{"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":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":"meta-llama-3-3-70b-instruct","name":"llama-3-3-70b-instruct","display_name":"Llama 3.3 70B Instruct","description":"Meta's 70B instruction-tuned LLM from Llama 3.3, optimized for complex instruction-following and deployed across multiple cloud regions.","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":120000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12","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":"2024-12-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":20,"ids":["accounts/fireworks/models/llama-v3p3-70b-instruct","azure_ai/Llama-3.3-70B-Instruct","crusoe/meta-llama/Llama-3.3-70B-Instruct","databricks/databricks-meta-llama-3-3-70b-instruct","deepinfra/meta-llama/Llama-3.3-70B-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct","gradient_ai/llama3.3-70b-instruct","groq/llama-3.3-70b-versatile","hyperbolic/meta-llama/Llama-3.3-70B-Instruct","lambda_ai/llama3.3-70b-instruct-fp8","llama-3-3-instruct-70b","llama-3.3-70b-instruct-maas","meta_llama/Llama-3.3-70B-Instruct","meta-llama-3-3-70b-instruct","meta-llama/llama-3.3-70b-instruct","meta-llama/llama-3.3-70b-instruct:free","meta-textgeneration-llama-3-3-70b-instruct","meta.llama3-3-70b-instruct-v1:0","meta.llama3-3-70b-instruct-v1:0:128k","nebius/meta-llama/Llama-3.3-70B-Instruct","novita/meta-llama/llama-3.3-70b-instruct","nscale/meta-llama/Llama-3.3-70B-Instruct","oci/meta.llama-3.3-70b-instruct","oci/meta.llama-3.3-70b-instruct-fp8-dynamic","ovhcloud/Meta-Llama-3_3-70B-Instruct","publishers/google/models/llama-3.3-70b-instruct-maas","publishers/meta/models/llama-3.3-70b-instruct-maas","sambanova/Meta-Llama-3.3-70B-Instruct","together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free","us.meta.llama3-3-70b-instruct-v1:0","wandb/meta-llama/Llama-3.3-70B-Instruct","watsonx/meta-llama/llama-3-3-70b-instruct"],"hf_likes":2731,"hf_downloads":496024,"hf_downloads_all_time":10779619,"hf_trending_score":1.5,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-3-70b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":71,"min_output_per_1m":0.2,"max_output_per_1m":71,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":20},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-4-small-h","name":"granite-4-small-h","display_name":"Granite 4 Small H","description":"A small-scale LLM from IBM's Granite 4 family with an H-suffix designation, balancing efficiency and instruction-following capability.","creator":"ibm","family":"granite","tier":"small","version":"4","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":20480,"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":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":["granite-4-0-h-small","ibm-granite-4-small-h","watsonx/ibm/granite-4-h-small"],"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-4-small-h","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.06,"max_input_per_1m":0.06,"min_output_per_1m":0.25,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-large","name":"mistral-large","display_name":"Mistral Large","description":"Mistral AI's flagship large language model excelling at reasoning, code generation, JSON output, and multilingual tasks.","creator":"mistral","family":"mistral","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","text"],"output":["text"]},"context_window":262144,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-11-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-02-26","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["azure_ai/mistral-large","azure_ai/mistral-large-2407","azure_ai/mistral-large-latest","azure/mistral-large-2402","azure/mistral-large-latest","bedrock/eu-west-3/mistral.mistral-large-2402-v1:0","bedrock/us-east-1/mistral.mistral-large-2402-v1:0","bedrock/us-west-2/mistral.mistral-large-2402-v1:0","mistral-large","mistral-large-2407","mistral-large-2512","mistral-large-latest","mistral.mistral-large-2402-v1:0","mistral.mistral-large-2407-v1:0","mistral/mistral-large-2402","mistral/mistral-large-2407","mistral/mistral-large-2411","mistral/mistral-large-2512","mistral/mistral-large-latest","mistralai/mistral-large","mistralai/mistral-large-2407","mistralai/mistral-large-2411","mistralai/mistral-large-2512","openrouter/mistralai/mistral-large","openrouter/mistralai/mistral-large-2512","snowflake/mistral-large","vercel_ai_gateway/mistral/mistral-large","vertex_ai/mistral-large-2411","vertex_ai/mistral-large@2407","vertex_ai/mistral-large@2411-001","vertex_ai/mistral-large@latest","watsonx/mistralai/mistral-large"],"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":"mistral-large","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":8,"min_output_per_1m":1.5,"max_output_per_1m":24,"min_cache_read_per_1m":0.05,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-medium","name":"mistral-medium","display_name":"Mistral