Nemotron 3.5 Lightning now available on AI Gateway for free
By Steven Van ·
The open-weight NVIDIA model supports a 1M token context window, tool calling, and structured outputs.
NVIDIA’s open-weight reasoning and chat model Nemotron 3.5 Lightning is now free through Vercel AI Gateway, served by NVIDIA. It is designed for long-running agents, sub-agent work, chatbots, and RAG systems.
Model capabilities
The model has a 1M token context window and supports tool calling and structured outputs. Its hybrid Mixture-of-Experts architecture combines Mamba-2, MoE, and attention layers, with 30B parameters and 3B active per token.
API and coding agent access
Use the model identifier nvidia/nemotron-3.5-lightning-free through the AI SDK, Chat Completions, Responses, or Messages APIs. The Responses API documentation explains how to point an OpenAI SDK at AI Gateway and authenticate requests.
For Claude Code, Codex, Cursor, and other supported coding agents, install the latest Vercel CLI, run npx vercel ai-gateway setup, then select nvidia/nemotron-3.5-lightning-free in the agent.
The provider may retain prompts for model improvement.