Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Gemini 4 NeonGoogleRemove
gemini-4-neon
AttributeGemini 4 Neongemini-4-neon
Pricing
Input$3.00 / 1M
Output$15.00 / 1M
Cache Write (5m)$3.00 / 1M
Cache Write (1h)$3.00 / 1M
Cache Read$3.00 / 1M
Web Search$0 / 1M
Context
Max context1M
Max outputN/A
Capabilities
VisionYes
Function CallingYes
JSON ModeYes
StreamingYes
Catalogue
ProviderGoogle
Categorychat
Charge typePay As You Go
Released—
Description
SummaryGemini 4 Neon is Google's fast, mid-priced multimodal model in the Gemini 4 family, designed for coding, agentic workflows, and complex STEM reasoning. Positioned above Gemini 4 Hydrogen, it targets Gemini 4 Carbon-level quality while delivering higher speed and lower cost. It excels at repository-level coding, terminal-based development, web application building, and multi-turn tool use. Optimized for high-performance agentic execution and efficient inference, Gemini 4 Neon supports up to 1M output tokens through continuation and configurable reasoning effort levels (low, medium, high, and xhigh) to balance reasoning depth, latency, and cost. It is well suited for autonomous coding agents, multimodal problem solving, and scalable production workflows.