{"data":[{"id":"moonshot-kimi-k2-5","name":"kimi-k2-5","display_name":"Kimi K2.5","description":"An updated iteration of Kimi K2 with enhanced reasoning, vision, and tool-use capabilities, supporting implicit caching for efficient inference.","creator":"moonshot","family":"kimi_k25","tier":"","version":"k2-5","type":"language","size_in_bn":1058.589,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":98304,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-01-27","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["@cf/moonshotai/kimi-k2.5","accounts/fireworks/models/kimi-k2p5","azure_ai/kimi-k2.5","baseten/moonshotai/Kimi-K2.5","bedrock/ap-northeast-1/moonshotai.kimi-k2.5","bedrock/ap-south-1/moonshotai.kimi-k2.5","bedrock/ap-southeast-3/moonshotai.kimi-k2.5","bedrock/eu-north-1/moonshotai.kimi-k2.5","bedrock/moonshotai.kimi-k2.5","bedrock/sa-east-1/moonshotai.kimi-k2.5","bedrock/us-east-1/moonshotai.kimi-k2.5","bedrock/us-east-2/moonshotai.kimi-k2.5","bedrock/us-west-2/moonshotai.kimi-k2.5","fireworks_ai/accounts/fireworks/models/kimi-k2p5","fireworks_ai/kimi-k2p5","huggingface-llm-kimi-k2-5","kimi-k2-5","kimi-k2-5-non-reasoning","kimi-k2.5","moonshot-kimi-k2-5","moonshot/kimi-k2.5","moonshotai.kimi-k2.5","moonshotai/kimi-k2.5","moonshotai/Kimi-K2.5","openrouter/moonshotai/kimi-k2.5","together_ai/moonshotai/Kimi-K2.5","wandb/moonshotai/Kimi-K2.5"],"hf_likes":2753,"hf_downloads":5222216,"hf_downloads_all_time":9851195,"hf_trending_score":34,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"moonshot-kimi-k2-5","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.375,"max_input_per_1m":0.6,"min_output_per_1m":2.025,"max_output_per_1m":3.011,"min_cache_read_per_1m":0.1,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":12},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-5-397b-a17b","name":"qwen3-5-397b-a17b","display_name":"Qwen3.5 397B A17B","description":"Alibaba's largest Qwen3.5 MoE model with 397B total parameters and 17B activated per token, targeting maximum capability for complex reasoning and generation.","creator":"alibaba","family":"qwen3_5_moe","tier":"","version":null,"type":"language","size_in_bn":397,"modalities":{"input":["image","text","video"],"output":["text"]},"context_window":262144,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"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":"2026-02-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/qwen3p5-397b-a17b","alibaba-qwen3-5-397b-a17b","openrouter/qwen/qwen3.5-397b-a17b","qwen/qwen3.5-397b-a17b","Qwen/Qwen3.5-397B-A17B","qwen3-5-397b-a17b","qwen3-5-397b-a17b-non-reasoning","qwen3.5-397b-a17b","together_ai/Qwen/Qwen3.5-397B-A17B"],"hf_likes":1462,"hf_downloads":710153,"hf_downloads_all_time":2631436,"hf_trending_score":11,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen3-5-397b-a17b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.39,"max_input_per_1m":0.71,"min_output_per_1m":2.34,"max_output_per_1m":4.25,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-7","name":"glm-4-7","display_name":"GLM-4.7","description":"A multilingual MoE LLM from Z AI designed for complex reasoning, agentic coding, and tool use, building on the GLM-4.6 architecture.","creator":"zhipu","family":"glm4_moe","tier":"","version":"4-7","type":"language","size_in_bn":358.338,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":204800,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-22","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":13,"ids":["accounts/fireworks/models/glm-4p7","baseten/zai-org/GLM-4.7","cerebras/zai-glm-4.7","fireworks_ai/accounts/fireworks/models/glm-4p7","fireworks_ai/glm-4p7","glm-4-7","glm-4-7-251222","glm-4-7-non-reasoning","glm-4.7","glm-4.7-maas","novita/zai-org/glm-4.7","openrouter/z-ai/glm-4.7","publishers/google/models/glm-4.7-maas","together_ai/zai-org/GLM-4.7","vertex_ai/zai-org/glm-4.7-maas","z-ai/glm-4.7","zai-org/glm-4.7","zai-org/GLM-4.7","zai.glm-4.7","zai/glm-4.7","zhipu-glm-4-7"],"hf_likes":2026,"hf_downloads":117151,"hf_downloads_all_time":436300,"hf_trending_score":4,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"zhipu-glm-4-7","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":2.25,"min_output_per_1m":1.75,"max_output_per_1m":2.75,"min_cache_read_per_1m":0.08,"min_cache_write_per_1m":0.06,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":13},