Spiral gives your agent every tool with one account. Browse the tools →

Instinct · LLMReleased 2026-11-18

How to Use Gemini 4 Neon in Instinct

Gemini 4 Neon suits multi-file debugging, architectural refactoring, and analytical work with several steps. It sits between Gemini 4 Carbon for the deepest long projects and Gemini 4 Hydrogen for fast everyday execution.

Prompts to try with Gemini 4 Neon in Instinct

Copy an example into Instinct, or ask in your own words.

Each morning, use Gemini 4 Neon with low reasoning to summarize the incident records supplied to this run. List new incidents, changed status, and unresolved follow-ups, citing record IDs.

Gemini 4 NeonInstinct
Try asking
  • Every hour, use Gemini 4 Neon with low reasoning to classify incoming support request text using our approved categories. Include the supporting sentence and flag requests that match multiple categories.

  • Each Friday, use Gemini 4 Neon to turn the week's supplied update messages into a project brief. Separate completed work, blockers, and decisions needed, with message references.

  • After each planning cycle, use Gemini 4 Neon with high reasoning to compare the supplied commitments with the current status records. Identify missed dependencies and unresolved contradictions without inventing dates or owners.

  • Each day, use Gemini 4 Neon with low reasoning to extract action items from new meeting transcripts supplied as text. Merge duplicates, preserve source references, and mark missing owners or deadlines as unspecified.

How to set up Gemini 4 Neon in Instinct

Pick the way that suits you. Each takes about two minutes.

Use the Spiral skill

  1. Send Instinct this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. 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

  1. Create an API key

    In the console, open API keys and create a key for Instinct. Copy it.

  2. Send Instinct this message

    Instinct reads Spiral's skill and asks for your API key.

    set up https://spiral.ai/SKILL.md
  3. 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

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run Gemini 4 Neon

    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": "vertex",
        "model": "google/gemini-4-neon",
        "input": {
          "messages": [
            {
              "role": "user",
              "content": "Hello!"
            }
          ]
        }
      }'

Then paste one of the prompts above: Instinct finds Gemini 4 Neon on Spiral, shows the price and runs it.

Gemini 4 Neon providers and prices

Spiral runs Gemini 4 Neon through Vertex AI. Open a card for today's price, with every fee included.

Vertex AILLM
Gemini 4 Neon
google/gemini-4-neon

Settings you can ask for

Ask Instinct for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number
Max tokens1 to 65536

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).

Reasoning effortlow, medium, or highhigh

How much the model reasons.

Every API field of Gemini 4 Neon is on its tool page: open its card above.

What can you do with Gemini 4 Neon in Instinct?

Turn recurring streams of text into consistent triage and operational summaries with Gemini 4 Neon. Define categories, evidence requirements, and escalation rules so each run produces a comparable result.

Trace a bug across files

Follow a failing request through its callers, identify the root cause, and propose a small patch with a regression test.

Plan an architectural refactor

Map dependencies before changing a shared interface. Request a staged migration plan with compatibility checks and rollback points.

Review a proposed code change

Inspect a diff for behavior changes and missing edge cases. Ask for a reproducible example for each suspected defect.

Compare technical proposals

Evaluate supplied proposals against explicit requirements. Separate documented support, assumptions, and unanswered questions.

Summarize operational incidents

Turn supplied event records into a timeline, impact summary, and follow-up list. Preserve uncertainty about causes.

Route incoming requests

Classify request text using a fixed category list and escalation rules. Include the supporting passage for each assignment.

Extract action items

Convert meeting text into tasks with owners and deadlines. Mark missing details explicitly instead of filling them in.

Build an evidence-based decision brief

Compare options using supplied research and constraints. Request a recommendation, its supporting evidence, and conditions that would change it.

Questions about Gemini 4 Neon in Instinct

Can Instinct use Gemini 4 Neon?

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Gemini 4 Neon like any built-in tool.

How much does Gemini 4 Neon cost in Instinct?

Up to $0.080009 per run at the default inputs. $3.90 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $19.50 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 a Vertex AI account to use Gemini 4 Neon in Instinct?

You need no Vertex AI account. Instinct uses one Spiral API key for every tool, and Spiral runs Gemini 4 Neon on its own Vertex AI account.

How long does it take to set up Gemini 4 Neon 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 Neon runs?

Gemini 4 Neon 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 Neon good at?

Gemini 4 Neon is built for complex coding and analytical work. Practical tasks include tracing bugs across files, planning architectural changes, and turning supplied evidence into a decision brief.

How does Gemini 4 Neon compare with Carbon and Hydrogen?

Google positions Gemini 4 Carbon for the deepest long projects and Gemini 4 Hydrogen for fast everyday execution. Gemini 4 Neon sits between them for demanding coding and analytical tasks.

How much context can Gemini 4 Neon handle?

The total budget is 1,048,576 tokens shared between input and output. Leave room for the response when supplying a large amount of material.

How long can a Gemini 4 Neon answer be?

Google documents a 65,536-token limit for a single foreground segment. That budget includes thinking and function calls as well as the visible answer, so it is not a promise of 65,536 tokens of prose.

When should I use more reasoning?

Use high reasoning for architectural refactoring, code generation, or analysis with several dependent steps. Low reasoning suits classification, summaries, and extracting structured details.

Get started

Start using Gemini 4 Neon in Instinct

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Instinct:

Set up Instinct

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options