Google: Gemini 4 Neon

Text input Audio input File input Video input Image input Text output
Author's Description

Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web...

Key Specifications
Cost
$$$$$
Context
1M
Released
Nov 18, 2026
Speed
★★
Ability
★★★★★
Reliability
★★★
Supported Parameters

This model supports the following parameters:

Tool Choice Temperature Reasoning Top P Include Reasoning Max Tokens Seed Tools Structured Outputs Response Format
Features

This model supports the following features:

Structured Outputs Reasoning Tools Response Format
Performance Summary

Google's Gemini 4 Neon demonstrates exceptional cognitive performance across core technical benchmarks, backed by an expansive 1M-token context window. The model truly excels in analytical problem-solving, achieving a flawless 100% accuracy on complex reasoning tasks—distinguishing itself as the most accurate model at its price point and among models of comparable latency. It complements this with elite execution in programming, reaching 96.0% accuracy on comprehensive coding evaluations, and 92.0% accuracy on complex, multi-layered instruction following. Operationally, Gemini 4 Neon exhibits standout reliability, maintaining a perfect 100% success rate with zero technical failures across all testing. However, this high-level precision comes with measurable trade-offs in efficiency and cost. The model demonstrates moderate speed performance, ranking in the 37th percentile, and is situated at premium pricing levels, landing in the 9th percentile for cost competitiveness. Ultimately, Gemini 4 Neon's key strengths are its peerless reasoning capability, sophisticated code generation, and rock-solid reliability. While its premium cost and moderate throughput may not suit budget-constrained or latency-sensitive pipelines, its industry-leading accuracy makes it an outstanding solution for demanding developer tasks and autonomous agentic workflows.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.5
Completion $7.5
Input Cache Read $0.075
Input Cache Write $0.0417
Internal Reasoning $7.5
Web Search $14000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Google AI Studio
Google AI Studio | google/gemini-4-neon-20261118 1M $1.5 / 1M tokens $7.5 / 1M tokens
Google AI Studio
Google AI Studio | google/gemini-4-neon-20261118 1M $3 / 1M tokens $15 / 1M tokens
Google
Google | google/gemini-4-neon-20261118 1M $3 / 1M tokens $15 / 1M tokens
Google
Google | google/gemini-4-neon-20261118 1M $5.4 / 1M tokens $27 / 1M tokens
Google AI Studio
Google AI Studio | google/gemini-4-neon-20261118 1M $5.4 / 1M tokens $27 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by google