Gemini 4 Hydrogen overview
Gemini 4 Hydrogen by Google
Gemini 4 Hydrogen is the fast, efficient model in Google's Gemini 4 family, aimed at everyday coding and agentic workflows. It accepts audio, image, text and video and answers in text.
Gemini 4 Hydrogen specs
- Model ID
google/gemini-4-hydrogen- Developer
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Input
- Audio, Image, Text, Video
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Long inputs, tool calls and structured replies
The context window holds 1,048,576 tokens, so a large codebase, a long transcript or a set of files can go into a single request. The model returns up to 65,536 tokens in one reply.
Parallel tool calls let an agent request several tools in one step instead of one after another. Structured output keeps the reply in a format your code can parse, and streaming returns text as it is generated.
Set reasoning effort to match the task
Reasoning effort is the one request option this endpoint exposes. It takes low, medium or high. Lower effort gives faster responses and spends fewer tokens on reasoning.
Start with low for routine edits, short answers and tool routing, since those are the everyday jobs this model targets. Move to medium or high only for tasks where low gives wrong answers, and compare the results on your own prompts.
Hydrogen, Carbon or Argon
Google positions Gemini 4 Carbon as a frontier model for coding, agentic and complex reasoning work. It describes Gemini 4 Argon as its flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.
Run the same set of prompts on Hydrogen first. Move up to Carbon or Argon only for the prompts where Hydrogen's answers fall short.
Use cases
Fix bugs and write small features across a repository loaded into one long prompt.
Run an agent that calls several tools in parallel to gather data and complete a multi-step task.
Extract structured fields from PDFs, screenshots or scanned pages and return them in a fixed format.
Summarize a recorded meeting or a video clip into notes with action items.
Capabilities
- File input
- Reasoning
- Streaming
- Structured outputs
- Function calling
- Vision
Gemini 4 Hydrogen API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $1.5 | 1M tokens |
| Output | $7.5 | 1M tokens |
| Cached input | $0.075 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 12, 2026.
Gemini 4 Hydrogen vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Gemini 4 Hydrogen | $1.5 | $7.5 |
| Gemini 3.8 Flash | $0.75 | $3.75 |
| Gemini 3.7 Flash | $0.75 | $3.75 |
| Gemini 3.6 Flash | $1.5 | $7.5 |
| Gemini 4 Argon | $2 | $10 |
How to use the Gemini 4 Hydrogen API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "google/gemini-4-hydrogen",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "google/gemini-4-hydrogen",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "google/gemini-4-hydrogen",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Gemini 4 Hydrogen
Related articles
Gemini 4 Hydrogen FAQ
How much does Gemini 4 Hydrogen cost?
Gemini 4 Hydrogen costs $1.5 / 1M tokens for input and $7.5 / 1M tokens for output on AI/ML API. Cached input is billed at $0.075 / 1M tokens.
Which inputs does Gemini 4 Hydrogen accept?
It accepts audio, image, text and video input, and file input is also supported. The output is text.
Which request option controls reasoning?
Reasoning effort accepts low, medium or high. Lower values give faster responses and use fewer tokens on reasoning.
How long can a single reply be?
The model returns up to 65,536 tokens per reply. Streaming is supported if you want to read the text as it is generated.
When should I use Gemini 4 Carbon or Gemini 4 Argon instead?
Google describes Carbon as a frontier model for complex reasoning work and Argon as its flagship reasoning model. Try Hydrogen first, then move up if your hardest prompts need it.
What is the Gemini 4 Hydrogen model ID?
Use google/gemini-4-hydrogen as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.
What is the context window of Gemini 4 Hydrogen?
Gemini 4 Hydrogen accepts up to 1,048,576 tokens of context and returns up to 65,536 output tokens.