Google
Operational· checked every few minutes

Gemini 4 Hydrogen API

The Gemini 4 Hydrogen API, Google's fast Gemini 4 model for everyday coding and agents, 60% below Google's list price

Price per 1M tokens60%off
Input
$0.60$1.50
Output
$3.00$7.50
Cached input
$0.03$0.075
Get your API keyTry it in the playground
Model IDgemini-4-hydrogenUpdated
chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="gemini-4-hydrogen",
    messages=[
        {"role": "user", "content": "Explain quicksort briefly."},
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK. Chat API docs

Context window
1M tokens
Max output
64K tokens
Reasoning
low · medium · high
Input
Text, Image, Audio
Released
Nov 12, 2026
Status
Operational

Pricing

Gemini 4 Hydrogen API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

RateZurelayGoogle list
Input
per 1M tokens
$0.60$1.50
Output
per 1M tokens
$3.00$7.50
Cached input
per 1M tokens
$0.03$0.075

One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.

Every Gemini model and price
Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M
Output tokens per month10M
Zurelay
$60.00
Google list price
$150.00
You save every month$90.00

$1,080 a year

Cost

Gemini 4 Hydrogen API cost, worked out. And compared.

Typical workloads at Zurelay's live prices next to the list price, and what other places charge for the same model.

  • Chatbot

    50,000 requests a month, 1,500 tokens in and 300 out, 30% of the input cached. $0.00154 a request.

    $77.18a month$192.94 at list

  • Documents

    20,000 requests a month, 8,000 tokens in and 500 out, 20% of the input cached. $0.00539 a request.

    $107.76a month$269.40 at list

  • Coding agent

    5,000 requests a month, 40,000 tokens in and 1,500 out, 85% of the input cached. $0.00912 a request.

    $45.60a month$114.00 at list

  • Classification

    1,000,000 requests a month, 400 tokens in and 5 out. $0.000255 a request.

    $255.00a month$637.50 at list

Where to buy Gemini 4 Hydrogen

Prices per 1M tokens

SellerInputOutput
Google
List price, direct
$1.50$7.50
OpenRouter
List price, plus 5.5% on card top-ups
$1.50$7.50
Zurelay
No fee to add credit
$0.60$3.00

OpenRouter's fee as its pricing page listed it on October 28, 2026. Zurelay's prices are live. Some labs also discount batch or off-peak requests.

Overview

What is Gemini 4 Hydrogen?

Gemini 4 Hydrogen is Google's fast, efficient Gemini 4 model for everyday coding and agentic workflows, released on November 12, 2026. The Zurelay Gemini 4 Hydrogen API serves it through one OpenAI-compatible endpoint with a 1M-token context window, at 60% below Google's list price.

Google released Gemini 4 Hydrogen on November 12, 2026, as gemini-4-hydrogen in the Gemini API and Google AI Studio. It takes the place of the Flash name in the Gemini 4 line: Google built it for rapid execution, and leaves deep, long-horizon reasoning to its frontier models. On Zurelay the model ID is gemini-4-hydrogen and it costs $0.60 per 1M input tokens and $3.00 per 1M output tokens.

Google says Hydrogen finishes tasks 2.5 times faster than Gemini 3.8 Flash at its default thinking level, and reports 57% on Terminal-Bench 4.1 against 18.2% for Gemini 3.8 Flash. It scores 51 on the Artificial Analysis Intelligence Index, one point above Gemini 4 Argon, 52.3% on the Vals Tax Agent Bench, first overall, and 55.8% on the Vals Legal Research Bench, tied for first. In early partner tests on SQL and data-heavy workflows it ran 2 to 2.8 times faster than 3.8 Flash and used 12% to 23% fewer tokens.

The context window is 1,048,576 tokens shared by input and output, with up to 65,536 output tokens per response. On Zurelay the model reads text, images, audio and PDFs and writes text. Thinking is built in, at low, medium or high; Zurelay uses medium unless you set reasoning_effort. It supports function calling and structured outputs, and Google caches repeated prompt prefixes automatically, so cached input bills at $0.03 per 1M tokens. Thinking tokens bill as output.

Google's price is $1.50 input and $7.50 output per 1M tokens, the same at every prompt length. Google also reports that Hydrogen is steadier in agent work than 3.8 Flash: up to 81% less overreach, up to 79% less under-service, and half as likely to go around a permission boundary when a task is blocked.

Strengths

Where Gemini 4 Hydrogen shines. And what teams build with it.

