[Integrations](https://spiral.ai/integrations) › [n8n](https://spiral.ai/integrations/n8n) › [Gemini 3.5 Flash](https://spiral.ai/integrations/n8n/gemini-3-5-flash)

# How to Use Gemini 3.5 Flash in n8n

Gemini 3.5 Flash suits code changes, document analysis, and tasks with several steps. Gemini 3.6 Flash improves on it with fewer unwanted edits and debugging loops.

|  |  |
| --- | --- |
| Model | Gemini 3.5 Flash |
| Available through | Vertex AI |
| Category | LLM |
| Price | Up to $0.04806 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $3.90 per 1M audio input tokens, $11.70 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Gemini 3.5 Flash in n8n

- Use Gemini 3.5 Flash each morning to classify the supplied support messages as billing, bug, feature request, or other. Return counts and a review queue for ambiguous messages.
- Use Gemini 3.5 Flash each week to compare the supplied old and new policy text. Report changed requirements with quotations and omit wording changes that preserve meaning.
- Use Gemini 3.5 Flash each afternoon to extract owners, deadlines, and blockers from the supplied project updates. Mark missing owners or dates explicitly.
- Use Gemini 3.5 Flash with low reasoning effort to categorize each supplied product feedback message. Return a JSON record containing its identifier, category, and supporting phrase.
- Use Gemini 3.5 Flash each month to organize the supplied financial summaries. List reported amounts, conflicting statements, and missing details with source passages for review.

## How to set up Gemini 3.5 Flash in n8n

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

### Use the Spiral skill

1. **Send n8n 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 a key**: Create a key under API keys in the console.

2. **Add an MCP Client node**: In a workflow, add an MCP Client node (or, under an AI Agent node, an MCP Client Tool) and set:

```text
https://api.spiral.ai/mcp
```

3. **Pick a tool**: The node lists Spiral's tools. In an MCP Client node pick one, such as `run`, and give it its arguments:

```json
{
  "provider": "fal",
  "model": "fal-ai/flux/schnell",
  "input": { "prompt": "a lighthouse at dawn" },
  "wait": true
}
```