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":21,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","cerebras/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sambanova/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"openai-gpt-oss-120b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.039,"max_input_per_1m":15,"min_output_per_1m":0.18,"max_output_per_1m":60,"min_cache_read_per_1m":0.075,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":21},"providers":[],"regions":[],"region_info":{}}},{"id":"openai-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":"alibaba-qwen3-next-80b-a3b-instruct","name":"qwen3-next-80b-a3b-instruct","display_name":"Qwen3 Next 80B A3B Instruct","description":"An instruction-tuned Qwen3 Next MoE model with 80B total and 3B activated parameters, optimized for text generation and conversational tasks.","creator":"alibaba","family":"qwen3_next","tier":"","version":null,"type":"language","size_in_bn":80,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-09-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-09-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3-next-80b-a3b-instruct","alibaba-qwen3-next-80b-a3b-instruct","alibaba/qwen3-next-80b-a3b-instruct","dashscope/qwen3-next-80b-a3b-instruct","deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct","huggingface-reasoning-qwen3-next-80b-a3b-instruct","novita/qwen/qwen3-next-80b-a3b-instruct","qwen/qwen3-next-80b-a3b-instruct","Qwen/Qwen3-Next-80B-A3B-Instruct","qwen/qwen3-next-80b-a3b-instruct:free","qwen3-next-80b-a3b-instruct","together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct"],"hf_likes":1012,"hf_downloads":292470,"hf_downloads_all_time":14864763,"hf_trending_score":4,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen3-next-80b-a3b-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.09,"max_input_per_1m":0.9,"min_output_per_1m":0.9,"max_output_per_1m":1.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1","name":"r1","display_name":"DeepSeek R1","description":"DeepSeek's flagship reasoning-focused LLM with strong performance in mathematics, coding, and logical inference, comparable to leading closed-source models.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":684.531,"modalities":{"input":["text"],"output":["text"]},"context_window":163840,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-01-20","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":14,"ids":["accounts/fireworks/models/deepseek-r1","azure_ai/deepseek-r1","deepinfra/deepseek-ai/DeepSeek-R1","deepseek-llm-r1","deepseek-r1","deepseek-r1-0120","deepseek-r1-qwen3-8b","deepseek-r1685","deepseek-reasoner","deepseek.r1-v1:0","deepseek/deepseek-r1","deepseek/deepseek-reasoner","fireworks_ai/accounts/fireworks/models/deepseek-r1","hyperbolic/deepseek-ai/DeepSeek-R1","nebius/deepseek-ai/DeepSeek-R1","openrouter/deepseek/deepseek-r1","replicate/deepseek-ai/deepseek-r1","sambanova/DeepSeek-R1","snowflake/deepseek-r1","together_ai/deepseek-ai/DeepSeek-R1","us.deepseek.r1-v1:0","vercel_ai_gateway/deepseek/deepseek-r1"],"hf_likes":13288,"hf_downloads":4020320,"hf_downloads_all_time":20204112,"hf_trending_score":20,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"deepseek-r1","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.28,"max_input_per_1m":5,"min_output_per_1m":0.4,"max_output_per_1m":10,"min_cache_read_per_1m":0.028,"min_cache_write_per_1m":null,"min_reasoning_per_1m":10,"cheapest_providers":["deepseek"],"provider_count":14},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-1-405b-instruct","name":"llama-3-1-405b-instruct","display_name":"Llama 3.1 405B Instruct","description":"Meta's 405B instruction-tuned LLM optimized for following complex instructions, with FP8 quantization for efficient large-scale inference.