[Integrations](https://spiral.ai/integrations) › [VS Code](https://spiral.ai/integrations/vscode) › [Gemini 3.1 Flash-Lite](https://spiral.ai/integrations/vscode/gemini-3-1-flash-lite)

# How to Use Gemini 3.1 Flash-Lite in VS Code

Gemini 3.1 Flash-Lite suits repeated translation, classification, and data extraction tasks. It also generates UI code, with adjustable reasoning for more involved requests.

|  |  |
| --- | --- |
| Model | Gemini 3.1 Flash-Lite |
| Available through | Vertex AI |
| Category | LLM |
| Price | Up to $0.008011 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $0.65 per 1M audio input tokens, $1.95 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Gemini 3.1 Flash-Lite in VS Code

- Use Gemini 3.1 Flash-Lite to build a sortable support-ticket table using this project's existing components. Include category filters and an empty state, use high reasoning, and run the relevant checks.
- Use Gemini 3.1 Flash-Lite to translate the English locale file into Spanish. Preserve keys, interpolation markers, and product names, and report strings that need translator review.
- Use Gemini 3.1 Flash-Lite with minimal reasoning to classify the messages in our support fixtures as billing, technical, account, or other. Return each fixture ID, category, and supporting excerpt as JSON.
- Use Gemini 3.1 Flash-Lite to extract order IDs, dates, and customer names from the text fixtures. Follow our existing record schema, use null for missing values, and validate the results.
- Use Gemini 3.1 Flash-Lite to summarize the design documents in this project into decisions, unresolved questions, and conflicting requirements. Cite file paths and supporting passages; keep the summary under 800 words.

## How to set up Gemini 3.1 Flash-Lite in VS Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: Use Add to VS Code on the console's Agents & MCP page, or run:

```bash
code --add-mcp '{"name":"spiral","type":"http","url":"https://api.spiral.ai/mcp"}'
```

2. **Sign in**: VS Code asks you to sign in when it first starts the server: sign in to Spiral and click Authorize. No API key. Run MCP: List Servers from the Command Palette to check that Spiral is running.

### Use the Spiral skill

1. **Send VS Code 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 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 3.1 Flash-Lite**: 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-3.1-flash-lite",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: VS Code finds Gemini 3.1 Flash-Lite on Spiral, shows the price and runs it.

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

## Gemini 3.1 Flash-Lite tools and prices

- [Gemini 3.1 Flash Lite](https://spiral.ai/tools/vertex/google/gemini-3.1-flash-lite) (Vertex AI): Up to $0.008011 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $0.65 per 1M audio input tokens, $1.95 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 65536 | — | The most output tokens to generate. |

## What can you do with Gemini 3.1 Flash-Lite in VS Code?

Turn project specifications into UI code and repetitive text work into structured records with Gemini 3.1 Flash-Lite. Give the agent a narrow task, relevant files, and clear acceptance criteria.

### Translate support replies

Translate repeated customer replies while preserving product names, order numbers, and a supplied terminology list.

### Classify incoming requests

Assign support messages to defined categories, with examples that distinguish billing questions, technical issues, and account requests.

### Extract records from text

Turn order confirmations or business messages into structured records. Require explicit evidence for each value and leave missing information empty.

### Review content against a policy

Label submitted text against a supplied moderation policy and flag uncertain cases for review.

### Summarize lengthy documents

Condense supplied documents into decisions, open questions, and supporting passages so a reviewer can check the summary.

### Build a dashboard prototype

Generate UI code from a defined layout, sample data, and interaction requirements, then test filtering, sorting, and empty states.

### Label customer feedback

Sort feedback into a fixed list of themes and return a short supporting excerpt for each label.

