How to Use Gemini 4 Hydrogen in Instinct
Gemini 4 Hydrogen suits repository fixes, web prototypes, and repeatable document work. Google positions it for everyday execution, while Gemini 4 Carbon and Gemini 4 Argon target deeper, longer reasoning tasks.
Prompts to try with Gemini 4 Hydrogen in Instinct
Copy an example into Instinct, or ask in your own words.
Each morning, use Gemini 4 Hydrogen to summarize newly received support messages by issue, supporting passage, and unresolved question.
Each weekday, use Gemini 4 Hydrogen to classify new requests as billing, access, bug, or other. Flag ambiguous requests for review.
Each Friday, use Gemini 4 Hydrogen to turn this week's meeting text into open actions. Mark missing owners and deadlines.
Each morning, use Gemini 4 Hydrogen to compare incoming release announcements with yesterday's brief. Include only changes supported by the supplied text.
Each week, use Gemini 4 Hydrogen with high reasoning to compare new project updates with stated commitments and list unresolved contradictions.
How to set up Gemini 4 Hydrogen in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Gemini 4 Hydrogen
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "google/gemini-4-hydrogen:batch", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds Gemini 4 Hydrogen on Spiral, shows the price and runs it.
Gemini 4 Hydrogen providers and prices
Spiral runs Gemini 4 Hydrogen through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.020004 per run at the default inputs. $0.975 per 1M input tokens, $4.875 per 1M output tokens.
Settings you can ask for
Ask Instinct for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 943718 | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). | |
| Temperature | 0 to 2 | ||
| Reasoning effort | low, medium, high, or xhigh | medium | How much the model reasons. |
Every API field of Google: Gemini 4 Hydrogen (batch) is on its tool page: open its card above.
What can you do with Gemini 4 Hydrogen in Instinct?
Gemini 4 Hydrogen can turn recurring streams of text into categorized records and concise review briefs. Define the categories and evidence requirements so each run produces comparable results.
Fix a reproducible repository bug
Have Gemini 4 Hydrogen trace a failing test, propose a focused patch, and explain the validation results.
Build an interactive prototype
Ask Gemini 4 Hydrogen to turn a written specification into a small web tool with working controls and defined acceptance criteria.
Verify an implementation
Give Gemini 4 Hydrogen a specification and implementation to compare, then request missing behaviors and targeted test cases.
Extract action items
Use Gemini 4 Hydrogen to turn meeting text into tasks, owners, and deadlines, marking details absent from the source.
Classify support requests
Ask Gemini 4 Hydrogen to assign supplied messages to defined categories and retain a supporting passage for each decision.
Rewrite operational documents
Have Gemini 4 Hydrogen rewrite procedures for a specified audience while preserving exceptions, required steps, and terminology.
Compare research notes
Give Gemini 4 Hydrogen source excerpts and request a comparison table that separates agreement, disagreement, and missing evidence.
More on Gemini 4 Hydrogen and Instinct
Overview
Gemini 4 Hydrogen in other agents
Questions about Gemini 4 Hydrogen in Instinct
Can Instinct use Gemini 4 Hydrogen?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Gemini 4 Hydrogen like any built-in tool.
How much does Gemini 4 Hydrogen cost in Instinct?
Up to $0.020004 per run at the default inputs. $0.975 per 1M input tokens, $4.875 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need an OpenRouter account to use Gemini 4 Hydrogen in Instinct?
You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs Gemini 4 Hydrogen on its own OpenRouter account.
How long does it take to set up Gemini 4 Hydrogen in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Gemini 4 Hydrogen runs?
Gemini 4 Hydrogen runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is Gemini 4 Hydrogen good at?
It suits repository fixes, debugging, interactive web prototypes, and document tasks with explicit formatting requirements. Give it a concrete deliverable and clear acceptance criteria.
How does Gemini 4 Hydrogen compare with Carbon and Argon?
Google positions Hydrogen for everyday execution. Carbon and Argon target deeper, longer reasoning, including architectural judgment and difficult bugs.
How much can Gemini 4 Hydrogen write?
Google documents a default limit of 65,536 combined reasoning and output tokens per response. Longer generation uses continuation, and input, reasoning, and output must together fit within 1,048,576 tokens.
When should I use extra-high reasoning?
Reserve it for difficult coding or multistep problems that high reasoning does not solve. It uses more tokens and can overthink straightforward text or JSON extraction.
Does lowering temperature make Gemini 4 Hydrogen more consistent?
Google says Hydrogen ignores in-range custom temperature and sampling values. Specify the required format, constraints, and an example instead.
Start using Gemini 4 Hydrogen in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


