{"data":{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","provider_id":"deepinfra","name":"nvidia/NVIDIA-Nemotron-3.5-Lightning","modalities":["text"],"context_window":262144,"family":"NVIDIA-Nemotron-3.5-Lightning","status":"active","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":null,"supported_parameters":["chat","prompt_cache","reasoning"],"created_at":null,"canonical_slug":"nvidia/NVIDIA-Nemotron-3.5-Lightning","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.085,"savings_pct":null,"savings_basis":null,"provider":{"id":"deepinfra","name":"DeepInfra","website":"https://deepinfra.com","categories":["text","image","audio","video"],"docs_url":"https://deepinfra.com/pricing","notes":"Secondary live feed from DeepInfra's public models API. Prices are DeepInfra's rates, not the origin lab's. Does not block the OpenRouter sync.","role":"host"},"prices":[{"id":60263,"model_id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","unit":"token","input_per_1m_usd":0.06,"output_per_1m_usd":0.16,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning","notes":"DeepInfra public models API. Token and character rates are already USD per 1M. Per-image and per-second rates are stored as flat USD. Discount, when present, is not applied. Cache read 0.03/1M.","last_verified_at":"2026-10-08T18:23:40.278Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":0.03,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}