Medium","description":"Mistral AI's mid-tier enterprise language model with vision and tool-use capabilities, delivering frontier performance at reduced cost.","creator":"mistral","family":"mistral","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image"],"output":["text"]},"context_window":131072,"max_output_tokens":64000,"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":true,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2025-05-07","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["azure_ai/mistral-medium-2505","mistral-medium","mistral/mistral-medium","mistral/mistral-medium-2312","mistral/mistral-medium-2505","mistral/mistral-medium-latest","watsonx/mistralai/mistral-medium-2505"],"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":"mistral-medium","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":3,"min_output_per_1m":2,"max_output_per_1m":10,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["azure_aifoundry","vercel_ai_gateway"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-small","name":"mistral-small","display_name":"Mistral Small","description":"A compact yet capable LLM from Mistral balancing efficiency and performance across reasoning, vision, and instruction-following tasks.","creator":"mistral","family":"mistral","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":262144,"max_output_tokens":8191,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Mistral","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":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-05-24","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["azure_ai/mistral-small","azure_ai/mistral-small-2503","mistral-small","mistral-small-2402","mistral-small-2503","mistral-small-2603","mistral-small-latest","mistral.mistral-small-2402-v1:0","mistral/mistral-small","mistral/mistral-small-latest","mistralai/mistral-small-2603","publishers/google/models/mistral-small-2503","vercel_ai_gateway/mistral/mistral-small","vertex_ai/mistral-small-2503","vertex_ai/mistral-small-2503@001","watsonx/mistralai/mistral-small-2503"],"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":"mistral-small","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":1,"min_output_per_1m":0.3,"max_output_per_1m":3,"min_cache_read_per_1m":0.015,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx","vercel_ai_gateway"],"provider_count":7},"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":"sdaia-allam-1-13b-instruct","name":"allam-1-13b-instruct","display_name":"Allam 1 13B Instruct","description":"A 13-billion-parameter Arabic-focused instruction-tuned language model developed by SDAIA, designed for Arabic NLP tasks and bilingual Arabic-English use cases.","creator":"sdaia","family":"allam","tier":"","version":"1","type":"language","size_in_bn":13,"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":["sdaia-allam-1-13b-instruct","watsonx/sdaia/allam-1-13b-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":"sdaia-allam-1-13b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":1.8,"max_input_per_1m":1.8,"min_output_per_1m":1.8,"max_output_per_1m":1.8,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"google-flan-t5-3b-xl","name":"flan-t5-3b-xl","display_name":"Flan-T5 3B XL","description":"3B-parameter XL variant of Flan-T5, an instruction-tuned T5 model excelling at zero-shot and few-shot text-to-text generation tasks.","creator":"google","family":"flan-t5","tier":"","version":null,"type":"language","size_in_bn":3,"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":["google-flan-t5-3b-xl","watsonx/google/flan-t5-xl-3b"],"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-flan-t5-3b-xl","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":0.6,"min_output_per_1m":0.6,"max_output_per_1m":0.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-2-13b-chat","name":"granite-2-13b-chat","display_name":"Granite 2 13B Chat","description":"IBM's 13B-parameter Granite 2 chat model fine-tuned for conversational interactions and enterprise dialogue applications.","creator":"ibm","family":"granite","tier":"","version":"2","type":"language","size_in_bn":13,"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":["ibm-granite-2-13b-chat","watsonx/ibm/granite-13b-chat-v2"],"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-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":0.6,"max_input_per_1m":0.6,"min_output_per_1m":0.6,"max_output_per_1m":0.