gemini-4-hydrogen
Google/Proprietary/2 providers
Gemini 4 Hydrogen is the high efficiency workhorse of Google's Gemini 4 family, built for high throughput agentic workflows, coding and routing at lower cost and latency, with a unified 1M token context window.MoreLess
Which id to call
gemini-4-hydrogen@usRequesty routes this id across every provider serving gemini-4-hydrogen, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
From /1M input
$0.75
Google Gemini API
Context
1.0M
66K output
Endpoints
5
3 regions
Price spread
2.2x
5 endpoints
Capabilities 6/8
5 endpoints / 3 regions
Providers serving gemini-4-hydrogen
Provider prices, per 1M tokens. Pay as you go adds 5%, or 0% on your own keys.
| Rank | Privacy | ||||||
|---|---|---|---|---|---|---|---|
| 1 | Google Gemini API | Global | 1.0M | $0.75 | $3.75 | $0.04 | zdr |
| 2 | Google Gemini API | Global | 1.0M | $1.50 | $7.50 | $0.07 | zdr |
| 3 |  Google Vertex AI | Global | 1.0M | $1.50 | $7.50 | $0.07 | zdr |
| 4 | Google Vertex AI | eu | 1.0M | $1.65 | $8.25 | $0.08 | zdr |
| 5 | Google Vertex AI | us | 1.0M | $1.65 | $8.25 | $0.08 | zdr |
A column is blank where no qualifying sample exists, and every row links to that provider's endpoint page.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
gemini-4-hydrogen@usRequesty routes this id across every provider serving gemini-4-hydrogen, picking on price and health and failing over automatically. The id stays valid when a provider changes underneath it.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="gemini-4-hydrogen@us", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
6
More from Google
Reference
gemini-4-hydrogen questions
Which providers serve gemini-4-hydrogen?
gemini-4-hydrogen is available from 2 providers through Requesty: Google Gemini API, Google Vertex AI. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does gemini-4-hydrogen cost?
Pricing starts at $0.75 per million input tokens and $3.75 per million output tokens on Google Gemini API, the cheapest endpoint. Prices vary by provider and region; the table above shows every endpoint. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
Is gemini-4-hydrogen open weights?
No. gemini-4-hydrogen is a proprietary model from Google, served through Google's own API and licensed cloud platforms.
What is the context window of gemini-4-hydrogen?
gemini-4-hydrogen supports up to 1.0M tokens of context, with up to 66K output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
How do I use gemini-4-hydrogen with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "gemini-4-hydrogen@us" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call gemini-4-hydrogen by its managed id or a provider id?
Use the managed id, "gemini-4-hydrogen@us". Requesty picks which of the 2 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. There is also an EU-only id, "gemini-4-hydrogen@eu", which routes the same way but only through EU-hosted providers. Send a provider id like "google/gemini-4-hydrogen:flex" only when you need one specific deployment and want no failover.
Route gemini-4-hydrogen through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in.