts/fireworks/models/qwen3-14b","huggingface-reasoning-qwen3-14b","nebius/Qwen/Qwen3-14B","qwen/qwen3-14b","Qwen/Qwen3-14B","qwen3-14b","qwen3-14b-instruct","qwen3-14b-instruct-reasoning","vercel_ai_gateway/alibaba/qwen-3-14b"],"hf_likes":386,"hf_downloads":3005499,"hf_downloads_all_time":14478982,"hf_trending_score":3,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-14b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.35,"min_output_per_1m":0.2,"max_output_per_1m":1.4,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-235b-a22b","name":"qwen3-235b-a22b","display_name":"Qwen3 235B A22B","description":"A large-scale Mixture-of-Experts LLM with 235B total parameters and 22B active parameters, designed for high-capability reasoning and instruction following.","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":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-04-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["accounts/fireworks/models/qwen3-235b-a22b","alibaba-qwen3-235b-a22b","deepinfra/Qwen/Qwen3-235B-A22B","fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b","hyperbolic/Qwen/Qwen3-235B-A22B","nebius/Qwen/Qwen3-235B-A22B","novita/qwen/qwen3-235b-a22b-fp8","openrouter/qwen/qwen3-235b-a22b-2507","qwen.qwen3-235b-a22b-2507-v1:0","qwen/qwen3-235b-a22b","qwen/qwen3-235b-a22b-2507","qwen/qwen3-235b-a22b-fp8","qwen3-235b-a22b","qwen3-235b-a22b-instruct-2507-reasoning","qwen3-235b-a22b-instruct-reasoning"],"hf_likes":1091,"hf_downloads":589589,"hf_downloads_all_time":3957896,"hf_trending_score":3,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-235b-a22b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.09,"max_input_per_1m":2,"min_output_per_1m":0.54,"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":["openrouter"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-coder-480b-a35b-instruct-turbo","name":"qwen3-coder-480b-a35b-instruct-turbo","display_name":"Qwen3 Coder 480B A35B Instruct Turbo","description":"A high-throughput turbo variant of the Qwen3 Coder 480B A35B Instruct MoE model, optimized for faster agentic coding and tool-use inference.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":480,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["alibaba-qwen3-coder-480b-a35b-instruct-turbo","deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo"],"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-qwen3-coder-480b-a35b-instruct-turbo","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.29,"max_input_per_1m":0.29,"min_output_per_1m":1.2,"max_output_per_1m":1.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-next-80b-a3b-thinking","name":"qwen3-next-80b-a3b-thinking","display_name":"Qwen3 Next 80B A3B Thinking","description":"A thinking-mode variant of the Qwen3 Next MoE model with 80B total and 3B activated parameters, featuring hybrid attention for extended chain-of-thought reasoning.","creator":"alibaba","family":"qwen3_next","tier":"","version":null,"type":"language","size_in_bn":80,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-09-30","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-09-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3-next-80b-a3b-thinking","alibaba-qwen3-next-80b-a3b-thinking","alibaba/qwen3-next-80b-a3b-thinking","dashscope/qwen3-next-80b-a3b-thinking","deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking","fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking","novita/qwen/qwen3-next-80b-a3b-thinking","qwen/qwen3-next-80b-a3b-thinking","qwen3-next-80b-a3b-thinking","together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking"],"hf_likes":487,"hf_downloads":32460,"hf_downloads_all_time":2304469,"hf_trending_score":0,"updated_at":"2026-08-14 08:03:18","pricing":{"model_id":"alibaba-qwen3-next-80b-a3b-thinking","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.14,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":1.5,"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":"microsoft-wizardlm-2-8x22b","name":"wizardlm-2-8x22b","display_name":"WizardLM 2 8x22B","description":"Microsoft's most capable WizardLM fine-tune built on a Mixtral 8x22B MoE backbone, targeting highly competitive instruction-following and reasoning performance.","creator":"microsoft","family":"wizardlm","tier":"","version":"2","type":"language","size_in_bn":22,"modalities":{"input":["text"],"output":["text"]},"context_window":65536,"max_output_tokens":8000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-04-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-04-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["deepinfra/microsoft/WizardLM-2-8x22B","huggingface-llm-alpindale-wizard-lm-2-8-22B","microsoft-wizardlm-2-8x22b","microsoft/wizardlm-2-8x22b","novita/microsoft/wizardlm-2-8x22b"],"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-wizardlm-2-8x22b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-08-14","ingestion_date":"2026-08-14","summary":{"currency":"USD","min_input_per_1m":0.48,"max_input_per_1m":0.62,"min_output_per_1m":0.48,"max_output_per_1m":0.62,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":38},"meta":{"updated_at":"2026-08-14","request_id":"0eaf33bb-714a-4e6b-9be9-ba5c9f1b4f32","execution_ms":18}}