01

Speed

Google says it finishes tasks 2.5 times faster than Gemini 3.8 Flash at its default thinking level, and partners measured 2 to 2.8 times faster runs.

02

Coding in the terminal

57% on Terminal-Bench 4.1, against 18.2% for Gemini 3.8 Flash, for agents that work through a shell and a codebase.

03

Professional research

52.3% on the Vals Tax Agent Bench, first overall, and 55.8% on the Vals Legal Research Bench, tied for first.

04

Reliable agent behavior

Up to 81% less overreach and up to 79% less under-service than Gemini 3.8 Flash in Google's agentic tests.

Use cases

  • Everyday coding

    Edits, reviews, tests and terminal work in coding tools, where a fast answer matters on every step.

  • Worker agents

    The model that runs and checks the steps while a larger model plans, which is how Google pairs it with its frontier models.

  • Data and SQL work

    Queries, charts and spreadsheet-style analysis, where Google's partners saw faster runs and fewer tokens.

  • Long documents

    Read contracts, reports or a codebase in up to 1,048,576 tokens and answer questions across them.

Get started

Call Gemini 4 Hydrogen in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

  1. 1

    Create a key

    Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.

    Get your API key
  2. 2

    Point your SDK at Zurelay

    Change the base URL. Everything else in your code stays the same.

    https://api.zurelay.com/v1
  3. 3

    Use gemini-4-hydrogen

    Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.

    gemini-4-hydrogen

Works with the tools you already use

Compare

Similar models. All on the same key.

60%off

Gemini 4 Argon

$0.80 / $4.00 per 1M tokens

Pick Gemini 4 Argon, Google's frontier model, for the longest and hardest multi-step work.

Gemini 4 Argon API
71%off

Gemini 3.8 Flash

$0.22 / $1.10 per 1M tokens

Pick Gemini 3.8 Flash for the same 1M-token context at a lower price per token, with video input.

Gemini 3.8 Flash API
75%off

GPT-6.1 Terra

$0.25 / $1.25 per 1M tokens

Pick GPT-6.1 Terra to compare OpenAI's mid-tier model on everyday coding and agent work.

GPT-6.1 Terra API

FAQ

Gemini 4 Hydrogen API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the Gemini 4 Hydrogen API cost?

On Zurelay, gemini-4-hydrogen costs $0.60 per 1M input tokens and $3.00 per 1M output tokens, with cached input at $0.03. Google's price is $1.50 input and $7.50 output per 1M, so you save 60%. Thinking tokens bill as output.

What is Gemini 4 Hydrogen best at?

Fast, everyday coding and agent work. Google reports 57% on Terminal-Bench 4.1, 52.3% on the Vals Tax Agent Bench and 55.8% on the Vals Legal Research Bench, and says it finishes tasks 2.5 times faster than Gemini 3.8 Flash.

How do I call the Gemini 4 Hydrogen API with the OpenAI SDK?

Install the official openai package, set base_url to https://api.zurelay.com/v1 and use your Zurelay API key. Then send a Chat Completions request with model set to "gemini-4-hydrogen". Images, PDFs and audio go in the message as data or links.

What is the Gemini 4 Hydrogen context window?

Gemini 4 Hydrogen has a 1,048,576-token context window shared by input and output, and writes up to 65,536 output tokens per response. On Zurelay it accepts text, image, audio and PDF input and writes text.

How do Gemini 4 Hydrogen thinking levels work?

The model thinks before it answers. On Zurelay you pick low, medium or high with reasoning_effort, and medium is used when you don't. Low answers fastest and costs the least; high thinks the longest, so stream long requests. Google's xhigh level is not offered on Zurelay yet.

Should I use Gemini 4 Hydrogen or Gemini 4 Argon?

Use Hydrogen for fast, everyday coding and agent steps at a lower price. Use Argon for the longest and hardest multi-step problems. Both have a 1M-token context window and work with the same Zurelay key, so test them side by side on your own prompts.

Is Gemini 4 Hydrogen the new Gemini Flash?

In effect, yes. Google released Hydrogen in place of a Gemini 4 Flash model, compares it with Gemini 3.8 Flash throughout its announcement, and uses it for fast, everyday work. Gemini 3.8 Flash stays available on Zurelay at a lower price per token.

Is it the same model as Google's Gemini 4 Hydrogen?

Yes, it is Google's Gemini 4 Hydrogen. Responses are sampled, so wording varies between runs, and Zurelay does not promise byte-identical output. Zurelay is independent and is not affiliated with or endorsed by Google.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer