NVIDIA open-sources Nemotron 3.5 Super VL: 120B-A12B MoE with 1M context, $0.50/M output
baseten · x · 2026-10-15
NVIDIA released Nemotron 3.5 Super VL, an open-weights model now live on Baseten's Model API.
- Specs: 120B-A12B MoE, text/image/video input, 1M-token context, OpenMDW-1.1 license
- Built for agent workflows: reasoning across documents and visual evidence, then tool calls for multi-step tasks (document intelligence, support, web research)
- Baseten pricing: $0.20/M input, $0.04/M cached input, $0.50/M output tokens
- Recommended settings: temperature=1.0, topp=0.95; reasoning toggle via chattemplatekwargs.enablethinking; OpenAI-SDK compatible, SFT/RL fine-tuning available
More from Models
- OpenAI ships GPT-Live-1.1: new voices in six languages, fewer confirmations — OpenAI · 2026-10-16
- Muse Spark model appears on LMArena, testable in Battle and Agent modes — arena · 2026-10-16
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Ilya Sutskever questions Meta license clause taxing MaaS providers above $20M revenue — ilyasu · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- Midas flags inconsistent Claude limits: 33% weekly and 45% window usage despite $100 credits, yet out of API credits — TheMoonMidas · 2026-10-16