[Integrations](https://spiral.ai/integrations) › [Devin](https://spiral.ai/integrations/devin) › [Gemini Pro Latest](https://spiral.ai/integrations/devin/gemini-pro-latest)

# How to Use Gemini Pro Latest in Devin

Use Gemini Pro Latest for code analysis, math, and questions that require reasoning across supplied text. Its Latest name follows new Pro releases, so behavior can change without a model-name change.

|  |  |
| --- | --- |
| Model | Gemini Pro Latest |
| Available through | Vertex AI |
| Category | LLM |
| Price | Up to $0.106678 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $0.24375 per 1M cache write tokens, $26.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Gemini Pro Latest in Devin

- Use Gemini Pro Latest to trace the failing test in this project through the relevant implementation. Propose the smallest fix, identify the affected files, and explain which regression check would catch the original defect.
- Use Gemini Pro Latest to review the current diff for changes to error handling. Return findings with file and line references, a concrete failure scenario, and a suggested check; leave out style comments.
- Use Gemini Pro Latest to compare this project's migration proposal with its current public interfaces. Identify compatibility risks and missing acceptance criteria, citing the relevant code or documentation for each.
- Use Gemini Pro Latest to inspect the calculation code and its tests. Check units, boundary conditions, and rounding assumptions, then propose one concrete test for each suspected gap.
- Use Gemini Pro Latest to extract the documented behavior of this project's configuration loader into JSON. Include each setting's name, stated default, and source location; use null when the documentation does not specify a default.

## How to set up Gemini Pro Latest in Devin

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

### Use Spiral's MCP server

1. **Add a custom MCP**: Open Customize › MCPs. Click + and choose New MCP. Fill in:

2. **Sign in to Spiral and approve**: In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.

3. **Check it**: On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.

### Use the Spiral skill

1. **Send Devin 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 Pro Latest**: 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-pro-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Devin finds Gemini Pro Latest on Spiral, shows the price and runs it.

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

## Gemini Pro Latest tools and prices

- [Gemini Pro Latest](https://spiral.ai/tools/vertex/~google/gemini-pro-latest) (Vertex AI): Up to $0.106678 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $0.24375 per 1M cache write tokens, $26.00 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. 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). |
| tool_choice |  | — |  |

## What can you do with Gemini Pro Latest in Devin?

Turn project code and error reports into proposed fixes, migration plans, and review findings with Gemini Pro Latest. Ask for file references and checks that make each proposal testable.

### Trace a software defect

Ask Gemini Pro Latest to examine relevant code and error output, identify a likely cause, and propose a small fix with a regression check.

### Review a migration plan

Give Gemini Pro Latest the current behavior and proposed changes. Request compatibility risks, unresolved assumptions, and acceptance criteria.

### Compare written requirements

Have Gemini Pro Latest compare supplied requirements for contradictions. Request one supporting passage for each finding and review separate requirement areas in separate passes.

### Extract action items

Turn meeting transcript text into proposed actions with Gemini Pro Latest. Require evidence for owners and deadlines, and leave missing details empty.

### Check a quantitative argument

Ask Gemini Pro Latest to examine a calculation using supplied figures, show the arithmetic, and distinguish stated assumptions from missing information.

### Draft answers from reference text

Use Gemini Pro Latest to draft responses from supplied reference passages. Request supporting excerpts and an explicit indication when the source does not answer the question.

## Overview

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

## Gemini Pro Latest in other agents

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

## More Devin guides

- [Gemini Flash Latest](https://spiral.ai/integrations/devin/gemini-flash-latest)
- [Gemma 2 27B Instruct](https://spiral.ai/integrations/devin/gemma-2-27b-instruct)
- [Gemini 4 Neon](https://spiral.ai/integrations/devin/gemini-4-neon)
- [Gemma 3 12B](https://spiral.ai/integrations/devin/gemma-3-12b)
- [Gemini 4 Hydrogen Vertex AI](https://spiral.ai/integrations/devin/gemini-4-hydrogen-vertex-ai)
- [Gemma 3 27B IT](https://spiral.ai/integrations/devin/gemma-3-27b-it)

## Questions about Gemini Pro Latest in Devin

**Can Devin use Gemini Pro Latest?**

Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Gemini Pro Latest like any built-in tool.

**How much does Gemini Pro Latest cost in Devin?**

Up to $0.106678 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $0.24375 per 1M cache write tokens, $26.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Devin plan is separate.

**Do I need a Vertex AI account to use Gemini Pro Latest in Devin?**

No. Spiral runs Gemini Pro Latest 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 Pro Latest in Devin?**

About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.

**Does Devin wait while Gemini Pro Latest runs?**

Gemini Pro Latest runs in the background. Devin starts the run, checks on it and gives you the text, json when it's ready.

**What does Latest mean in Gemini Pro Latest?**

Latest is a moving name: Google can update the release behind it. Treat an update as a reason to rerun representative tasks before relying on the same behavior.

**What is Gemini Pro good at?**

Coding, advanced math, and data analysis are documented uses for Gemini's reasoning capabilities. Give it the code, assumptions, or source data needed to check the answer.

**Can Gemini Pro reliably find every detail in a long text?**

Do not assume exhaustive recall. Google reports lower accuracy when retrieval requires multiple separate details, so split a completeness-sensitive review into focused questions and check the supporting passages.

**How should I prompt Gemini Pro with a long passage?**

Put the relevant text first and the specific question at the end. For example, ask which requirements conflict and request a supporting passage for each finding.

**Can I trust the values in Gemini Pro's JSON?**

JSON can be correctly formatted and still contain incorrect values. Check extracted numbers, dates, and labels against the source before using them.