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":405,"modalities":{"input":["image","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":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":"2024-07-23","earliest_deprecation_date":"2026-07","deprecated":false,"has_pricing":true,"provider_count":11,"ids":["accounts/fireworks/models/llama-v3p1-405b-instruct","azure_ai/Meta-Llama-3.1-405B-Instruct","databricks/databricks-meta-llama-3-1-405b-instruct","fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct","hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct","lambda_ai/llama3.1-405b-instruct-fp8","llama-3-1-instruct-405b","meta-llama-3-1-405b-instruct","meta-textgeneration-llama-3-1-405b-instruct-fp8","meta.llama3-1-405b-instruct-v1:0","nebius/meta-llama/Meta-Llama-3.1-405B-Instruct","oci/meta.llama-3.1-405b-instruct","sambanova/Meta-Llama-3.1-405B-Instruct","together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","us.meta.llama3-1-405b-instruct-v1:0","vertex_ai/meta/llama-3.1-405b-instruct-maas"],"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-3-1-405b-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":10.68,"min_output_per_1m":0.3,"max_output_per_1m":16,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-v3","name":"v3","display_name":"DeepSeek V3","description":"DeepSeek's third-generation MoE LLM with 671B total parameters (37B activated per token), excelling at coding, reasoning, and tool use.","creator":"deepseek","family":"deepseek-v3","tier":"","version":"3.0","type":"language","size_in_bn":684.531,"modalities":{"input":["image","text"],"output":["text"]},"context_window":163840,"max_output_tokens":81920,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"DeepSeek","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-12-26","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":11,"ids":["accounts/fireworks/models/deepseek-v3","azure_ai/deepseek-v3","deepinfra/deepseek-ai/DeepSeek-V3","deepseek-ai/DeepSeek-V3","deepseek-chat","deepseek-v3","deepseek.v3-v1:0","deepseek/deepseek_v3","deepseek/deepseek-chat","deepseek/deepseek-v3","fireworks_ai/accounts/fireworks/models/deepseek-v3","hyperbolic/deepseek-ai/DeepSeek-V3","nebius/deepseek-ai/DeepSeek-V3","openrouter/deepseek/deepseek-chat","replicate/deepseek-ai/deepseek-v3","together_ai/deepseek-ai/DeepSeek-V3","vercel_ai_gateway/deepseek/deepseek-v3"],"hf_likes":4056,"hf_downloads":882009,"hf_downloads_all_time":15156328,"hf_trending_score":4,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"deepseek-v3","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.2,"max_input_per_1m":1.45,"min_output_per_1m":0.2,"max_output_per_1m":4.56,"min_cache_read_per_1m":0.028,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["hyperbolic"],"provider_count":11},"providers":[],"regions":[],"region_info":{}}},{"id":"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":"baai-bge-1-5-base-en","name":"bge-1-5-base-en","display_name":"BGE Base EN V1.5","description":"A base-size English text embedding model from BAAI's BGE series, optimized for sentence similarity and semantic search tasks.","creator":"baai","family":"embed","tier":"","version":"1-5","type":"embedding","size_in_bn":0.109,"modalities":{"input":["text"],"output":["embedding"]},"context_window":153600,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[768],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["@cf/baai/bge-base-en-v1.5","baai-bge-1-5-base-en","BAAI/bge-base-en-v1.5","huggingface-sentencesimilarity-bge-base-en-v1-5","huggingface-textembedding-bge-base-en-v1-5","together_ai/baai/bge-base-en-v1.5","together_ai/BAAI/bge-base-en-v1.5"],"hf_likes":411,"hf_downloads":6725168,"hf_downloads_all_time":519748129,"hf_trending_score":1,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"baai-bge-1-5-base-en","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.008,"max_input_per_1m":0.067,"min_output_per_1m":null,"max_output_per_1m":null,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"deepseek-r1-528b","name":"deepseek-r1-528b","display_name":"DeepSeek R1 528B","description":"A 528B-parameter variant of the DeepSeek R1 reasoning model, offering large-scale chain-of-thought reasoning capabilities.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":528,"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":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":2,"ids":["deepseek-r1-0528685","deepseek-r1-528b","together_ai/deepseek-ai/DeepSeek-R1-0528-tput"],"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-r1-528b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.55,"max_input_per_1m":0.574,"min_output_per_1m":2.19,"max_output_per_1m":2.294,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"zhipu-glm-4-5-air-fp8","name":"glm-4-5-air-fp8","display_name":"GLM-4.5 Air FP8","description":"An FP8-quantized version of the GLM-4.5 Air MoE model, optimized for memory-efficient deployment while