{"data":{"id":"meta-llama-3-1-70b-instruct-fp8-fast","name":"llama-3-1-70b-instruct-fp8-fast","display_name":"Llama 3.1 70B Instruct FP8 Fast","description":"A quantized FP8 variant of Llama 3.1 70B optimized for faster inference throughput while preserving instruction-following capability.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":["@cf/meta/llama-3.1-70b-instruct-fp8-fast","meta-llama-3-1-70b-instruct-fp8-fast"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-11 08:02:18"},"meta":{"updated_at":"2026-06-11","request_id":"d5a3240a-be2b-48df-9ed4-f351f27eb366","execution_ms":1}}