{"data":{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Super-VL","provider_id":"deepinfra","name":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","modalities":["text","image"],"context_window":262144,"family":"NVIDIA-Nemotron-3.5-Super-VL","status":"active","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal model for agents that see, reason, and act. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, and adds reasoning and tool use on top.","architecture":null,"supported_parameters":["chat","vlm","vision","prompt_cache","reasoning"],"created_at":null,"canonical_slug":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.2375,"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":64668,"model_id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Super-VL","unit":"token","input_per_1m_usd":0.15,"output_per_1m_usd":0.5,"flat_usd":null,"currency":"USD","effective_at":"2026-10-20","source_url":"https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Super-VL","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 0.0199999995/1M.","last_verified_at":"2026-10-20T00:15:40.825Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":0.0199999995,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}