{"data":[{"id":"alibaba-qwq-32b","name":"qwq-32b","display_name":"QwQ 32B","description":"A 32B reasoning-focused LLM from Alibaba's Qwen team, designed to match frontier closed-model performance on complex reasoning and problem-solving tasks.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":32,"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":["default"],"tokenizer":"Qwen","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":"2025-03-05","earliest_deprecation_date":"2026-04-29","deprecated":false,"has_pricing":true,"provider_count":9,"ids":["@cf/qwen/qwq-32b","accounts/fireworks/models/qwq-32b","alibaba-qwq-32b","deepinfra/Qwen/QwQ-32B","fireworks_ai/accounts/fireworks/models/qwq-32b","huggingface-llm-qwq-32b","hyperbolic/Qwen/QwQ-32B","nebius/Qwen/QwQ-32B","nscale/Qwen/QwQ-32B","qwen/qwq-32b","qwq-32b","sambanova/QwQ-32B"],"hf_likes":2906,"hf_downloads":73024,"hf_downloads_all_time":2875672,"hf_trending_score":1,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwq-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.15,"max_input_per_1m":0.9,"min_output_per_1m":0.2,"max_output_per_1m":1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra","nebius"],"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":32768,"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":8,"ids":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","accounts/fireworks/models/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":"2026-06-13 08:02:30","pricing":{"model_id":"deepseek-r1-distill-qwen-32b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.15,"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":8},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-qwen-14b","name":"deepseek-r1-distill-qwen-14b","display_name":"DeepSeek R1 Distill Qwen 14B","description":"A 14B Qwen-based model distilled from DeepSeek R1, balancing strong reasoning performance with moderate computational requirements.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","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":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":false,"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":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/deepseek-r1-distill-qwen-14b","deepseek-llm-r1-distill-qwen-14b","deepseek-r1-distill-qwen-14b","deepseek/deepseek-r1-distill-qwen-14b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-14b","novita/deepseek/deepseek-r1-distill-qwen-14b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"],"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":"deepseek-r1-distill-qwen-14b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.07,"max_input_per_1m":0.2,"min_output_per_1m":0.07,"max_output_per_1m":0.431,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":5},"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":"deepseek-r1-distill-llama-8b","name":"deepseek-r1-distill-llama-8b","display_name":"DeepSeek R1 Distill Llama 8B","description":"A compact 8B Llama-based model distilled from DeepSeek R1, delivering strong reasoning performance in a lightweight architecture.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":8,"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":3,"ids":["accounts/fireworks/models/deepseek-r1-distill-llama-8b","deepseek-llm-r1-distill-llama-8b","deepseek-r1-distill-llama-8b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-8b","nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-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":"deepseek-r1-distill-llama-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.025,"max_input_per_1m":0.2,"min_output_per_1m":0.025,"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":["nscale"],"provider_count":3},"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":"alibaba-qwen2-5-coder-7b-instruct","name":"qwen2-5-coder-7b-instruct","display_name":"Qwen2.5 Coder 7B Instruct","description":"A 7-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, designed for responsive code generation and developer assistance.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"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":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen2p5-coder-7b-instruct","alibaba-qwen2-5-coder-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct","huggingface-llm-qwen2-5-coder-7b-instruct","nscale/Qwen/Qwen2.5-Coder-7B-Instruct","qwen2-5-coder-7b-instruct","qwen2.5-coder-7b-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":"alibaba-qwen2-5-coder-7b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.2,"min_output_per_1m":0.03,"max_output_per_1m":0.287,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","nscale"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"mistral-mixtral-8x22b-instruct","name":"mistral-mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","description":"The instruction-tuned version of Mistral AI's Mixtral 8x22B MoE model, optimized for following complex instructions and multi-turn