## Overview

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

## Gemini 3.1 Flash-Lite in other agents

- [Amp](https://spiral.ai/integrations/amp/gemini-3-1-flash-lite)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gemini-3-1-flash-lite)
- [Claude](https://spiral.ai/integrations/claude-desktop/gemini-3-1-flash-lite)
- [Claude Code](https://spiral.ai/integrations/claude-code/gemini-3-1-flash-lite)
- [Cline](https://spiral.ai/integrations/cline/gemini-3-1-flash-lite)
- [Codex](https://spiral.ai/integrations/codex/gemini-3-1-flash-lite)
- [Cursor](https://spiral.ai/integrations/cursor/gemini-3-1-flash-lite)
- [Devin](https://spiral.ai/integrations/devin/gemini-3-1-flash-lite)
- [dots](https://spiral.ai/integrations/dots/gemini-3-1-flash-lite)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gemini-3-1-flash-lite)
- [Gemini](https://spiral.ai/integrations/gemini/gemini-3-1-flash-lite)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gemini-3-1-flash-lite)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gemini-3-1-flash-lite)
- [goose](https://spiral.ai/integrations/goose/gemini-3-1-flash-lite)
- [Grok](https://spiral.ai/integrations/grok/gemini-3-1-flash-lite)
- [Grok Build](https://spiral.ai/integrations/grok-build/gemini-3-1-flash-lite)
- [Hermes](https://spiral.ai/integrations/hermes/gemini-3-1-flash-lite)
- [Instinct](https://spiral.ai/integrations/instinct/gemini-3-1-flash-lite)
- [Manus](https://spiral.ai/integrations/manus/gemini-3-1-flash-lite)
- [Muse](https://spiral.ai/integrations/muse/gemini-3-1-flash-lite)
- [Muse Code](https://spiral.ai/integrations/muse-code/gemini-3-1-flash-lite)
- [n8n](https://spiral.ai/integrations/n8n/gemini-3-1-flash-lite)
- [Notion](https://spiral.ai/integrations/notion/gemini-3-1-flash-lite)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gemini-3-1-flash-lite)
- [opencode](https://spiral.ai/integrations/opencode/gemini-3-1-flash-lite)
- [Perplexity](https://spiral.ai/integrations/perplexity/gemini-3-1-flash-lite)
- [Raycast](https://spiral.ai/integrations/raycast/gemini-3-1-flash-lite)
- [Windsurf](https://spiral.ai/integrations/windsurf/gemini-3-1-flash-lite)
- [Zapier](https://spiral.ai/integrations/zapier/gemini-3-1-flash-lite)

## More VS Code guides

- [Gemini 3 Flash Preview](https://spiral.ai/integrations/vscode/gemini-3-flash-preview)
- [Gemini 3.1 Pro Custom Tools](https://spiral.ai/integrations/vscode/gemini-3-1-pro-custom-tools)
- [GPT-oss-120B](https://spiral.ai/integrations/vscode/gpt-oss-120b)
- [Gemini 3.1 Pro Preview](https://spiral.ai/integrations/vscode/gemini-3-1-pro-preview)
- [GPT-oss Safeguard 20B](https://spiral.ai/integrations/vscode/gpt-oss-safeguard-20b)
- [Gemini 3.5 Flash](https://spiral.ai/integrations/vscode/gemini-3-5-flash)

## Questions about Gemini 3.1 Flash-Lite in VS Code

**Can VS Code use Gemini 3.1 Flash-Lite?**

Yes. Add Spiral to VS Code as an MCP server, and VS Code can find and run Gemini 3.1 Flash-Lite like any built-in tool.

**How much does Gemini 3.1 Flash-Lite cost in VS Code?**

Up to $0.008011 per run at the default inputs. $0.325 per 1M input tokens, $0.0325 per 1M cached input tokens, $0.108333335 per 1M cache write tokens, $0.65 per 1M audio input tokens, $1.95 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your VS Code plan is separate.

**Do I need a Vertex AI account to use Gemini 3.1 Flash-Lite in VS Code?**

No. Spiral runs Gemini 3.1 Flash-Lite on its own Vertex AI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Gemini 3.1 Flash-Lite in VS Code?**

About two minutes: add the hosted server, then sign in.

**Does VS Code wait while Gemini 3.1 Flash-Lite runs?**

Gemini 3.1 Flash-Lite runs in the background. VS Code starts the run, checks on it and gives you the text, json when it's ready.

**What is Gemini 3.1 Flash-Lite good at?**

It is designed for repeated translation, classification, and simple data extraction. Other documented uses include content moderation, document summaries, and generating UI code.

**How much text can Gemini 3.1 Flash-Lite handle?**

Google lists an input limit of 1,048,576 tokens and an output limit of 65,536 tokens. These are token limits, so avoid treating them as fixed word or page counts.

**When should I increase the reasoning level?**

Start with minimal reasoning for straightforward extraction and labeling. Try higher reasoning for requests with interacting constraints, such as generating a dashboard with filtering and validation.

**Can Gemini 3.1 Flash-Lite write code?**

Yes. Google specifically identifies user interfaces, dashboards, and simulations as supported coding uses; give it a concrete specification and test the resulting behavior.

**How should I write prompts for Gemini 3.1 Flash-Lite?**

State the task, constraints, and required output directly. Separate the source material from instructions, and include examples when labels or formatting could be ambiguous.

