LLM

Gemini 4 Hydrogen

by Google

Prices last updated November 22, 2026

Gemini 4's fast everyday model for coding and agentic work, tuned for speed and efficiency, with thinking levels up to xhigh. 1M-token context; the only Gemini 4 model with a free tier in the Gemini API.

Context
1.0M
Max Output
66k
Providers
8
Cheapest Input
$0.600
Vision Audio Function Calling JSON Mode Streaming Chat / InstructCodeVision

Price Comparison

Compare pricing across 8 providers serving Gemini 4 Hydrogen

Provider Input $/1M Output $/1M Context Speed TTFT Status
KIE AI
KIE AI
$0.600 ● $3.00 — — — Live
Infron
Infron
$1.20 $6.00 1M — — Live
Google
Google
$1.50 $7.50 1.0M — — Live
OpenRouter
OpenRouter
$1.50 $7.50 1.0M — — Live
Atlas Cloud
Atlas Cloud
$1.50 $7.50 1.0M — — Live
WaveSpeed AI
WaveSpeed AI
$1.50 $7.50 1.0M — — Live
Token Harbor
Token Harbor
$1.50 $7.50 1M — — Live
Venice AI
Venice AI
$1.88 $9.38 1M — — Live
● Cheapest ● Fastest Prices in USD per 1M tokens

Benchmarks

Independent results for Gemini 4 Hydrogen, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.

BenchmarkScoreRankAs tested
Overall
One score combining a model's results across many benchmarks, on a common scale.
166.8±3.1
#9 of 258
Gemini 4 Hydrogen
Reasoning
GPQA DiamondEpoch AI
Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up.
96.8%±2.3
#2 of 232
gemini-4-hydrogen_xhigh
Nov 2026
Math
Unpublished research-level maths problems with automatically checkable answers.
88.1%±3.8
#13 of 95
gemini-4-hydrogen_xhigh
Nov 2026
FrontierMath's hardest tier: problems that take specialist mathematicians days.
87.8%±10.1
#11 of 77
gemini-4-hydrogen_xhigh
Nov 2026
Competition maths problems from the OTIS mock AIME exams (2024-2025).
100.0%
#1 of 215
gemini-4-hydrogen_xhigh
Nov 2026
Coding
Text Arena votes on coding prompts only.
1,514±18
1,078 votes
#55 of 421
Gemini 4 Hydrogen (High)
Nov 2026
Human votes on web apps the models build from a prompt.
1,701±14
2,021 votes
#14 of 161
Gemini 4 Hydrogen (High)
Nov 2026
Knowledge
Short factual questions answered without search, measuring what the model knows and whether it makes things up.
70.9%±2.8
#10 of 97
gemini-4-hydrogen_xhigh
Nov 2026
Chat
Text ArenaLMArena
Human votes on chat answers across all kinds of prompts (style-controlled).
1,490±9
4,743 votes
#18 of 426
Gemini 4 Hydrogen (High)
Nov 2026

Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).

LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).

Rank is among all models the source ranks, including ones we don't list.

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.