BroadRouter

Gemini 4 Hydrogen API pricing

Updated

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 tie for the lowest blended standard price for Gemini 4 Hydrogen; Google Gemini API charges USD 1.50 per 1M input tokens and USD 7.50 per 1M output tokens. The median across 3 standard prices is USD 1.50 / USD 7.50. That is Google Gemini API's own API.

Google · slug gemini-4-hydrogen · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

What does Google Gemini API charge for Gemini 4 Hydrogen?

Input
USD 1.50
Cached input
USD 0.075
Output
USD 7.50
Blended 3:1
USD 3

USD per 1M tokens on Google (Gemini API), model gemini-4-hydrogen, standard tier. Source, checked 2026-11-14.

Other Google Gemini API tiers: batch USD 0.75 / USD 3.75 · flex / spot USD 0.75 / USD 3.75 · priority USD 2.70 / USD 13.50.

Is a host cheaper than Google Gemini API? They tie. Google Vertex AI and Google Gemini API's own API both work out at USD 3 per 1M tokens on the 3:1 blend.

Gemini 4 Hydrogen price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Gemini 4 Hydrogen API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Google Gemini API tied cheapest maker
gemini-4-hydrogen
Notes and source quote

Paid tier.

“Gemini 4 Hydrogen Standard: Input price $1.50 … Output price (including thinking tokens) $7.50 … Context caching price $0.075 Implicit caching only (explicit caching is not supported).”
USD 1.50USD 0.075USD 7.50USD 3not statednot statedGoogle Gemini API page
checked 2026-11-14
re-checked 2026-11-16
2Google Vertex AI tied cheapest
gemini-4-hydrogen
Notes and source quote

Global endpoint; non-global regions cost 10% more.

“Gemini 4 Hydrogen [Global] Input (text, image, video, audio) $1.50 … Text output (response and reasoning) $7.50 … cached $0.075”
USD 1.50USD 0.075USD 7.50USD 3not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
3Perplexity tied cheapest
google/gemini-4-hydrogen
Notes and source quote

Third-party model resold through the Perplexity Agent API.

“`google/gemini-4-hydrogen` | 1.50 | 7.50 | 0.075”
USD 1.50USD 0.075USD 7.50USD 3not statednot statedPerplexity page
checked 2026-11-15
re-checked 2026-11-16
—Google Gemini API maker batch
gemini-4-hydrogen
Notes and source quote

Paid tier.

“Gemini 4 Hydrogen Batch: Input price $0.75 … Output price (including thinking tokens) $3.75 … Context caching price $0.0375 Implicit caching only (explicit caching is not supported).”
USD 0.75USD 0.0375USD 3.75USD 1.50not statednot statedGoogle Gemini API page
checked 2026-11-14
re-checked 2026-11-16
—Google Vertex AI batch
gemini-4-hydrogen
Notes and source quote

Global endpoint; non-global regions cost 10% more.

“Gemini 4 Hydrogen [Global] Input (text, image, video, audio) $0.75 … Text output (response and reasoning) $3.75 … cached $0.0375”
USD 0.75USD 0.0375USD 3.75USD 1.50not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
—Google Gemini API maker flex / spot
gemini-4-hydrogen
Notes and source quote

Paid tier.

“Gemini 4 Hydrogen Flex: Input price $0.75 … Output price (including thinking tokens) $3.75 … Context caching price $0.0375 Implicit caching only (explicit caching is not supported).”
USD 0.75USD 0.0375USD 3.75USD 1.50not statednot statedGoogle Gemini API page
checked 2026-11-14
re-checked 2026-11-16
—Google Gemini API maker priority
gemini-4-hydrogen
Notes and source quote

Paid tier.

“Gemini 4 Hydrogen Priority: Input price $2.70 … Output price (including thinking tokens) $13.50 … Context caching price $0.135 Implicit caching only (explicit caching is not supported).”
USD 2.70USD 0.135USD 13.50USD 5.40not statednot statedGoogle Gemini API page
checked 2026-11-14
re-checked 2026-11-16
—Google Vertex AI priority
gemini-4-hydrogen
Notes and source quote

Global endpoint; non-global regions cost 10% more.

