Gemini 4 Hydrogen
Gemini 4 Hydrogen delivers high-speed inference and cost-efficient processing for everyday coding, task automation, and interactive conversational systems.
- Gemini 4 models
Compare the four models, Standard API prices and personal Gemini app access.
- Gemini 4 Neon API reference
Check the request model ID, Standard rates, thinking levels and output limits.
Browse Language Models models to compare other options for this task.
🚀Function Overview
Google launched gemini-4-hydrogen to Developer API general availability on November 12, 2026, offering both free and paid tiers. Paid Developer API usage costs $1.50 per million input tokens and $7.50 per million output tokens, with thinking tokens billing as output tokens. In personal apps, Free chats can route to Hydrogen through Auto. Plus, Pro, and Ultra can select it directly. Hydrogen accepts multimodal inputs across text, images, audio, video, and PDFs within a 1,048,576-token context window, returning text outputs with high thinking enabled by default.
Key Features
- Designed for fast interactive workflows, everyday coding and chat.
- Dual access tiers featuring a free Developer API option alongside standard $1.50/$7.50 pricing
- Accepts text, images, audio, video and PDF. The default synchronous output cap is 65,536 tokens. Long decode continues within the shared 1,048,576-token context.
- Flexible thinking settings spanning low, medium, high, and xhigh, with high enabled by default
Use Cases
- •Draft unit tests and check everyday code changes.
- •Running high-volume conversational interfaces and interactive customer support agents
- •Extracting structured summaries and answering queries from documents and multimedia inputs
⚙️Input Parameters
contents
arrayGemini generateContent contents with text or supported media parts
generationConfig
objectDocumented output and thinking configuration; ordinary synchronous output is distinct from long decode
💡Usage Examples
Example 1
Input Parameters
{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Review the supplied project notes. List confirmed findings, open questions, and the checks that would resolve them."
}
]
}
]
}Output Results
Quick Actions
Technical Specifications
- Hardware Type
- Hosted Google API
- Commercial Use
- Hosted API use follows Google’s terms.
- Pricing
- Gemini Developer API Standard. $1.50 input, $7.50 output and $0.075 cached input per million tokens on the Standard paid tier. A free tier is also available.