Gemini 4 Hydrogen
The fast-execution tier of the Gemini 4 family rather than the deepest reasoner: at its default high thinking level it scores 51 on the Artificial Analysis Intelligence Index — just above the flagship Argon at 50 but clearly below Carbon at 60 — in exchange for faster responses and lower cost, with flat pricing across the full 1M context at $1.50 per million input and $7.50 per million output tokens, roughly 75% of Carbon/Argon rates. It is built for everyday coding, running and verifying tests, and serving as the execution engine or parallel worker sub-agents in multi-model orchestration; it can also carry agentic knowledge work such as deep research, data analysis, and summarizing PDFs, spreadsheets, audio or video. Hard architectural judgment and long-horizon work still belong to Carbon or Argon.
- Reasoning
- Web search
- Tool use
- Structured output
- Long context
AI Chat
Send a prompt and see the response here.
gemini-4-hydrogenStart a conversation with this model and ask follow-up questions.
USD /1M tokens
Pricing
| Group | Input | Output | Cache Read |
|---|---|---|---|
| default | $1.57 | $7.899926 | $0.100009 |
Public list prices are shown in USD. Final charges may vary by account group and usage tier.
API
Code examples
curl --location --request POST 'https://api.tokenhot.ai/v1beta/models/gemini-4-hydrogen:generateContent' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Hello"
}
}
]
}'FAQ
Frequently asked questions
What is Gemini 4 Hydrogen best suited for?
Gemini 4 Hydrogen is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.
How is Gemini 4 Hydrogen priced?
Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.
How can I call Gemini 4 Hydrogen?
Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.
Get started
Build with Gemini 4 Hydrogen
API