“Gemini 4 Hydrogen [Global] Input (text, image, video, audio) $2.70 … Text output (response and reasoning) $13.50 … cached $0.135”
USD 2.70USD 0.135USD 13.50USD 5.40not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Gemini 4 Hydrogen cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Gemini 4 Hydrogen, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Google Gemini API (maker)USD 193.05USD 369.90USD 1,195
Google Vertex AIUSD 193.05USD 369.90USD 1,195
PerplexityUSD 193.05USD 369.90USD 1,195

For the support chatbot, the cheapest price (Google Gemini API and 2 others, tied, USD 193.05 a month) saves USD 0 against the median (USD 193.05). For the coding agent the gap is USD 0 a month.

Which Gemini 4 Hydrogen provider is cheapest for your traffic?

All 3 providers charge the same standard price, USD 1.50 input and USD 7.50 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.

Gemini 4 Hydrogen: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Google Gemini API (maker)USD 3 cheapestUSD 2.466 cheapestUSD 2.038 cheapest
Google Vertex AIUSD 3 cheapestUSD 2.466 cheapestUSD 2.038 cheapest
PerplexityUSD 3 cheapestUSD 2.466 cheapestUSD 2.038 cheapest

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

All 3 providers publish a cached-input price below the input price: Google Gemini API (95% off), Google Vertex AI (95% off), Perplexity (95% off).

No provider states a context window for Gemini 4 Hydrogen on its pricing page.

Estimate your own bill

The Google models whose cheapest standard price is closest to Gemini 4 Hydrogen's (USD 3 blended):

Google models priced closest to Gemini 4 Hydrogen
ModelCheapest inputCheapest outputMax contextProviders
Gemini 3.5 FlashUSD 1.50USD 91,048,5763
Gemini 2.5 ProUSD 1.25USD 101,000,0003
Gemini 4 ArgonUSD 2USD 101,048,5764
Gemini 4 CarbonUSD 2USD 101,048,5764
Gemini 3.1 Pro PreviewUSD 2USD 121,048,5763
Gemini 3.6 FlashUSD 0.75USD 3.751,048,5763

Priced closest from other makers: Grok 4.5 (xAI, USD 3) · Grok 4.6 (xAI, USD 3) · Grok 4.7 (xAI, USD 3).

Compare Gemini 4 Hydrogen with

Also compared: vs Claude Sonnet 5.5 · vs GPT-6.1 Terra.

Every Gemini 4 Hydrogen price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Gemini 4 Hydrogen API cost per token?

From USD 1.50 per 1M input tokens (USD 0.0000015 per token) and USD 7.50 per 1M output tokens (USD 0.0000075 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 1.50 input and USD 7.50 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Gemini 4 Hydrogen?

Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 3 are tied for the lowest price: Google Gemini API, Google Vertex AI and Perplexity, each USD 3 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1.50 (Google Gemini API and 2 others, tied); for output alone, USD 7.50 (Google Gemini API and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Gemini 4 Hydrogen cheaper from a host than from Google Gemini API?

They tie. Google Vertex AI and Google Gemini API's own API both work out at USD 3 per 1M tokens on the 3:1 blend.

Does Gemini 4 Hydrogen have cached input pricing?

All 3 standard prices include one. The lowest is USD 0.075 per 1M at Google Gemini API; the median is USD 0.075. Providers without one bill cached input at the input price. What cached input means.

How much does a coding agent cost per month on Gemini 4 Hydrogen?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,195 a month at Google Gemini API, USD 1,195 at the median price and USD 1,195 at Perplexity. Try your own numbers.

Is there a batch, flex or priority price for Gemini 4 Hydrogen?

Yes: batch from Google Gemini API at USD 0.75 / USD 3.75; flex / spot from Google Gemini API at USD 0.75 / USD 3.75; priority from Google Gemini API at USD 2.70 / USD 13.50 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Gemini 4 Hydrogen free to use through an API?

No provider in our data lists a free price for Gemini 4 Hydrogen as of 2026-11-15. Google Gemini API's free offer names it: Free tier: many models show "Free of charge" on the pricing page, including Gemini 4 Hydrogen, Gemini 3.8 Flash and Gemini 3.5 Flash-Lite (source, checked 2026-11-14). Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity