# Vercel adds free Nemotron 3.5 Lightning model to AI Gateway

published: 2026-10-14T17:06:24.215Z
topic: infrastructure
source: https://vercel.com/changelog/nemotron-3-5-lightning-now-available-on-ai-gateway-for-free
url: https://aiagentnews.io/stories/vercel-adds-free-nemotron-3-5-lightning-model-to-ai-gateway

NVIDIA's Nemotron 3.5 Lightning is now available at no cost on Vercel's AI Gateway under the identifier nvidia/nemotron-3.5-lightning-free, served by NVIDIA. The open-weight model targets long-running agents, sub-agent work, chatbots and RAG systems, and it supports a 1M token context window.

NVIDIA's Nemotron 3.5 Lightning can now be called for free through AI Gateway as nvidia/nemotron-3.5-lightning-free, with NVIDIA serving the model. The open-weight reasoning and chat model has 30B parameters, of which 3B are active per token. It uses a hybrid Mixture-of-Experts design that interleaves Mamba-2 and MoE layers with a few attention layers.

The model has a 1M token context window and supports tool calling and structured outputs. It can be called through the AI SDK, the Chat Completions, Responses and Messages APIs, or from a coding agent connected to AI Gateway. Vercel notes that the provider may retain prompts for model improvement.

AI Gateway offers a unified API for models, with usage and cost tracking, retries, failover, routing rules and budgets for API keys. Vercel says it passes provider pricing through with no markup and charges no platform fee on inference, including Bring Your Own Key requests. Coding agents such as Claude Code, Codex and Cursor can be set up with the Vercel CLI command npx vercel ai-gateway setup, then pointed at the new model.

## Why it matters if you build agents

Agent builders can try a 1M token context model with tool calling for no cost by changing the model string to the free identifier. Because the provider may keep prompts for model improvement, sensitive data should not be sent through it until that policy has been checked.