4. **Run Gemini 3.5 Flash in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Gemini 3.5 Flash, prices it and runs it each time the step fires.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Gemini 3.5 Flash**: One request; the result comes back by polling or a webhook.

```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-3.5-flash",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: n8n finds Gemini 3.5 Flash on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/n8n

## Gemini 3.5 Flash tools and prices

- [Gemini 3.5 Flash](https://spiral.ai/tools/vertex/google/gemini-3.5-flash) (Vertex AI): Up to $0.04806 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $3.90 per 1M audio input tokens, $11.70 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 65536 | — | The most output tokens to generate. |
| tool_choice |  | — |  |

## What can you do with Gemini 3.5 Flash in n8n?

Gemini 3.5 Flash can turn recurring batches of text into categorized queues and review summaries. Define the categories, evidence requirements, and stopping point for each run.

### Fix a reproducible bug

Use Gemini 3.5 Flash to trace a failing test, propose a focused patch, and explain which behavior the patch changes.

### Plan a codebase migration

Have Gemini 3.5 Flash map dependencies, divide a migration into reviewable changes, and identify checks for each stage.

### Build an application prototype

Ask Gemini 3.5 Flash to turn a written specification into application code, then revise it against concrete acceptance criteria.

### Compare long documents

Give Gemini 3.5 Flash the source text and ask for conflicting requirements, changed obligations, and supporting passages.

### Extract records from text

Use Gemini 3.5 Flash to extract names, dates, amounts, and source passages into JSON for validation.

### Sort incoming requests

Have Gemini 3.5 Flash classify support requests against defined categories and flag ambiguous cases for review.

### Prepare a financial document review

Ask Gemini 3.5 Flash to organize supplied financial text into a checklist of reported amounts, missing details, and questions for the reviewer.

## Overview

- [Google Vertex AI](https://spiral.ai/providers/vertex)
- [All n8n guides](https://spiral.ai/integrations/n8n)

## Gemini 3.5 Flash in other agents

- [Amp](https://spiral.ai/integrations/amp/gemini-3-5-flash)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gemini-3-5-flash)
- [Claude](https://spiral.ai/integrations/claude-desktop/gemini-3-5-flash)
- [Claude Code](https://spiral.ai/integrations/claude-code/gemini-3-5-flash)
- [Cline](https://spiral.ai/integrations/cline/gemini-3-5-flash)
- [Codex](https://spiral.ai/integrations/codex/gemini-3-5-flash)
- [Cursor](https://spiral.ai/integrations/cursor/gemini-3-5-flash)
- [Devin](https://spiral.ai/integrations/devin/gemini-3-5-flash)
- [dots](https://spiral.ai/integrations/dots/gemini-3-5-flash)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gemini-3-5-flash)
- [Gemini](https://spiral.ai/integrations/gemini/gemini-3-5-flash)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gemini-3-5-flash)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gemini-3-5-flash)
- [goose](https://spiral.ai/integrations/goose/gemini-3-5-flash)
- [Grok](https://spiral.ai/integrations/grok/gemini-3-5-flash)
- [Grok Build](https://spiral.ai/integrations/grok-build/gemini-3-5-flash)
- [Hermes](https://spiral.ai/integrations/hermes/gemini-3-5-flash)
- [Instinct](https://spiral.ai/integrations/instinct/gemini-3-5-flash)
- [Manus](https://spiral.ai/integrations/manus/gemini-3-5-flash)
- [Muse](https://spiral.ai/integrations/muse/gemini-3-5-flash)
- [Muse Code](https://spiral.ai/integrations/muse-code/gemini-3-5-flash)
- [Notion](https://spiral.ai/integrations/notion/gemini-3-5-flash)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gemini-3-5-flash)
- [opencode](https://spiral.ai/integrations/opencode/gemini-3-5-flash)
- [Perplexity](https://spiral.ai/integrations/perplexity/gemini-3-5-flash)
- [Raycast](https://spiral.ai/integrations/raycast/gemini-3-5-flash)
- [VS Code](https://spiral.ai/integrations/vscode/gemini-3-5-flash)
- [Windsurf](https://spiral.ai/integrations/windsurf/gemini-3-5-flash)
- [Zapier](https://spiral.ai/integrations/zapier/gemini-3-5-flash)

## More n8n guides

- [Gemini 3.1 Pro Preview](https://spiral.ai/integrations/n8n/gemini-3-1-pro-preview)
- [Gemini 3.5 Flash-Lite](https://spiral.ai/integrations/n8n/gemini-3-5-flash-lite)
- [Gemini 3.1 Pro Custom Tools](https://spiral.ai/integrations/n8n/gemini-3-1-pro-custom-tools)
- [Gemini 3.7 Flash](https://spiral.ai/integrations/n8n/gemini-3-7-flash)
- [Gemini 3.1 Flash-Lite](https://spiral.ai/integrations/n8n/gemini-3-1-flash-lite)
- [Gemini 3.8 Flash](https://spiral.ai/integrations/n8n/gemini-3-8-flash)

## Questions about Gemini 3.5 Flash in n8n

**Can n8n use Gemini 3.5 Flash?**

Yes. Add Spiral to n8n as an MCP server, and n8n can find and run Gemini 3.5 Flash like any built-in tool.

**How much does Gemini 3.5 Flash cost in n8n?**

Up to $0.04806 per run at the default inputs. $1.95 per 1M input tokens, $0.195 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $3.90 per 1M audio input tokens, $11.70 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your n8n plan is separate.

**Do I need a Vertex AI account to use Gemini 3.5 Flash in n8n?**

You need no Vertex AI account. n8n uses one Spiral API key for every tool, and Spiral runs Gemini 3.5 Flash on its own Vertex AI account.

**How long does it take to set up Gemini 3.5 Flash in n8n?**

About two minutes: create a key, then add an MCP Client node, then pick a tool.

**Does n8n wait while Gemini 3.5 Flash runs?**

Gemini 3.5 Flash runs in the background. n8n starts the run, checks on it and gives you the text, json when it's ready.

**What is Gemini 3.5 Flash good at?**

Code generation, codebase maintenance, and workflows that require several steps are documented uses. It can also turn supplied documents into summaries or extracted records.

**How much context can Gemini 3.5 Flash handle?**

Google lists a context window of 1,048,576 tokens and a maximum output of 65,536 tokens. For long documents, put the source material before the final question.

**Can Gemini 3.5 Flash generate images or video?**

Its output is text. It can write code for a visual interface, but it does not directly return generated image, audio, or video files.

**When should I increase reasoning effort?**

Use high effort for hard math, complex reasoning, or difficult coding problems. Try low effort when faster responses matter, and compare the results on your actual task.

**Can I trust every value in its JSON?**

Validate the values before using them. Correct JSON syntax does not establish that a date, amount, or extracted name matches the source.

