{"data":[{"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":"meta-llama-3-1-70b","name":"meta-llama-3-1-70b","display_name":"Llama 3.1 70B","description":"Meta's 70B pre-trained LLM in the Llama 3.1 series, balancing high capability with practical deployment costs and supporting tool-use tasks.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":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":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["cerebras/llama3.1-70b","meta-llama-3-1-70b","meta-textgeneration-llama-3-1-70b","meta-textgenerationneuron-llama-3-1-70b","meta/llama-3.1-70b","snowflake/llama3.1-70b","vercel_ai_gateway/meta/llama-3.1-70b"],"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-3-1-70b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.36,"max_input_per_1m":0.72,"min_output_per_1m":0.36,"max_output_per_1m":0.72,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["snowflake"],"provider_count":3},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-1-8b","name":"meta-llama-3-1-8b","display_name":"Llama 3.1 8B","description":"Meta's compact 8B pre-trained LLM in the Llama 3.1 series, offering efficient on-device or low-cost inference with tool-use support.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":8,"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":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["cerebras/llama3.1-8b","llamagate/llama-3.1-8b","meta-llama-3-1-8b","meta-textgeneration-llama-3-1-8b","meta-textgenerationneuron-llama-3-1-8b","meta/llama-3.1-8b","snowflake/llama3.1-8b","vercel_ai_gateway/meta/llama-3.1-8b"],"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":"meta-llama-3-1-8b","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.03,"max_input_per_1m":0.22,"min_output_per_1m":0.05,"max_output_per_1m":0.22,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["other/llamagate"],"provider_count":4},"providers":[],"regions":[],"region_info":{}}},{"id":"meta-llama-3-3-70b","name":"llama-3-3-70b","display_name":"Llama 3.3 70B","description":"Meta's 70B instruction-tuned LLM from the Llama 3.3 series, designed for high-performance conversational AI, content creation, and enterprise applications.","creator":"meta","family":"llama","tier":"","version":"3-3","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":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":"2024-12-06","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["cerebras/llama-3.3-70b","meta-llama-3-3-70b","meta/llama-3.3-70b","snowflake/llama3.3-70b","snowflake/snowflake-llama-3.3-70b","vercel_ai_gateway/meta/llama-3.3-70b"],"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","currency":"USD","exchange_rate":1,"exchange_rate_date":"2026-06-13","ingestion_date":"2026-06-13","summary":{"currency":"USD","min_input_per_1m":0.36,"max_input_per_1m":0.85,"min_output_per_1m":0.36,"max_output_per_1m":1.2,"min_cache_read_per_1m":null,"min_cache_write_per_1m":null,"min_reasoning_per_1m":null,"cheapest_providers":["snowflake"],"provider_count":6},"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":6},"meta":{"updated_at":"2026-06-13","request_id":"6f7f2dd7-1a66-47f0-b06e-b00941c92f42","execution_ms":10}}