# Gemini 4 Hydrogen

Generate and analyse text with Gemini 4 Hydrogen from Vertex AI through one Spiral API key. It runs in the background and returns text and structured JSON. Pay as you go, with no subscription.

- Provider: Vertex AI
- Category: LLM
- Runs: In the background
- Returns: text, json
- Released: 2026-11-12
- Tool id: `vertex` / `google/gemini-4-hydrogen`
- Page: https://spiral.ai/tools/vertex/google/gemini-4-hydrogen

## Pricing

Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $0.0975 per 1M cached input tokens, $2.4375 per 1M cache write tokens, $9.75 per 1M output tokens.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 225 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `messages` (required) | JSON |  | — | The conversation so far, oldest first. |
| `seed` | number (whole) |  | — |  |
| `stop` | JSON |  | — |  |
| `tools` | JSON |  | — |  |
| `reasoning` | JSON |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| `max_tokens` | number (whole) | 1 to 65536 | — | The most output tokens to generate. |
| `tool_choice` | JSON |  | — |  |
| `response_format` | JSON |  | — |  |
| `reasoning_effort` | one of | low, medium, high | medium | How much the model reasons. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "vertex",
    "model": "google/gemini-4-hydrogen",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=vertex&model=google%2Fgemini-4-hydrogen

## Common questions

### Gemini 4 Hydrogen

**How much does Gemini 4 Hydrogen cost?**

Up to $0.040005 per run at the default inputs. $1.95 per 1M input tokens, $0.0975 per 1M cached input tokens, $2.4375 per 1M cache write tokens, $9.75 per 1M output tokens. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Gemini 4 Hydrogen through an API?**

Send `POST /v1/runs` with `"provider": "vertex"`, `"model": "google/gemini-4-hydrogen"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with Vertex AI to use Gemini 4 Hydrogen?**

No. Spiral runs it on its own Vertex AI account and charges your Spiral balance.

**Can my AI agent use Gemini 4 Hydrogen?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