dialogue.","creator":"mistral","family":"mixtral","tier":"","version":null,"type":"language","size_in_bn":22,"modalities":{"input":["text"],"output":["text"]},"context_window":65536,"max_output_tokens":2048,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-01-31","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":"2024-04-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/mixtral-8x22b-instruct","anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf","huggingface-llm-mistralai-mixtral-8x22B-instruct-v0-1","mistral-8x22b-instruct","mistral-mixtral-8x22b-instruct","mistral/mixtral-8x22b-instruct","mistralai/mixtral-8x22b-instruct","nscale/mistralai/mixtral-8x22b-instruct-v0.1","ollama/mixtral-8x22B-Instruct-v0.1","openrouter/mistralai/mixtral-8x22b-instruct","vercel_ai_gateway/mistral/mixtral-8x22b-instruct"],"hf_likes":748,"hf_downloads":28279,"hf_downloads_all_time":6052030,"hf_trending_score":0,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"mistral-mixtral-8x22b-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":2,"min_output_per_1m":0.6,"max_output_per_1m":6,"min_cache_read_per_1m":0.2,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["nscale"],"provider_count":6},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-qwen-1-5b","name":"deepseek-r1-distill-qwen-1-5b","display_name":"DeepSeek R1 Distill Qwen 1.5B","description":"A 1.5B Qwen-based model distilled from DeepSeek R1's reasoning chains, offering chain-of-thought capabilities in an extremely compact form factor.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":1.5,"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":3,"ids":["accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b","deepseek-llm-r1-distill-qwen-1-5b","deepseek-r1-distill-qwen-1-5b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"],"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":"deepseek-r1-distill-qwen-1-5b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.09,"max_input_per_1m":0.1,"min_output_per_1m":0.09,"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":["nscale"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-distill-qwen-7b","name":"deepseek-r1-distill-qwen-7b","display_name":"DeepSeek R1 Distill Qwen 7B","description":"A 7B Qwen-based model distilled from DeepSeek R1, providing efficient reasoning capabilities suitable for resource-constrained deployments.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":4,"ids":["accounts/fireworks/models/deepseek-r1-distill-qwen-7b","deepseek-llm-r1-distill-qwen-7b","deepseek-r1-distill-qwen-7b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-7b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"],"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":"deepseek-r1-distill-qwen-7b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.072,"max_input_per_1m":0.2,"min_output_per_1m":0.144,"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":["alibaba_qwen"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-4-17b-scout-instruct","name":"llama-4-17b-scout-instruct","display_name":"Llama 4 17B Scout Instruct","description":"Meta's Llama 4 Scout instruction-tuned MoE model with 17B active parameters, optimized for efficient multimodal inference with a lean expert configuration.","creator":"meta","family":"llama","tier":"","version":"4","type":"language","size_in_bn":17,"modalities":{"input":["image","text"],"output":["text"]},"context_window":10000000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08","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":["@cf/meta/llama-4-scout-17b-16e-instruct","azure_ai/Llama-4-Scout-17B-16E-Instruct","deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","groq/meta-llama/llama-4-scout-17b-16e-instruct","lambda_ai/llama-4-scout-17b-16e-instruct","llama-4-scout-17b-16e-instruct-maas","meta-llama-4-17b-scout-instruct","meta-llama/llama-4-scout-17b-16e-instruct","meta-llama/Llama-4-Scout-17B-16E-Instruct","novita/meta-llama/llama-4-scout-17b-16e-instruct","nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct","publishers/google/models/llama-4-scout-17b-16e-instruct-maas","sambanova/Llama-4-Scout-17B-16E-Instruct","together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct","vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas","vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas","wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct"],"hf_likes":1272,"hf_downloads":390765,"hf_downloads_all_time":5421895,"hf_trending_score":0.5,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-4-17b-scout-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":17,"min_output_per_1m":0.1,"max_output_per_1m":66,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["lambda"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen2-5-coder-3b-instruct","name":"qwen2-5-coder-3b-instruct","display_name":"Qwen2.5 Coder 3B Instruct","description":"A 3-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, suitable for compact coding assistant applications.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":3,"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":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":["accounts/fireworks/models/qwen2p5-coder-3b-instruct","alibaba-qwen2-5-coder-3b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct","nscale/Qwen/Qwen2.5-Coder-3B-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":"alibaba-qwen2-5-coder-3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.01,"max_input_per_1m":0.1,"min_output_per_1m":0.03,"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":["huggingface","nscale"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":13},"meta":{"updated_at":"2026-06-13","request_id":"fac31917-7ef4-42d8-b4b3-42e159632db6","execution_ms":39}}