Gemini 4 Hydrogen is a large language model made by Google, added to the catalog on 12 Nov 2026. It has a context window of 1,048,576 tokens and costs $1.50 per 1M input tokens and $7.50 per 1M output tokens. It accepts text, images, files, audio and video and produces text. Typical uses: coding workflows, reviewing long documents and working with mixed-media inputs.
Price checked ยท source: OpenRouter
What Gemini 4 Hydrogen is
Google Gemini 4 Hydrogen is a Google model in the Gemini 4 family, described as a high-efficiency workhorse for high-throughput agentic workflows, coding, and multi-model routing. It accepts text, files, images, audio, and video as input, and produces text. Its listed capabilities include reasoning, tool support, structured outputs, and response-format controls. The model can therefore be considered for workflows that combine different input types with text responses or structured results. The catalog lists audio and video as accepted inputs, but text as the only produced output.
The model has a context window of 1,048,576 tokens and a maximum output of 943,718 tokens. This capacity suits requests that place substantial source material in a single context, such as reviewing long documents or working with multiple files, and supports extended text generation. The catalog identifies coding and agentic workflows as intended areas, with multi-model routing also part of its stated focus. Its support for tools and structured outputs may suit tasks that rely on tool-enabled workflows or responses in a specified format. The available facts do not specify particular programming languages, file formats, audio or video tasks, or tool integrations, so those details should not be assumed. Gemini 4 Hydrogen is relevant when a workflow calls for broad input modalities, text output, and a large context.
Key features
- Accepts text, files, images, audio, and video; produces text
- Has a context window of 1,048,576 tokens
- Supports tool use, reasoning, structured outputs, and response formats
- Maximum output length is 943,718 tokens
- Described for coding, agentic workflows, and multi-model routing
Typical uses
- Coding workflows
- Reviewing long documents
- Working with mixed-media inputs
- Generating structured text responses
- Tool-enabled agentic workflows
- Multi-model routing
Gemini 4 Hydrogen pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $1.50 | $0.75 |
| Output, per 1M tokens | $7.50 | $3.75 |
| Cached input read, per 1M tokens | $0.075 | $0.0375 |
| Cache write, per 1M tokens | $0.0833 | $0.0833 |
| Image input, per image | $0.000002 | $0.000001 |
| Web search, per search | $0.014 | $0.014 |
| Variant | Model id |
|---|---|
| Batch | google/gemini-4-hydrogen:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 12 Nov 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0030 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.044 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.060 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.236 |
Gemini 4 Hydrogen specifications
| Model id | google/gemini-4-hydrogen |
|---|---|
| Version | gemini-4-hydrogen-20261112 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 12 Nov 2026 |
| Input types | audio, file, image, text, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Gemini 4 Hydrogen yet.
Compare Gemini 4 Hydrogen
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.