{"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":"openai-gpt-oss-20b","name":"gpt-oss-20b","display_name":"GPT OSS 20B","description":"A 20-billion-parameter open-weights GPT model from OpenAI suited for reasoning and tool-use tasks at a smaller, more efficient scale.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":20,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":16,"ids":["@cf/openai/gpt-oss-20b","accounts/fireworks/models/gpt-oss-20b","bedrock_mantle/openai.gpt-oss-20b","databricks/databricks-gpt-oss-20b","deepinfra/openai/gpt-oss-20b","fireworks_ai/accounts/fireworks/models/gpt-oss-20b","gpt-oss-20b","gpt-oss-20b-low","gpt-oss-20b-maas","groq/openai/gpt-oss-20b","lemonade/gpt-oss-20b-mxfp4-GGUF","novita/openai/gpt-oss-20b","ollama/gpt-oss:20b-cloud","openai-gpt-oss-20b","openai-reasoning-gpt-oss-20b","openai.gpt-oss-20b-1:0","openai/gpt-oss-20b","openai/gpt-oss-20b:free","openrouter/openai/gpt-oss-20b","ovhcloud/gpt-oss-20b","publishers/google/models/gpt-oss-20b-maas","replicateopenai/gpt-oss-20b","together_ai/openai/gpt-oss-20b","vertex_ai/openai/gpt-oss-20b-maas","wandb/openai/gpt-oss-20b"],"hf_likes":4552,"hf_downloads":6455272,"hf_downloads_all_time":59707566,"hf_trending_score":12,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-20b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.029,"max_input_per_1m":5,"min_output_per_1m":0.14,"max_output_per_1m":20,"min_cache_read_per_1m":0.0375,"min_cache_write_per_1m":0.007,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":16},"providers":[],"regions":[],"region_info":{}}},{"id":"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":"alibaba-qwen2-5-coder-32b-instruct","name":"qwen2-5-coder-32b-instruct","display_name":"Qwen2.5 Coder 32B Instruct","description":"A 32-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, excelling at code generation, debugging, and explanation across many programming languages.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":false,"adaptive_reasoning":false},"release_date":"2024-11-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["@cf/qwen/qwen2.5-coder-32b-instruct","accounts/fireworks/models/qwen2p5-coder-32b-instruct","accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","alibaba-qwen2-5-coder-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k","huggingface-llm-qwen2-5-coder-32b-instruct","hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct","lambda_ai/qwen25-coder-32b-instruct","nscale/Qwen/Qwen2.5-Coder-32B-Instruct","openrouter/qwen/qwen-2.5-coder-32b-instruct","ovhcloud/Qwen2.5-Coder-32B-Instruct","qwen/qwen-2.5-coder-32b-instruct","qwen2-5-coder-32b-instruct","qwen2.5-coder-32b-instruct"],"hf_likes":2008,"hf_downloads":1257495,"hf_downloads_all_time":5998607,"hf_trending_score":0,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen2-5-coder-32b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.9,"min_output_per_1m":0.1,"max_output_per_1m":1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":9},"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":13,"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":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-1-70b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.12,"max_input_per_1m":2.68,"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":13},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-1-8b-instruct","name":"llama-3-1-8b-instruct","display_name":"Llama 3.1 8B Instruct","description":"Meta's 8B instruction-tuned LLM optimized for fast, cost-effective deployment across multiple cloud regions with strong instruction-following performance.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":8,"modalities":{"input":["image","text"],"output":["text"]},"context_window":200000,"max_output_tokens":128000,"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":21,"ids":["@cf/meta/llama-3.1-8b-instruct","accounts/fireworks/models/full-llama-v3p1-8b-instruct-8b-fp8","accounts/fireworks/models/full-llama-v3p1-8b-instruct-8b-fp8-amd","accounts/fireworks/models/llama-v3p1-8b-instruct","azure_ai/Meta-Llama-3.1-8B-Instruct","databricks/databricks-meta-llama-3-1-8b-instruct","deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct","friendliai/meta-llama-3.1-8b-instruct","groq/llama-3.1-8b-instant","hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct","lambda_ai/llama3.1-8b-instruct","llama-3-1-instruct-8b","meta-llama-3-1-8b-instruct","meta-llama/llama-3.1-8b-instruct","meta-llama/Meta-Llama-3.1-8B-Instruct","meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","meta-textgeneration-llama-3-1-8b-instruct","meta-textgenerationneuron-llama-3-1-8b-instruct","meta.llama3-1-8b-instruct-v1:0","meta.llama3-1-8b-instruct-v1:0:128k","nebius/meta-llama/Meta-Llama-3.1-8B-Instruct","novita/meta-llama/llama-3.1-8b-instruct","nscale/meta-llama/Llama-3.1-8B-Instruct","oci/meta.llama-3.1-8b-instruct","ovhcloud/Llama-3.1-8B-Instruct","perplexity/llama-3.1-8b-instruct","sambanova/Meta-Llama-3.1-8B-Instruct","together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","us.meta.llama3-1-8b-instruct-v1:0","vertex_ai/meta/llama-3.1-8b-instruct-maas","wandb/meta-llama/Llama-3.1-8B-Instruct"],"hf_likes":5731,"hf_downloads":9306502,"hf_downloads_all_time":140394735,"hf_trending_score":24,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-1-8b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.02,"max_input_per_1m":22,"min_output_per_1m":0.03,"max_output_per_1m":22,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","nebius","novita","openrouter"],"provider_count":21},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-mamba-codestral-7b","name":"mamba-codestral-7b","display_name":"Mamba