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-2-13b-instruct","name":"granite-2-13b-instruct","display_name":"Granite 2 13B Instruct","description":"IBM's 13B-parameter Granite 2 instruction-following model optimized for enterprise task completion and structured text generation.","creator":"ibm","family":"granite","tier":"","version":"2","type":"language","size_in_bn":13,"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":["ibm-granite-2-13b-instruct","watsonx/ibm/granite-13b-instruct-v2"],"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-2-13b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.6,"max_input_per_1m":0.6,"min_output_per_1m":0.6,"max_output_per_1m":0.6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-3-8b-instruct","name":"granite-3-8b-instruct","display_name":"Granite 3 8B Instruct","description":"IBM's 8B-parameter Granite 3.0 instruction model for enterprise use, excelling in multilingual and code tasks under an Apache 2.0 license.","creator":"ibm","family":"granite","tier":"","version":"3","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":1024,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["granite-3-0-8b-instruct","ibm-granite-3-8b-instruct","watsonx/ibm/granite-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-3-8b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-guardian-3-2-2b","name":"granite-guardian-3-2-2b","display_name":"Granite Guardian 3.2 2B","description":"A 2B-parameter safety-focused LLM from IBM's Granite Guardian series, designed to detect and mitigate harmful or policy-violating content.","creator":"ibm","family":"granite","tier":"","version":"3-2","type":"language","size_in_bn":2,"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":["ibm-granite-guardian-3-2-2b","watsonx/ibm/granite-guardian-3-2-2b"],"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-guardian-3-2-2b","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":0.1,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-guardian-3-3-8b","name":"granite-guardian-3-3-8b","display_name":"Granite Guardian 3.3 8B","description":"An 8B-parameter safety-focused LLM from IBM's Granite Guardian series for content moderation and risk detection in enterprise deployments.","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":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":["ibm-granite-guardian-3-3-8b","watsonx/ibm/granite-guardian-3-3-8b"],"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":"ibm-granite-guardian-3-3-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":0.2,"min_output_per_1m":0.2,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-ttm-r2-1024-96","name":"granite-ttm-r2-1024-96","display_name":"Granite TTM R2 1024 96","description":"A time-series foundation model from IBM's Granite TTM R2 series with a 1024-token context and 96-step prediction horizon.","creator":"ibm","family":"granite","tier":"","version":"r2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":512,"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":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":["ibm-granite-ttm-r2-1024-96","watsonx/ibm/granite-ttm-1024-96-r2"],"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-ttm-r2-1024-96","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.38,"max_input_per_1m":0.38,"min_output_per_1m":0.38,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-ttm-r2-1536-96","name":"granite-ttm-r2-1536-96","display_name":"Granite TTM R2 1536 96","description":"A time-series foundation model from IBM's Granite TTM R2 series with a 1536-token context and 96-step prediction horizon.","creator":"ibm","family":"granite","tier":"","version":"r2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":512,"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":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":["ibm-granite-ttm-r2-1536-96","watsonx/ibm/granite-ttm-1536-96-r2"],"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-ttm-r2-1536-96","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.38,"max_input_per_1m":0.38,"min_output_per_1m":0.38,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-ttm-r2-512-96","name":"granite-ttm-r2-512-96","display_name":"Granite TTM R2 512 96","description":"A time-series foundation model from IBM's Granite TTM R2 series with a 512-token context and 96-step prediction horizon.","creator":"ibm","family":"granite","tier":"","version":"r2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":512,"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":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":["ibm-granite-ttm-r2-512-96","watsonx/ibm/granite-ttm-512-96-r2"],"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-ttm-r2-512-96","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.38,"max_input_per_1m":0.38,"min_output_per_1m":0.38,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"ibm-granite-vision-3-2-2b","name":"granite-vision-3-2-2b","display_name":"Granite Vision 3.2 2B","description":"A 2B-parameter multimodal vision-language model from IBM's Granite 3.2 series, supporting image understanding alongside text tasks.","creator":"ibm","family":"granite","tier":"","version":"3-2","type":"language","size_in_bn":2,"modalities":{"input":["image"],"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":["ibm-granite-vision-3-2-2b","watsonx/ibm/granite-vision-3-2-2b"],"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-vision-3-2-2b","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":0.1,"max_output_per_1m":0.