Gemini 4 Neon

google/gemini-4-neon

fast multimodal reasoning for coding & agents.

cmd --model google/gemini-4-neon
Intelligence index
not yet scored
Coding index
not yet scored
Input
$3 /M
Output
$15 /M
Cache read
$0.15 /M
Agent-loop cost
$1.01 /M in
Context window
1M tokens
Released
November 18, 2026
Modalities
→

vs. the lineup

Gemini 4 Neon beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingInput $/MOutput $/MBlended $/MContext
Gemini 4 Argon52.6◆—$2$10$41M
Gemini 3.8 Flash40.976.3◆$1.50$7.50$31M
Gemini 3.7 Flash39.176.1$1.50$7.50$31.05M◆
Gemini 3.6 Flash3469.2$1.50$7.50$31M
Gemini 4 Neon ◆——$3$15$61M
Gemini 4 Carbon——$2$10$41M
DeepSeek V4 Pro (latest)pinned3668.8$0.66$1.98$0.991M
DeepSeek V4 Flash (latest)pinned3469.1$0.15◆$0.60◆$0.26◆1M

usage calculator

How far a month of credits goes on Gemini 4 Neon.

Gemini 4 Neon runs on Pro and up — from $20/mo.
Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.013 · in $3 · out $15 · cache $0.15 per M
fresh input 19%output 21%cache reads 60%
Requests / 30 days
1.6K
$20 credits ÷ $0.013 per request
~317 quick fixes~63 bug fixes~11 feature PRs

what real work costs

Real coding tasks priced end to end on Gemini 4 Neon, from a quick lookup to a full-repo agent run.

One agent task
$0.34
180K in at 75% cache hit, 12K out
What you pay
$1.75 /M
all-in across every token that task touched
Sticker input
$3 /M
cache reads bill at $0.15 /M instead
TaskTokens in · outGemini 4 NeonClaude Sonnet 5.5Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.02$0.01$0.0065
Review a 500-line PR60K · 4K$0.12$0.08$0.04
Fix a bug (agent loop)180K · 12K$0.34$0.22$0.12
Refactor a module320K · 20K$0.60$0.40$0.21
Full-repo agent run900K · 45K$1.37$0.92$0.49

frequently asked

How much does Gemini 4 Neon cost?
$3/M input and $15/M output, cache reads $0.15/M. In an agent loop most input is cache-read, so the effective input rate is about $1.01/M.
Which plan do I need?
Available on Pro and above.
How do I switch to it?
Run cmd --model google/gemini-4-neon, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/gemini-4-neon