Verified November 2026

Home › Models › Gemini 4 Hydrogen

Gemini 4 Hydrogen API pricing

Gemini 4 Hydrogen is a model from Google Gemini with a 1,000,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026.

$1.50Input / 1M tokens
$7.50Output / 1M tokens
$0.075Cached input / 1M
1,000,000Context window

Price list

Gemini 4 Hydrogen rates in USD per 1M tokens, November 2026
Token classRate / 1MNotes
Input$1.50Prompt tokens not served from cache
Cached input$0.07595% below base input
Cache write—Not billed per token
Output$7.505.0× the input rate
Batch API−50%Input and output, results within 24 h

Everyday Gemini 4 tier with a 1M-token context window. Flat rate at any prompt length; implicit caching only.

What Gemini 4 Hydrogen costs at three real workloads

Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.

WorkloadRequestsTokensEstimated cost
Support chat1,0004K in / 600 out$10.50
RAG with caching1,00050K in (45K cached) / 1K out$18.44
Nightly batch job10,00010K in / 2K out$150

Caching the 45K-token prefix saves about 78% on the RAG workload versus sending it uncached every call ($82.50 → $18.44). Batch mode halves the nightly job.

Where Gemini 4 Hydrogen sits in the market

Out of 45 models in this dataset, Gemini 4 Hydrogen ranks #24 cheapest by input rate, #25 by output rate, and #23 on a blended 1M-input-plus-250K-output workload.

ModelProviderInputOutputBlended
Gemini 4 HydrogenGoogle Gemini$1.50$7.50$3.38
DeepSeek V4 ProDeepSeek$1.32$3.96$2.31
Grok 4.6xAI Grok$2$6$3.50
Claude Haiku 4.5Anthropic$1$5$2.25

Blended cost = 1M input tokens + 250K output tokens at list price.

FAQ

How much does Gemini 4 Hydrogen cost per 1M tokens?

$1.50 per 1M input tokens and $7.50 per 1M output tokens on the standard tier.

Is prompt caching cheaper on Gemini 4 Hydrogen?

Yes. Cached input bills at $0.075 per 1M tokens, 95.0% below the $1.50 base input rate, with no separate cache-write rate published.

Does Gemini 4 Hydrogen support the Batch API?

Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $300 at list price and about $150 in batch mode.

Keep reading

Run these numbers in the calculator