AI KNOWLEDGE DESK

Models · entities · concepts · comparisons · practical tools

GETLLMS.ORG

🚀Function Overview

Google announced and launched gemini-4-neon to Developer API general availability on November 18, 2026, as a paid model priced at $3 per million input tokens and $15 per million output tokens. Neon features a 1,048,576-token multimodal context window, 65,536 default synchronous output tokens, optional long decode up to 1,048,576 tokens, and thinking budgets ranging from low to xhigh with high as the default. In consumer applications, Neon is available to Pro and Ultra subscribers. Google demonstrated Neon's orchestration strength by using Antigravity parallel agents and Blender through MCP to render a 3D laboratory bench.

Key Features

  • Intermediate reasoning model offering deeper analysis than Hydrogen at lower token rates than post-promotion Carbon
  • Multimodal input handling for text, images, audio, video, and PDFs within a 1,048,576-token window
  • Standard Developer API pricing of $3 per million input tokens and $15 per million output tokens
  • Google demonstrated Neon coordinating parallel agents in Antigravity while Blender rendered a lab bench.

Use Cases

  • •Test a multi-step workflow with a fixed set of tools and check the finished output.
  • •Performing multi-step code reviews, complex script synthesis, and intermediate refactoring
  • •Executing rigorous data transformations and analytical evaluations across mixed media sources

⚙️Input Parameters

contents

array

Gemini generateContent contents with text or supported media parts

generationConfig

object

Documented output and thinking configuration; ordinary synchronous output is distinct from long decode

💡Usage Examples

Example 1

Input Parameters

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Review the supplied project notes. List confirmed findings, open questions, and the checks that would resolve them."
        }
      ]
    }
  ]
}

Output Results

Illustrative generateContent request. Inspect candidates and usageMetadata after running it with your own API access.