Gemini 4 Neon now available on AI Gateway Google's Gemini 4 Neon is now available on Vercel's AI Gateway under the model ID google/gemini-4-neon, the gateway announced. The model accepts text, images, video and documents with a 1M-token context window, supports tool calling, structured outputs, grounding with Google Search and Google Maps, and four reasoning levels (low, medium, high, xhigh), and is positioned for coding, agent workflows and multi-step tasks with output quality close to Google's larger Gemini 4 models at faster response speeds. Gemini 4 Neon from Google https://vercel.com/ai-gateway/models/gemini-4-neon is now available on AI Gateway. Gemini 4 Neon is a major upgrade over the earlier, lighter Gemini 4 model, delivering output quality close to Google’s larger Gemini 4 models with faster responses. It’s built for coding, agent workflows, and multi-step tasks. The model accepts text, images, video, and documents, with a 1M-token context window. It supports tool calling, structured outputs, grounding with Google Search and Google Maps, and four reasoning levels: low, medium, high, and xhigh. Use google/gemini-4-neon as the model ID: To use Gemini 4 Neon in Codex, Cursor, or another supported agent, see the coding agents guide https://vercel.com/docs/ai-gateway/coding-agents . Try Gemini 4 Neon in the model playground https://vercel.com/ai-gateway/models/gemini-4-neon , or explore all language models https://vercel.com/ai-gateway/models?type=text .