NVIDIA 发布 Nemotron 3.5 Super VL，CoreWeave 提供无服务器推理
精选理由
NVIDIA 新出的多模态 MoE 模型，12B 激活参数，能处理图片加文本，CoreWeave 上直接能调，缓存输入只要 $0.05 每百万 token。
NVIDIA 发布多模态混合专家模型 Nemotron 3.5 Super VL，激活参数 12B，以 NVFP4 精度部署。模型支持文本与图像输入，带推理、工具调用和结构化输出能力。CoreWeave Serverless Inference 已可调用，定价为每百万 token 输入 $0.25、输出 $1.50、缓存输入 $0.05。调用记录可通过 CoreWeave Agent Lens 追踪。
原文 · CoreWeave
The @NVIDIAAI team shipped Nemotron 3.5 Super VL today, and you can call it now on CoreWeave Serverless Inference.
Send it text and images, build with supported reasoning, tool calling and structured outputs, and trace every call in CoreWeave Agent Lens.
It's a multimodal mixture-of-experts model with 12B active parameters, served in NVFP4.
Pricing per 1M tokens is $0.25 input, $1.50 output, and $0.05 cached input.
Try it here: https://t.co/MUfcALKOnu