Codestral 7B","description":"A 7B Mamba state-space model variant of Codestral, combining efficient linear-time sequence modeling with code generation.","creator":"mistral","family":"codestral","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":256000,"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":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":1,"ids":["mistral-mamba-codestral-7b","ovhcloud/mamba-codestral-7B-v0.1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"mistral-mamba-codestral-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.19,"max_input_per_1m":0.19,"min_output_per_1m":0.19,"max_output_per_1m":0.19,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["ovhcloud"],"provider_count":1},"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":128000,"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":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":3,"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"],"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-3-2-24b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.075,"max_input_per_1m":0.09,"min_output_per_1m":0.2,"max_output_per_1m":0.28,"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-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":5,"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":"2026-06-13 08:02:30","pricing":{"model_id":"mistral-nemo-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.02,"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":5},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-vl-72b-instruct","name":"qwen2-5-vl-72b-instruct","display_name":"Qwen2.5 VL 72B Instruct","description":"A 72-billion-parameter multimodal vision-language LLM from Alibaba's Qwen2.5-VL series, delivering high-capacity image understanding and visual reasoning.","creator":"alibaba","family":"qwen2_5_vl","tier":"","version":null,"type":"language","size_in_bn":72,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":128000,"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":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":"2025-02-01","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/qwen2p5-vl-72b-instruct","alibaba-qwen2-5-vl-72b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-vl-72b-instruct","nebius/Qwen/Qwen2.5-VL-72B-Instruct","novita/qwen/qwen2.5-vl-72b-instruct","ovhcloud/Qwen2.5-VL-72B-Instruct","qwen/qwen2.5-vl-72b-instruct","qwen2.5-vl-72b-instruct"],"hf_likes":609,"hf_downloads":103451,"hf_downloads_all_time":5812114,"hf_trending_score":1,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen2-5-vl-72b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.13,"max_input_per_1m":2.8,"min_output_per_1m":0.4,"max_output_per_1m":8.4,"min_cache_read_per_1m":0.4,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nebius"],"provider_count":7},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-32b","name":"qwen3-32b","display_name":"Qwen3 32B","description":"A dense 32B-parameter LLM from the Qwen3 series with strong reasoning and tool-use capabilities, suitable for a wide range of language tasks.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":40960,"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":15,"ids":["accounts/fireworks/models/qwen3-32b","alibaba-qwen3-32b","alibaba/qwen-3-32b","cerebras/qwen-3-32b","deepinfra/Qwen/Qwen3-32B","fireworks_ai/accounts/fireworks/models/qwen3-32b","gradient_ai/alibaba-qwen3-32b","groq/qwen/qwen3-32b","huggingface-reasoning-qwen3-32b","lambda_ai/qwen3-32b-fp8","nebius/Qwen/Qwen3-32B","novita/qwen/qwen3-32b-fp8","ovhcloud/Qwen3-32B","qwen.qwen3-32b-v1:0","qwen/qwen3-32b","Qwen/Qwen3-32B","qwen/qwen3-32b-fp8","qwen3-32b","qwen3-32b-instruct","qwen3-32b-instruct-reasoning","sambanova/Qwen3-32B","vercel_ai_gateway/alibaba/qwen-3-32b"],"hf_likes":685,"hf_downloads":2337650,"hf_downloads_all_time":26634596,"hf_trending_score":4,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen3-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.05,"max_input_per_1m":0.9,"min_output_per_1m":0.1,"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":["lambda"],"provider_count":15},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":11},"meta":{"updated_at":"2026-06-13","request_id":"d2379a1a-e1f0-4071-a895-3864033345a7","execution_ms":10}}