modelbenchmark.io

Gemini 4 Hydrogen

Google · gemini-4-hydrogen

Compare

Google's Gemini 4 model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window

Specification

google listing

Context
1M
Max output
66K
Released
2026-11-12
Knowledge cutoff
2026-03
Retires
—
Open weights
no
Input
text, image, video, audio, pdf
Output
text

Price

US dollars per million tokens · google list price

Input
$1.50
Output
$7.50
Cache read
$0.075
Cache write
$0.0833

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputgemini$0.75
Batch outputgemini$3.75
Priority inputgemini$2.70
Priority outputgemini$13.50

Batch input is 50% below the interactive input price at the same listing.

Rate limits

as listed

Requests per minute
2,000
Tokens per minute
800,000

Available from 20 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
googlevendor$1.50$7.50$0.075—1M66K—
kilo$0.75$3.75$0.0375$0.04171M944K—
edenai$1.50$7.50$0.075$0.08331M66K—
gemini$1.50$7.50$0.075—1M1M—
github_copilot · github-copilot$1.50$7.50$0.075—200K66K—
github-copilot$1.50$7.50$0.075—1M66K—
google-vertex$1.50$7.50$0.075—1M66K—
llmgateway$1.50$7.50$0.075—1M66K—
llmgateway-providers · google-ai-studio$1.50$7.50$0.075—1M66K—
llmgateway-providers · google-vertex$1.50$7.50$0.075—1M66K—
merge-gateway$1.50$7.50$0.075—1M66K—
nano-gpt$1.50$7.50$0.075—1M66K—
ofox$1.50$7.50$0.075—1M66K—
opencode$1.50$7.50$0.075—1M66K—
openrouter$1.50$7.50$0.075$0.08331M944K—
perplexity$1.50$7.50$0.075————
vercel$1.50$7.50$0.075—1M1M—
vertex_ai$1.50$7.50$0.075—1M1M—
cortecs$1.688$8.437$0.085—1M66K—
venice$1.875$9.375$0.0938—1M66K—

More from Google

most-hosted first