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"core42-jais-13b-chat","name":"jais-13b-chat","display_name":"Jais 13B Chat","description":"A 13B-parameter Arabic-English bilingual chat LLM from Core42, designed for conversational tasks in both Arabic and English.","creator":"core42","family":"jais","tier":"","version":null,"type":"language","size_in_bn":13,"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":["core42-jais-13b-chat","watsonx/core42/jais-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":"core42-jais-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":0.5,"max_input_per_1m":0.5,"min_output_per_1m":2,"max_output_per_1m":2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-2-11b-vision-instruct","name":"meta-llama-3-2-11b-vision-instruct","display_name":"Llama 3.2 11B Vision Instruct","description":"Meta's 11B instruction-tuned vision-language model optimized for visual recognition, image reasoning, and captioning with multimodal input support.","creator":"meta","family":"mllama","tier":"","version":"3-2","type":"language","size_in_bn":11,"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":false,"adaptive_reasoning":false},"release_date":"2024-09-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":8,"ids":["@cf/meta/llama-3.2-11b-vision-instruct","accounts/fireworks/models/llama-v3p2-11b-vision-instruct","azure_ai/Llama-3.2-11B-Vision-Instruct","deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct","lambda_ai/llama3.2-11b-vision-instruct","meta-llama-3-2-11b-vision-instruct","meta-llama/llama-3.2-11b-vision-instruct","meta-llama/Llama-3.2-11B-Vision-Instruct","meta-vlm-llama-3-2-11b-vision-instruct","oci/meta.llama-3.2-11b-vision-instruct","watsonx/meta-llama/llama-3-2-11b-vision-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":"meta-llama-3-2-11b-vision-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.015,"max_input_per_1m":2,"min_output_per_1m":0.025,"max_output_per_1m":2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":8},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-2-90b-vision-instruct","name":"meta-llama-3-2-90b-vision-instruct","display_name":"Llama 3.2 90B Vision Instruct","description":"Meta's 90B instruction-tuned vision-language model from Llama 3.2, optimized for high-capacity visual recognition, reasoning, and captioning tasks.","creator":"meta","family":"mllama","tier":"","version":"3-2","type":"language","size_in_bn":90,"modalities":{"input":["image"],"output":["text"]},"context_window":128000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":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":4,"ids":["accounts/fireworks/models/llama-v3p2-90b-vision-instruct","azure_ai/Llama-3.2-90B-Vision-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct","meta-llama-3-2-90b-vision-instruct","meta-vlm-llama-3-2-90b-vision-instruct","oci/meta.llama-3.2-90b-vision-instruct","vertex_ai/meta/llama-3.2-90b-vision-instruct-maas","watsonx/meta-llama/llama-3-2-90b-vision-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":"meta-llama-3-2-90b-vision-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.9,"max_input_per_1m":2.04,"min_output_per_1m":0.9,"max_output_per_1m":2.04,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["fireworks_ai"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-4-maverick-17b","name":"llama-4-maverick-17b","display_name":"Llama 4 Maverick 17B","description":"Meta's Llama 4 Maverick pre-trained MoE model at the 17B active-parameter scale, supporting natively multimodal text and image inputs.