Gemini 4 Neon now available on Vercel AI Gateway
Vercel announced that Google's Gemini 4 Neon model is available on Vercel AI Gateway under the model ID google/gemini-4-neon. The model accepts text, images, video, and documents with a 1M-token context window, supports tool calling, structured outputs, and grounding with Google Search and Google Maps, and offers four reasoning levels (low, medium, high, xhigh).

Why it matters
Builders using Vercel AI Gateway can call Gemini 4 Neon through an existing gateway integration, with a 1M-token context window and multimodal input for coding, agent, and multi-step workflows. The model is described as a faster upgrade over the earlier lighter Gemini 4 model, with output quality close to Google's larger Gemini 4 models.
Who should care
Developers building AI agents, coding tools, or multimodal apps on Vercel; teams using Codex, Cursor, or other supported agents.
What you can do
Set the model ID to google/gemini-4-neon in your AI Gateway configuration and test it against an existing agent or coding workflow, adjusting the reasoning level as needed.