{"data":{"id":"zhipu-glm-4-7-fp8","name":"glm-4-7-fp8","display_name":"GLM-4.7 FP8","description":"An FP8-quantized version of Z AI's GLM-4.7 MoE model, enabling memory-efficient deployment with reduced precision for fast inference.","creator":"zhipu","family":"glm","tier":"","version":"4-7","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":202752,"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":1,"ids":["gmi/zai-org/GLM-4.7-FP8","zhipu-glm-4-7-fp8"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"},"meta":{"updated_at":"2026-06-19","request_id":"bb74c11a-7ea8-4aaa-8a6b-bbae9685f2f5","execution_ms":40}}