{"schema":"postcutoff/model@1","as_of":"2026-10-15T23:34:00+02:00","url":"https://postcutoff.com/m/nemotron-3-5-super-vl/","md":"https://postcutoff.com/m/nemotron-3-5-super-vl/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"nemotron-3-5-super-vl","name":"NVIDIA Nemotron 3.5 Super VL (120B-A12B)","org":"NVIDIA","family":"Nemotron 3.5","released":"2026-10-15","status":"current","type":"multimodal","modality_in":["text","image","pdf"],"modality_out":["text"],"open_weights":true,"model_license":"openmdw-1.1","context_window":1000000,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0.15,"output":0.5,"unit":"per 1M tokens (USD) on OpenRouter (also a rate-limited :free variant)","source":"https://openrouter.ai/api/v1/models"},"price_line":"$0.15 in, $0.50 out per 1M tokens","access":[{"provider":"Hugging Face","url":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4"},{"provider":"OpenRouter","model_id":"nvidia/nemotron-3.5-super-vl","url":"https://openrouter.ai/nvidia/nemotron-3.5-super-vl"},{"provider":"NVIDIA NIM / build.nvidia.com (free rate-limited dev API)","docs":"https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/"},{"provider":"ModelScope","docs":"https://blogs.nvidia.com/blog/nemotron-3-5-super-vl/"}],"capabilities":[{"name":"Open vision-language agent model with 1M context","detail":"120B total / 12B active Mamba-2–Transformer hybrid MoE with a C-RADIO vision encoder and native multi-token prediction; reads PDFs, charts, tables, images and web pages; up to 1M tokens.","first":false,"discovered":"launch","source":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4"},{"name":"Fast at long input","detail":"About 625 output tokens/s at 100K input on four B200s per Artificial Analysis (via VentureBeat); NVIDIA claims up to 5x the throughput of comparable open models.","first":false,"discovered":"launch","source":"https://venturebeat.com/technology/nvidias-new-open-nemotron-3-5-super-vl-with-post-training-beats-claude-opus-5-gpt-6-1-sol-on-specialized-task-benchmarks"}],"entry":"2026-10-15-nvidia-nemotron-3-5-super-vl-bolt","notes":"Trained on ~26T tokens, 3.8M post-training samples and RL in ~100 open environments. Ranks below GLM-5.3-Flash and Qwen3.8-Flash-Next on the Artificial Analysis index (~26). Production use via NVIDIA AI Enterprise ($4,500/GPU/year).","verified":"2026-10-15","body_md":"NVIDIA's open multimodal model for enterprise document and tool-using agents, released with training recipes and data for customization in NeMo.\n</content>\n</invoke>","page_url":"https://postcutoff.com/m/nemotron-3-5-super-vl/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":0,"you_url":"https://postcutoff.com/you/nemotron-3-5-super-vl/","briefings":null}