Back to every model

Google

Gemini 4 Neon API pricing and specs

Google's Gemini 4 Neon: price per million tokens, context window, limits and capabilities, re-read from OpenRouter's model feed every 6 hours.

Input

$3

Output

$15

Context

1M

Gemini 4 Neon costs $3 per million input tokens and $15 per million output tokens. Cached input is billed at $0.15 per million, 95% less than fresh input.

Specifications

LabGoogle
Model idgoogle/gemini-4-neon
Input price$3 per million tokens
Output price$15 per million tokens
Cached input price$0.15 per million tokens
Context window1,048,576 tokens (1M)
Maximum output943,718 tokens (944K)
Tool callingyes
Image inputyes
Reasoningyes
Intelligence index61.4
First listed18 November 2026

Google's other models

ModelInput / 1MOutput / 1MContextListed
Gemini 4 Hydrogen$1.50$7.501M12 November 2026
Gemini 4 Carbon$2$101M10 November 2026
Gemini Omni 1.2 Flash$1.50$9128K5 November 2026
Gemini Omni 1.1 Flash$1.50$9128K4 November 2026
Gemini 4 Argon$2$101M13 October 2026
Nano Banana 2.1$1.50$7.5064K6 October 2026
Gemini 3.5 Flash Lite$0.30$2.501M21 July 2026
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)$0.25$1.5064K30 June 2026
Nano Banana Pro (Gemini 3 Pro Image)$2$12128K18 June 2026
Nano Banana 2 (Gemini 3.1 Flash Image)$0.50$3128K18 June 2026
Gemini 3.1 Flash Lite$0.25$1.501M7 May 2026
Gemma 4 26B A4B $0.09$0.30256K3 April 2026

Where these numbers come from

Read from OpenRouter's listing of Gemini 4 Neon every 6 hours into the catalog Founden's builders choose their models from. Prices are OpenRouter's listed price per million tokens: for a lab's closed models that is the lab's own list price, and for an open-weight model it is the price of the host OpenRouter routes to by default, which can differ from the lab's own API and from other hosts. US dollars, before batch, volume or regional discounts. Every model.