Google Gemini 4 Hydrogen: Pricing, Specs and Limits
Google Gemini 4 Hydrogen: high-efficiency workhorse model of the Gemini 4 family, 1M context, 1.50 in / 7.50 out per 1M tokens. Specs, limits and test...
By ShilpBot Team · Published · 3 min read
Gemini 4 Hydrogen is described as the high-efficiency workhorse of Google's Gemini 4 family, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than the larger models in the family.
It accepts audio, files, images, text and video, which is the widest input list of any model in this series, and can return up to 943,718 tokens in one response.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Google Gemini 4 Hydrogen quick facts
| Detail | Value |
|---|---|
| Developer | |
| Model ID | google/gemini-4-hydrogen |
| Added to the catalogue | 2026-11-12 |
| Type | High-efficiency workhorse model of the Gemini 4 family |
| Parameters | Not listed |
| Context window | about 1M tokens (1,048,576) |
| Maximum output | 943,718 tokens |
| Input types | audio, file, image, text, video |
| Price | 1.50 in / 7.50 out per 1M tokens (cached input 0.075) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What Google Gemini 4 Hydrogen is good for
- High-volume agent steps and routing, where the listing says it is designed to be cheaper and faster.
- Mixed-media inputs, such as an audio note plus a PDF plus screenshots in one request.
- Coding assistance at moderate cost.
Limits of Google Gemini 4 Hydrogen
- It is cheaper than Carbon and Argon but still $7.50 per million output tokens, so long outputs add up.
- A 943K output limit is a ceiling. Ask for what you need.
- Check file and audio size limits in your client, since they vary.
How Google Gemini 4 Hydrogen compares
- Google Gemini 4 Carbon: Both have a 1,048,576-token context window; both cap output at 943,718 tokens; it costs 1.50 input and 7.50 output per million tokens against 2.00 and 10.00.
- Google Gemini 4 Argon: Both have a 1,048,576-token context window; both cap output at 943,718 tokens; it costs 1.50 input and 7.50 output per million tokens against 2.00 and 10.00.
- Anthropic Claude Haiku 5.5: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 943,718 tokens against 128,000; it also accepts audio and video input; it costs 1.50 input and 7.50 output per million tokens against 0.10 and 0.50.
Calling Google Gemini 4 Hydrogen from code
Use the model ID google/gemini-4-hydrogen with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/gemini-4-hydrogen", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Google Gemini 4 Hydrogen can do
- Send a voice memo and a screenshot together and ask for a combined bug report.
- Use it as a router: ask it to label 20 requests as simple or complex and compare with your own labels.
- Give it a failing test and the code and ask for a minimal fix.
What Google Gemini 4 Hydrogen costs
The catalogue lists 1.50 per million input tokens and 7.50 per million output tokens, with cached input at 0.075 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 2.25. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.30 before caching. If your client reuses the same prompt prefix, cached input at 0.075 per million tokens can cut the input side of that bill by about 95 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
How does Gemini 4 Hydrogen differ from Carbon and Argon?
Google positions Hydrogen as the efficient workhorse. Carbon and Argon are higher-end Gemini 4 models and cost $2.00 input and $10.00 output per million tokens against $1.50 and $7.50 for Hydrogen.
What are the cost and limits of Google Gemini 4 Hydrogen?
As of 2026-11-16 the catalogue lists 1.50 per million input tokens and 7.50 per million output tokens. About 1M tokens (1,048,576) context window, up to 943,718 output tokens, model ID google/gemini-4-hydrogen. Prices can change, so check the live model page.
