[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [Gemini 3.1 Pro Custom Tools](https://spiral.ai/integrations/muse-code/gemini-3-1-pro-custom-tools)

# How to Use Gemini 3.1 Pro Custom Tools in Muse Code

Gemini 3.1 Pro Custom Tools suits coding and investigations that combine Bash with custom search and inspection tools. Compared with Gemini 3.1 Pro Preview, it prioritizes custom tools more strongly, though Google warns of quality fluctuations on tasks that do not benefit from tools.

|  |  |
| --- | --- |
| Model | Gemini 3.1 Pro Custom Tools |
| Available through | Vertex AI |
| Category | LLM |
| Price | Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $0.4875 per 1M cache write tokens, $15.60 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $0.975 per 1M cache write tokens, $23.40 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 Pro Custom Tools in Muse Code

- Use Gemini 3.1 Pro Custom Tools to investigate the failing tests in this repository. Search and inspect the relevant code, reproduce one failure, make the smallest justified fix, and report the test results.
- Use Gemini 3.1 Pro Custom Tools with high reasoning to audit the retry logic in this project. Trace callers and error handling, identify a reproducible duplicate-processing path, and add a focused regression test.
- Use Gemini 3.1 Pro Custom Tools to refactor the duplicated validation code in this repository. Find all callers before editing, preserve current behavior, and run the relevant checks after each meaningful change.
- Use Gemini 3.1 Pro Custom Tools to compare this branch with the main branch. Inspect changed behavior and related tests, then return the three most consequential findings with file references and evidence.
- Use Gemini 3.1 Pro Custom Tools to trace this project's request lifecycle from route to database call. Use search and inspection tools, then produce a concise map of the actual code paths and unresolved assumptions.

## How to set up Gemini 3.1 Pro Custom Tools in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse 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 Pro Custom Tools**: 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-pro-preview-customtools",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse Code finds Gemini 3.1 Pro Custom Tools on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## Gemini 3.1 Pro Custom Tools tools and prices

- [Gemini 3.1 Pro Preview Custom Tools](https://spiral.ai/tools/vertex/google/gemini-3.1-pro-preview-customtools) (Vertex AI): Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $0.4875 per 1M cache write tokens, $15.60 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $0.975 per 1M cache write tokens, $23.40 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 Pro Custom Tools in Muse Code?

Trace a failure from code search to a tested fix with Gemini 3.1 Pro Custom Tools. Its emphasis on custom tools suits work that combines repository inspection with Bash commands.

### Trace a bug across a repository

Use code search and inspection tools to follow a failing request through the relevant modules. Ask for a minimal patch and a test that reproduces the failure.

### Plan and verify a refactor

Find callers, inspect assumptions, and change one interface at a time. Request a report of affected behavior and the checks used to verify it.

### Investigate recurring test failures

Combine test output, code inspection, and targeted test runs to examine intermittent failures. Separate reproduced causes from hypotheses that still need evidence.

### Prepare a support investigation

Retrieve account history, order records, and relevant policy through custom tools. Build a timeline and draft a response that distinguishes confirmed facts from missing information.

### Triage operational incidents

Query monitoring data and deployment history, then compare the timing of errors and changes. Produce an evidence-based incident brief with the next checks to run.

### Investigate business data discrepancies

Retrieve related records from business systems and use calculation tools to compare totals. Return discrepancies with record references and leave unresolved matches explicit.

### Turn retrieved evidence into a structured report

Search a knowledge base for material relevant to a question, compare conflicting statements, and return a concise report or schema-constrained JSON for downstream validation.

## Overview

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

## Gemini 3.1 Pro Custom Tools in other agents

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

## More Muse Code guides

- [Gemini 3.1 Flash-Lite](https://spiral.ai/integrations/muse-code/gemini-3-1-flash-lite)
- [Gemini 3.1 Pro Preview](https://spiral.ai/integrations/muse-code/gemini-3-1-pro-preview)
- [Gemini 3 Flash Preview](https://spiral.ai/integrations/muse-code/gemini-3-flash-preview)
- [Gemini 3.5 Flash](https://spiral.ai/integrations/muse-code/gemini-3-5-flash)
- [GPT-oss-120B](https://spiral.ai/integrations/muse-code/gpt-oss-120b)
- [Gemini 3.5 Flash-Lite](https://spiral.ai/integrations/muse-code/gemini-3-5-flash-lite)

## Questions about Gemini 3.1 Pro Custom Tools in Muse Code

**Can Muse Code use Gemini 3.1 Pro Custom Tools?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Gemini 3.1 Pro Custom Tools like any built-in tool.

**How much does Gemini 3.1 Pro Custom Tools cost in Muse Code?**

Up to $0.063989 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $0.4875 per 1M cache write tokens, $15.60 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $0.975 per 1M cache write tokens, $23.40 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

**Do I need a Vertex AI account to use Gemini 3.1 Pro Custom Tools in Muse Code?**

No. Spiral runs Gemini 3.1 Pro Custom Tools 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 Pro Custom Tools in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while Gemini 3.1 Pro Custom Tools runs?**

Gemini 3.1 Pro Custom Tools runs in the background. Muse Code starts the run, checks on it and gives you the text, json when it's ready.

**How does Gemini 3.1 Pro Custom Tools differ from Gemini 3.1 Pro Preview?**

It prioritizes custom tools more strongly in workflows that also use Bash. Choose it for tasks that benefit from searching, inspecting evidence, and acting on tool results.

**Is Gemini 3.1 Pro Custom Tools better for every task?**

Google warns of quality fluctuations on tasks that do not benefit from tools. Test it on your actual work before choosing it for standalone writing or simple questions.

**How much context and output can Gemini 3.1 Pro Custom Tools handle?**

Google lists a maximum of 1,048,576 input tokens and 65,536 output tokens for Gemini 3.1 Pro. These are token limits, so request a specific answer length rather than treating them as page counts.

**Can Gemini 3.1 Pro Custom Tools return reliable JSON?**

Structured output can constrain the response to a supplied JSON Schema. Validate the returned values against the evidence because valid JSON can still contain incorrect information.

**Which setting should I test first for difficult investigations?**

Start with the default high reasoning level for a difficult investigation. Compare lower reasoning levels on routine tasks and keep the lowest level that passes your quality checks.

