NVIDIA's open Nemotron 3.5 Super VL (120B-A12B) lands on Baseten day 0
baseten · x · 2026-10-15
- NVIDIA Nemotron 3.5 Super VL is live day 0 on Baseten Model APIs and Loops, positioned for multimodal agent workflows across text, images, and video.
- The open 120B-A12B MoE model has a 1M-token context window, lets agents reason over documents and visual evidence then call tools, and targets document intelligence, support, and web research. NVIDIA recommends temperature=1.0, topp=0.95, with reasoning toggleable via chattemplatekwargs.
- Baseten pricing: $0.20/M input tokens ($0.04 cached), $0.50/M output, under the OpenMDW-1.1 license, callable via the OpenAI SDK.
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