preserving agentic reasoning capabilities.","creator":"zhipu","family":"glm","tier":"air","version":"4-5","type":"language","size_in_bn":null,"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":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":["together_ai/zai-org/GLM-4.5-Air-FP8","zhipu-glm-4-5-air-fp8"],"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":"zhipu-glm-4-5-air-fp8","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":1.1,"max_output_per_1m":1.1,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["together_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"moonshot-kimi-k2-instruct","name":"kimi-k2-instruct","display_name":"Kimi K2 Instruct","description":"The instruction-tuned version of Kimi K2, a 1T-parameter MoE LLM optimized for following user instructions and agentic tool-use tasks.","creator":"moonshot","family":"deepseek_v3","tier":"","version":"k2","type":"language","size_in_bn":1026.471,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":9,"ids":["accounts/fireworks/models/kimi-k2-instruct","accounts/fireworks/models/kimi-k2-instruct-0905","baseten/moonshotai/Kimi-K2-Instruct-0905","deepinfra/moonshotai/Kimi-K2-Instruct","deepinfra/moonshotai/Kimi-K2-Instruct-0905","fireworks_ai/accounts/fireworks/models/kimi-k2-instruct","fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905","groq/moonshotai/kimi-k2-instruct-0905","hyperbolic/moonshotai/Kimi-K2-Instruct","moonshot-kimi-k2-instruct","moonshotai/kimi-k2-instruct","novita/moonshotai/kimi-k2-instruct","together_ai/moonshotai/Kimi-K2-Instruct","together_ai/moonshotai/Kimi-K2-Instruct-0905","wandb/moonshotai/Kimi-K2-Instruct"],"hf_likes":2352,"hf_downloads":276135,"hf_downloads_all_time":2074036,"hf_trending_score":2,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"moonshot-kimi-k2-instruct","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.5,"max_input_per_1m":2,"min_output_per_1m":2,"max_output_per_1m":3,"min_cache_read_per_1m":0.4,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":9},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-3-70b-instruct-turbo","name":"llama-3-3-70b-instruct-turbo","display_name":"Llama 3.3 70B Instruct Turbo","description":"FP8-quantized turbo variant of Llama 3.3 70B Instruct, delivering significantly faster inference speeds with minimal accuracy trade-off.","creator":"meta","family":"llama","tier":"","version":"3-3","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","meta-llama-3-3-70b-instruct-turbo","meta-llama/Llama-3.3-70B-Instruct-Turbo","together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-3-3-70b-instruct-turbo","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":1.04,"min_output_per_1m":0.39,"max_output_per_1m":1.04,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["deepinfra"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-4-17b-maverick-instruct","name":"llama-4-17b-maverick-instruct","display_name":"Llama 4 17B Maverick Instruct","description":"Meta's Llama 4 Maverick instruction-tuned MoE model with 17B active parameters, delivering high-performance multimodal text and image understanding.","creator":"meta","family":"llama","tier":"","version":"4","type":"language","size_in_bn":17,"modalities":{"input":["image","text"],"output":["text"]},"context_window":1048576,"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":9,"ids":["azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8","deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","groq/meta-llama/llama-4-maverick-17b-128e-instruct","lambda_ai/llama-4-maverick-17b-128e-instruct-fp8","llama-4-maverick-17b-128e-instruct-maas","meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8","meta-llama-4-17b-maverick-instruct","meta-llama/llama-4-maverick-17b-128e-instruct-fp8","meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","publishers/google/models/llama-4-maverick-17b-128e-instruct-maas","publishers/meta/models/llama-4-maverick-17b-128e-instruct-maas","sambanova/Llama-4-Maverick-17B-128E-Instruct","together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas","vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas"],"hf_likes":163,"hf_downloads":93997,"hf_downloads_all_time":1156723,"hf_trending_score":0,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"meta-llama-4-17b-maverick-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":1.41,"min_output_per_1m":0.1,"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":["lambda"],"provider_count":9},"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-qwen3-235b-a22b-fp8-tput","name":"qwen3-235b-a22b-fp8-tput","display_name":"Qwen3 235B A22B FP8 Tput","description":"A throughput-optimized FP8-quantized variant of the Qwen3 235B A22B MoE model, balancing inference speed with large-scale reasoning capability.