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":17,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"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":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":["meta-llama-4-maverick-17b","watsonx/meta-llama/llama-4-maverick-17b"],"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-4-maverick-17b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.35,"max_input_per_1m":0.35,"min_output_per_1m":1.4,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llamaguard-3-11b-vision","name":"meta-llamaguard-3-11b-vision","display_name":"LlamaGuard 3 11B Vision","description":"An 11B vision-language safety classifier capable of moderating both text and image content in multimodal LLM interactions.","creator":"meta","family":"llama-guard","tier":"","version":"3","type":"language","size_in_bn":11,"modalities":{"input":["image"],"output":["text"]},"context_window":128000,"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":["meta-llamaguard-3-11b-vision","meta-vlm-llama-guard-3-11b-vision","watsonx/meta-llama/llama-guard-3-11b-vision"],"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-llamaguard-3-11b-vision","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.35,"max_input_per_1m":0.35,"min_output_per_1m":0.35,"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":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-small-3-1-24b-instruct","name":"mistral-small-3-1-24b-instruct","display_name":"Mistral Small 3.1 24B Instruct","description":"An instruction-tuned 24B-parameter multimodal LLM from Mistral, combining vision understanding with strong text generation performance.","creator":"mistral","family":"mistral3","tier":"","version":"3-1","type":"language","size_in_bn":24,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":null,"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":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":"2025-03-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["@cf/mistralai/mistral-small-3.1-24b-instruct","mistral-small-3-1-24b-instruct","mistralai/mistral-small-3.1-24b-instruct","openrouter/mistralai/mistral-small-3.1-24b-instruct","watsonx/mistralai/mistral-small-3-1-24b-instruct-2503"],"hf_likes":1355,"hf_downloads":525643,"hf_downloads_all_time":2775582,"hf_trending_score":0,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"mistral-small-3-1-24b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.1,"max_input_per_1m":0.351,"min_output_per_1m":0.3,"max_output_per_1m":0.555,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"bigscience-mt0-13b-xxl","name":"mt0-13b-xxl","display_name":"mT0 13B XXL","description":"A 13B parameter multilingual instruction-tuned model from BigScience based on mT5, designed for zero-shot cross-lingual task generalization.","creator":"bigscience","family":"mt0","tier":"","version":null,"type":"language","size_in_bn":13,"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":["bigscience-mt0-13b-xxl","watsonx/bigscience/mt0-xxl-13b"],"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":"bigscience-mt0-13b-xxl","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":0.5,"min_output_per_1m":2,"max_output_per_1m":2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ibm_watsonx"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-pixtral-12b","name":"mistral-pixtral-12b","display_name":"Pixtral 12B","description":"A 12B-parameter multimodal LLM from Mistral supporting vision and tool-use, capable of processing both images and text for image-text-to-text tasks.","creator":"mistral","family":"pixtral","tier":"","version":null,"type":"language","size_in_bn":12,"modalities":{"input":["image"],"output":["text"]},"context_window":128000,"max_output_tokens":4000,"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":"2024-09-01","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["huggingface-vlm-mistral-pixtral-12b-2409","mistral-pixtral-12b","mistral/pixtral-12b","mistral/pixtral-12b-2409","vercel_ai_gateway/mistral/pixtral-12b","watsonx/mistralai/pixtral-12b-2409"],"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":"mistral-pixtral-12b","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":0.35,"min_output_per_1m":0.15,"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":["mistral","vercel_ai_gateway"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-whisper-3-large-turbo","name":"whisper-3-large-turbo","display_name":"Whisper 3 Large Turbo","description":"A faster, distilled variant of Whisper Large V3 that maintains strong multilingual ASR accuracy with reduced inference latency.","creator":"openai","family":"whisper","tier":"","version":"3","type":"speech-to-text","size_in_bn":0.809,"modalities":{"input":["audio"],"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":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":["@cf/openai/whisper-large-v3-turbo","groq/whisper-large-v3-turbo","huggingface-asr-whisper-large-v3-turbo","openai-whisper-3-large-turbo","openai/whisper-large-v3-turbo","watsonx/whisper-large-v3-turbo"],"hf_likes":3012,"hf_downloads":7277395,"hf_downloads_all_time":83858224,"hf_trending_score":10,"updated_at":"2026-06-13 08:02:30"}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":27},"meta":{"updated_at":"2026-06-13","request_id":"14521635-c5c7-4b90-8c4c-c0f0c237f422","execution_ms":10}}