{"data":{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B","created":1755815280,"released":1786406400,"description":"NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.","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":"deepinfra | nvidia/nemotron-3.5-lightning","model_name":"Nemotron 3.5 Lightning 30B","context_length":262144,"pricing":{"prompt":"0.00000006","completion":"0.00000016","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.00000003","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":null,"max_completion_tokens":131072,"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":99.9843,"latency_last_1h":{"p50":265.5,"p95":548.75},"throughput_last_1h":null,"supports_implicit_caching":true},{"name":"runinfra | nvidia/nemotron-3.5-lightning","model_name":"Nemotron 3.5 Lightning 30B","context_length":262144,"pricing":{"prompt":"0.00000004","completion":"0.00000012","image":"0","image_output":"0","web_search":"0","internal_reasoning":"0","input_cache_read":"0.000000008","discount":0},"provider_name":"runinfra","has_zdr":false,"has_no_training":false,"headquarters_country":"US","tags":["reasoning","tool-use","implicit-caching","structured-output","open-weights"],"quantization":null,"max_completion_tokens":131072,"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":192.5,"p95":376.84999999999957},"throughput_last_1h":{"p50":285.5,"p95":285.95},"supports_implicit_caching":true}]}}