Gemini 4 Hydrogen cost calculator

Hydrogen bills $1.50 per 1M input tokens, $0.075 per 1M cached input tokens (implicit caching, prompts of 4,096+ tokens), and $7.50 per 1M output tokens — and output includes thinking tokens. Enter your own token counts below; the thinking level changes how many output tokens you pay for, not the price per token.

Task type → Google’s recommended thinking level

Workload-to-level mapping is copied from Google Cloud’s Hydrogen developer guide. It sets the level only; your token counts stay yours.

Requests per month Input tokens per request Output tokens per request (thinking + answer) Share of input served from cache (%) Thinking level My output count was measured at — rescale it to the level above using Artificial Analysis’s measured output volume

The 50,000 / 8,000 defaults are placeholders, not a measurement. Read your real numbers from usage_metadata (prompt_token_count, cached_content_token_count, candidates_token_count, thoughts_token_count).

— per month on Hydrogen

Same token counts on other models

Official list prices (retrieved 13 November 2026). Cache discount applied only where the vendor publishes a Gemini cache-read rate here; other rows assume no cache. Real token counts differ by model and tokenizer.
Model	Price window	Monthly cost	Comparison

What each thinking level costs in practice

Measured independently by Artificial Analysis on each vendor's own API (retrieved 14 November 2026); speed is averaged over the past 5 days and changes. A dash means AA had not published that figure. This site did not run these tests.
Model · thinking/effort level	AA Intelligence Index	Output speed (tok/s)	Minutes per AA Index task	Time to first answer token (s)
Gemini 4 Hydrogen · xhigh	54	178	14.5	44.79
Gemini 4 Hydrogen · high	51	171	8.3	17.37
Gemini 4 Hydrogen · medium	41	174	3.8	11.81
Gemini 4 Hydrogen · low	27	173	1.4	5.58

Output tokens Artificial Analysis recorded while running its whole Intelligence Index (more tokens = more cost and time for the same work): Gemini 4 Hydrogen: xhigh 304M, high 110M, medium 54.4M, low 20.3M.

Google’s guidance: start with high, reserve xhigh for hard multi-step problems where high falls short, and pick the lowest level that meets your quality bar. xhigh “increases latency and token use and can cause overthinking on simpler prompts.” Billing counts every token the model processes, including thinking tokens and, with grounding, internal tool instructions; Grounding with Google Search is billed per query on top.

Source: Google AI Studio / Gemini API docs, Retrieved 13 November 2026 · Source: Google AI Studio / Gemini API docs, Retrieved 13 November 2026 · Source: Google Cloud documentation, Last updated 12 November 2026 · Artificial Analysis: Gemini 4 Hydrogen (retrieved 14 November 2026)

Related: Pricing · All comparisons · Errors & limits