Skip to content

Gemini 4 Neon

Reasoning
google/gemini-4-neon

Vision · 1M context · Nov 2026 · 6 upstreams

Gemini 4 Neon is Google's fast frontier model between Carbon and Hydrogen for software engineering, knowledge work and science. It reads text, images and video, returns text, and has a 1,048,576-token context window.

Needs your own keyTo use Gemini 4 Neon, add a key from Google Aistudio, OpenRouter, Vercel AI Gateway or 3 more. AnyRouter adds no fee.
context
1M
input / 1M (list)
$3.00
output / 1M (list)
$15.00
routes
6
speed, 24h
No data yet

Upstreams

6
  1. 1Google AI StudioBYOKnot addedBilled to your key
  2. 2OpenRouterBYOKnot addedBilled to your key
  3. 3Vercel AI GatewayBYOKnot addedBilled to your key
  4. 4RespanBYOKnot addedBilled to your key
  5. 5InfronBYOKnot addedBilled to your key
  6. 6ExperientialBYOKnot addedBilled to your key
Google launch comparisonGemini 4 familyFrontier peers
Gemini 4 NeonGemini 4 CarbonGemini 4 ArgonGemini 4 HydrogenClaude Opus 5.5GPT-6.2 Sol
Google DeepMind's published comparison, read 2026-11-19. All figures are the vendor's claims.
Capability indices61.0 (Highest reported score in this row)–––59.0 (Second-highest reported score in this row)57.0
70.9% (Highest reported score in this row)–––70.1% (Second-highest reported score in this row)66.1%
CursorBench 4.165.4% (Highest reported score in this row)–––58.1% (Second-highest reported score in this row)–
Terminal-bench 4.1Cheating adjusted accuracy65.2% (Second-highest reported score in this row)–––65.8% (Highest reported score in this row)61.5%
FrontierCode 2.0Main score46.2% (Second-highest reported score in this row)–––47.3% (Highest reported score in this row)43.8%
SWE-sweepProvider harness39.0% (Highest reported score in this row)–––10.1% (Second-highest reported score in this row)8.3%
SWE-sweepMini-SWE harness12.8% (Highest reported score in this row)–––3.6%11.6% (Second-highest reported score in this row)
AutomationBench56.3% (Highest reported score in this row)–––42.5% (Second-highest reported score in this row)41.3%
Agents' Last Exam v1.175.8% (Highest reported score in this row)–––71.6%73.0% (Second-highest reported score in this row)
RiemannBench84.0% (Highest reported score in this row)–––80.0% (Second-highest reported score in this row)80.0% (Second-highest reported score in this row)
Terminal-Bench-Science 0.170.5% (Highest reported score in this row)–––63.3%68.0% (Second-highest reported score in this row)
HLE-Diamond71.3% (Highest reported score in this row)–––67.9% (Second-highest reported score in this row)64.0%
MKAClimb WSR56.5% (Highest reported score in this row)–––53.0% (Second-highest reported score in this row)52.7%
Chartography73.5% (Second-highest reported score in this row)–––66.3%75.1% (Highest reported score in this row)
LVBench89.0% (Highest reported score in this row)–––83.7%87.6% (Second-highest reported score in this row)
GraphWalks256k to 1M, BFS (F1)95.2% (Highest reported score in this row)–––66.8%80.1% (Second-highest reported score in this row)
CWE-Bench v270.7% (Highest reported score in this row)–––67.1% (Second-highest reported score in this row)66.0%
SEC-bench Pro90.5% (Highest reported score in this row)––––88.3% (Second-highest reported score in this row)
WebExploitBench v1.251.3% (Highest reported score in this row)–––37.1% (Second-highest reported score in this row)–

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-4-neon",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'

Details

Owner
Google
Kind
Vision
Released
Nov 2026
Context
1M
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Gallery

Images from the vendor
  • Gemini 4 Neon versus Claude Opus 5.5 and GPT-6.2 Sol — Google-reported results (Google DeepMind-reported)© Google DeepMind