[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [Grok 4.7](https://spiral.ai/integrations/antigravity/grok-4-7)

# How to Use Grok 4.7 in Google Antigravity

Grok 4.7 suits difficult coding tasks and document work that require several passes and verification. Compared with Grok 4.6, it has stronger self-checking and more training on tasks that take hours to complete.

|  |  |
| --- | --- |
| Model | Grok 4.7 |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Grok 4.7 in Google Antigravity

- Use Grok 4.7 with high reasoning effort to investigate the failing tests in this project. Trace the cause through the relevant files, make a focused fix, and run the affected tests. Report the cause, changed behavior, and any checks you could not complete.
- Use Grok 4.7 to review this repository's database migration code against its documented rollback requirements. List concrete failure scenarios with file references, then propose tests for the three most consequential gaps.
- Use Grok 4.7 with the highest reasoning effort to plan a replacement for this project's authentication middleware. Read the existing implementation and tests, preserve documented behavior, and produce a staged plan with a verification step for each stage.
- Use Grok 4.7 to compare the API specification with the implementation in this project. Identify mismatches with file references and propose the smallest changes needed to make them agree.
- Use Grok 4.7 to turn this project's architecture notes into a technical decision record. Compare the documented options, cite the relevant files, and distinguish recorded decisions from assumptions.

## How to set up Grok 4.7 in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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 Grok 4.7**: 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": "openrouter",
    "model": "x-ai/grok-4.7",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds Grok 4.7 on Spiral, shows the price and runs it.

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

## Grok 4.7 tools and prices

- [SpaceXAI: Grok 4.7](https://spiral.ai/tools/openrouter/x-ai/grok-4.7) (OpenRouter): Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| top_p | … to 1 | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 450000 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Grok 4.7 in Google Antigravity?

Grok 4.7 can help carry a difficult code change from investigation through verification. Give the agent the relevant project files, the intended behavior, and checks that define a successful result.

### Fix a bug across several files

Use Grok 4.7 to trace a failure through related code, propose a focused patch, and check the result against a regression test.

### Plan and carry out a code migration

Give Grok 4.7 the old behavior, target requirements, and compatibility constraints. Ask for staged changes with checks after each stage.

### Review a technical design

Ask Grok 4.7 to compare a proposed design against explicit requirements, identify unresolved decisions, and explain which evidence supports each concern.

### Turn source material into a decision brief

Have Grok 4.7 organize supplied research into options, supporting evidence, tradeoffs, and a recommendation with stated assumptions.

### Draft a presentation from a report

Ask Grok 4.7 for slide titles, evidence, and speaker notes tailored to a named audience. Require every factual point to trace back to the supplied report.

### Reconcile conflicting requirements

Use Grok 4.7 to compare lengthy specifications, locate contradictions, and draft a decision log that separates agreed requirements from open questions.

### Prepare a recurring project review

Give Grok 4.7 dated progress updates and the previous review. Ask for changes, unresolved blockers, and decisions needed, with evidence for each entry.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## Grok 4.7 in other agents

- [Amp](https://spiral.ai/integrations/amp/grok-4-7)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/grok-4-7)
- [Claude](https://spiral.ai/integrations/claude-desktop/grok-4-7)
- [Claude Code](https://spiral.ai/integrations/claude-code/grok-4-7)
- [Cline](https://spiral.ai/integrations/cline/grok-4-7)
- [Codex](https://spiral.ai/integrations/codex/grok-4-7)
- [Cursor](https://spiral.ai/integrations/cursor/grok-4-7)
- [Devin](https://spiral.ai/integrations/devin/grok-4-7)
- [dots](https://spiral.ai/integrations/dots/grok-4-7)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/grok-4-7)
- [Gemini](https://spiral.ai/integrations/gemini/grok-4-7)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/grok-4-7)
- [goose](https://spiral.ai/integrations/goose/grok-4-7)
- [Grok](https://spiral.ai/integrations/grok/grok-4-7)
- [Grok Build](https://spiral.ai/integrations/grok-build/grok-4-7)
- [Hermes](https://spiral.ai/integrations/hermes/grok-4-7)
- [Instinct](https://spiral.ai/integrations/instinct/grok-4-7)
- [Manus](https://spiral.ai/integrations/manus/grok-4-7)
- [Muse](https://spiral.ai/integrations/muse/grok-4-7)
- [Muse Code](https://spiral.ai/integrations/muse-code/grok-4-7)
- [n8n](https://spiral.ai/integrations/n8n/grok-4-7)
- [Notion](https://spiral.ai/integrations/notion/grok-4-7)
- [OpenClaw](https://spiral.ai/integrations/openclaw/grok-4-7)
- [opencode](https://spiral.ai/integrations/opencode/grok-4-7)
- [Perplexity](https://spiral.ai/integrations/perplexity/grok-4-7)
- [Raycast](https://spiral.ai/integrations/raycast/grok-4-7)
- [VS Code](https://spiral.ai/integrations/vscode/grok-4-7)
- [Windsurf](https://spiral.ai/integrations/windsurf/grok-4-7)
- [Zapier](https://spiral.ai/integrations/zapier/grok-4-7)

## More Google Antigravity guides

- [Grok 4.6](https://spiral.ai/integrations/antigravity/grok-4-6)
- [Grok Latest](https://spiral.ai/integrations/antigravity/grok-latest)
- [Grok 4.5](https://spiral.ai/integrations/antigravity/grok-4-5)
- [Hermes 4 405B](https://spiral.ai/integrations/antigravity/hermes-4-405b)
- [Grok 4.3](https://spiral.ai/integrations/antigravity/grok-4-3)
- [Hy-MT2-1.8B](https://spiral.ai/integrations/antigravity/hy-mt2-1-8b)

## Questions about Grok 4.7 in Google Antigravity

**Can Google Antigravity use Grok 4.7?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run Grok 4.7 like any built-in tool.

**How much does Grok 4.7 cost in Google Antigravity?**

Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need an OpenRouter account to use Grok 4.7 in Google Antigravity?**

No. Spiral runs Grok 4.7 on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Grok 4.7 in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while Grok 4.7 runs?**

Grok 4.7 runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is Grok 4.7 best suited for?**

Difficult coding tasks and knowledge work that require multiple steps and verification. The maker also reports improvements in creating documents and presentations.

**How does Grok 4.7 differ from Grok 4.6?**

Grok 4.7 uses a larger base model and received more training on harder tasks that take hours to complete. Its documented improvements include stronger self-checking and more reliable handling of long context.

**How much context can Grok 4.7 handle?**

The maker documents a 500,000-token context window. For a long review, ask for a concise result with references to the supplied material.

**How long can a Grok 4.7 answer be?**

The maker's guide lists no separate text-output limit. Context and request limits still apply, so specify the length you need instead of asking for the longest possible answer.

**Does Grok 4.7 know current events?**

Its documented knowledge cutoff is May 2026, and training alone does not provide real-time information. Supply dated evidence when a task depends on recent changes.