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["text"],"output":["text"]},"context_window":40000,"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":["alibaba-qwen3-235b-a22b-fp8-tput","together_ai/Qwen/Qwen3-235B-A22B-fp8-tput"],"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-qwen3-235b-a22b-fp8-tput","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":0.6,"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":["together_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-235b-a22b-instruct-tput","name":"qwen3-235b-a22b-instruct-tput","display_name":"Qwen3 235B A22B Instruct Tput","description":"A throughput-optimized serving variant of the Qwen3 235B A22B Instruct MoE model, tuned for high-volume inference workloads.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":235,"modalities":{"input":["text"],"output":["text"]},"context_window":262000,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["alibaba-qwen3-235b-a22b-instruct-tput","together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput"],"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-qwen3-235b-a22b-instruct-tput","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":0.6,"max_output_per_1m":6,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["huggingface","together_ai"],"provider_count":2},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-coder-480b-a35b-instruct-fp8","name":"qwen3-coder-480b-a35b-instruct-fp8","display_name":"Qwen3 Coder 480B A35B Instruct FP8","description":"An FP8-quantized variant of the Qwen3 Coder 480B A35B Instruct MoE model, enabling efficient deployment of the large agentic coding model.","creator":"alibaba","family":"qwen","tier":"","version":null,"type":"language","size_in_bn":480,"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":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":1,"ids":["alibaba-qwen3-coder-480b-a35b-instruct-fp8","together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"],"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-qwen3-coder-480b-a35b-instruct-fp8","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":2,"max_input_per_1m":2,"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":["together_ai"],"provider_count":1},"providers":[],"regions":[],"region_info":{}}},{"id":"alibaba-qwen3-next-80b-a3b-thinking","name":"qwen3-next-80b-a3b-thinking","display_name":"Qwen3 Next 80B A3B Thinking","description":"A thinking-mode variant of the Qwen3 Next MoE model with 80B total and 3B activated parameters, featuring hybrid attention for extended chain-of-thought reasoning.","creator":"alibaba","family":"qwen3_next","tier":"","version":null,"type":"language","size_in_bn":80,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-09-30","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-09-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":10,"ids":["accounts/fireworks/models/qwen3-next-80b-a3b-thinking","alibaba-qwen3-next-80b-a3b-thinking","alibaba/qwen3-next-80b-a3b-thinking","dashscope/qwen3-next-80b-a3b-thinking","deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking","fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking","novita/qwen/qwen3-next-80b-a3b-thinking","qwen/qwen3-next-80b-a3b-thinking","qwen3-next-80b-a3b-thinking","together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking"],"hf_likes":487,"hf_downloads":32460,"hf_downloads_all_time":2304469,"hf_trending_score":0,"updated_at":"2026-06-13 08:02:30","pricing":{"model_id":"alibaba-qwen3-next-80b-a3b-thinking","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.0975,"max_input_per_1m":0.9,"min_output_per_1m":0.78,"max_output_per_1m":1.5,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["openrouter"],"provider_count":10},"providers":[],"regions":[],"region_info":{}}}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":22},"meta":{"updated_at":"2026-06-13","request_id":"d1a1d52d-b907-4b80-a9a4-7953ed1859bf","execution_ms":19}}