{"data":[{"id":"zcx/qwen-2.5-32b-instruct","name":"Qwen 2.5 32B Instruct (ZCX dedicated GB10)","created":1776758400,"description":"Qwen 2.5 32B Instruct served on dedicated NVIDIA GB10 silicon. Q4_K_M quantization, lower latency than 72B, best for high-volume agent loops.","input_modalities":["text"],"output_modalities":["text"],"quantization":"Q4_K_M","context_length":32768,"max_output_length":8192,"pricing":{"prompt":"0.00000010","completion":"0.00000012","request":"0","image":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","frequency_penalty","presence_penalty","stop","seed","max_tokens"],"supported_features":["chat_completions","openai_compatible","function_calling","json_mode"],"datacenters":["us-west / spark-23 (single node)"],"openrouter":{"slug":"zcx/qwen-2.5-32b-instruct"}}]}