{"data":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra","created":1755815280,"released":1780531200,"description":"A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.","architecture":{"tokenizer":null,"instruct_type":null,"modality":"text→text","input_modalities":["text"],"output_modalities":["text"]},"reasoning":{"mandatory":false,"supported_efforts":["none","low","medium","high"]},"endpoints":[{"name":"baseten | nvidia/nemotron-3-ultra-550b-a55b","model_name":"Nemotron 3 Ultra","context_length":1000000,"pricing":{"prompt":"0.0000006","completion":"0.0000024","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000012","discount":0},"provider_name":"baseten","has_zdr":true,"has_no_training":true,"headquarters_country":"US","tags":["reasoning","tool-use","structured-output","open-weights"],"inference_regions":[{"scope":"zone","geo_region":"us","pricing":{"prompt":"0.0000006","completion":"0.0000024","input_cache_read":"0.00000012"}}],"quantization":null,"max_completion_tokens":65000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"status":0,"uptime_last_15m":100,"uptime_last_1h":100,"uptime_last_1d":99.9792,"latency_last_1h":{"p50":379,"p95":1114.6},"throughput_last_1h":{"p50":210.5,"p95":237.95},"supports_implicit_caching":false},{"name":"deepinfra | nvidia/nemotron-3-ultra-550b-a55b","model_name":"Nemotron 3 Ultra","context_length":262144,"pricing":{"prompt":"0.0000005","completion":"0.0000022","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.0000001","discount":0},"provider_name":"deepinfra","has_zdr":false,"has_no_training":true,"headquarters_country":"US","tags":["reasoning","tool-use","implicit-caching","structured-output","open-weights"],"quantization":"fp4","max_completion_tokens":65000,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","stop","tools","tool_choice","reasoning","include_reasoning","response_format","structured_outputs"],"status":0,"uptime_last_15m":100,"uptime_last_1h":100,"uptime_last_1d":100,"latency_last_1h":{"p50":937.5,"p95":2638.9},"throughput_last_1h":{"p50":181,"p95":196.3},"supports_implicit_caching":true}]}}