[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [GPT-5.2](https://spiral.ai/integrations/antigravity/gpt-5-2)

# How to Use GPT-5.2 in Google Antigravity

GPT-5.2 suits code changes, document analysis, and spreadsheet work with adjustable reasoning. Unlike GPT-5.2 Pro, it can turn reasoning off for simpler requests.

|  |  |
| --- | --- |
| Model | GPT-5.2 |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5.2 in Google Antigravity

- Use GPT-5.2 with high reasoning effort to trace the failing tests through this project's source. Make the smallest justified fix, run the relevant tests, and explain the cause in no more than 150 words.
- Use GPT-5.2 with medium reasoning effort to compare the implementation against the requirements in this repository. Return a table of requirement, supporting code, and missing behavior. Make no changes.
- Use GPT-5.2 with medium reasoning effort to draft documentation for this project's public functions from the source and tests. Mark uncertain behavior explicitly and avoid documenting features the code does not implement.
- Ask GPT-5.2 through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
- Get a second opinion from GPT-5.2 on this function, then tell me what the call cost.

## How to set up GPT-5.2 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 GPT-5.2**: 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": "openai",
    "model": "openai/gpt-5.2",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds GPT-5.2 on Spiral, shows the price and runs it.

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

## GPT-5.2 tools and prices

- [GPT-5.2](https://spiral.ai/tools/openai/openai/gpt-5.2) (OpenAI): Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| top_p | … to 1 | — | Taken only at reasoning effort "none", this model's default. |
| logprobs |  | — | Taken only at reasoning effort "none", this model's default. |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 16 to 128000 | — | The most output tokens to generate. |

## What can you do with GPT-5.2 in Google Antigravity?

Turn project requirements and source code into focused patches, reviews, and implementation plans with GPT-5.2. Specify the acceptance criteria and permitted scope so the work stays tied to the requested behavior.

### Fix a bug across several files

Trace a reported failure through the relevant code, propose a focused patch, and identify checks that demonstrate the fix.

### Review a difficult code change

Inspect a proposed change for logic errors, missed edge cases, and conflicts with the stated requirements. Request findings tied to specific code.

### Compare long proposals

Turn supplied proposals into a requirements comparison. Separate supported commitments, contradictions, and unanswered questions.

### Extract document obligations

Pull deadlines, responsible parties, and required actions from supplied text into a table. Leave absent information blank and include supporting passages.

### Review spreadsheet logic

Analyze supplied formulas and assumptions for inconsistent references, missing conditions, and mismatches with the intended calculation.

### Draft a presentation from evidence

Convert research notes or business results into a slide outline with a clear argument. Attach supporting evidence and speaker notes to each slide.

### Synthesize research findings

Compare supplied research excerpts, explain where findings agree, and identify differences in assumptions or methods before drafting a conclusion.

### Prepare a recurring operations brief

Combine supplied status updates, customer issues, and performance figures into a concise brief with evidence, unresolved questions, and proposed next actions.

## Overview

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

## GPT-5.2 in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-5-2)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-5-2)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-5-2)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-5-2)
- [Cline](https://spiral.ai/integrations/cline/gpt-5-2)
- [Codex](https://spiral.ai/integrations/codex/gpt-5-2)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-5-2)
- [Devin](https://spiral.ai/integrations/devin/gpt-5-2)
- [dots](https://spiral.ai/integrations/dots/gpt-5-2)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-5-2)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-5-2)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-5-2)
- [goose](https://spiral.ai/integrations/goose/gpt-5-2)
- [Grok](https://spiral.ai/integrations/grok/gpt-5-2)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-5-2)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-5-2)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-5-2)
- [Manus](https://spiral.ai/integrations/manus/gpt-5-2)
- [Muse](https://spiral.ai/integrations/muse/gpt-5-2)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-5-2)
- [n8n](https://spiral.ai/integrations/n8n/gpt-5-2)
- [Notion](https://spiral.ai/integrations/notion/gpt-5-2)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-5-2)
- [opencode](https://spiral.ai/integrations/opencode/gpt-5-2)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-5-2)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-5-2)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-5-2)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-5-2)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-5-2)

## More Google Antigravity guides

- [GPT-5.1](https://spiral.ai/integrations/antigravity/gpt-5-1)
- [GPT-5.2 Pro](https://spiral.ai/integrations/antigravity/gpt-5-2-pro)
- [GPT-5 Pro](https://spiral.ai/integrations/antigravity/gpt-5-pro)
- [GPT-5.3-Codex](https://spiral.ai/integrations/antigravity/gpt-5-3-codex)
- [GPT-5 Nano](https://spiral.ai/integrations/antigravity/gpt-5-nano)
- [GPT-5.4](https://spiral.ai/integrations/antigravity/gpt-5-4)

## Questions about GPT-5.2 in Google Antigravity

**Can Google Antigravity use GPT-5.2?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run GPT-5.2 like any built-in tool.

**How much does GPT-5.2 cost in Google Antigravity?**

Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 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 OpenAI account to use GPT-5.2 in Google Antigravity?**

No. Spiral runs GPT-5.2 on its own OpenAI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GPT-5.2 in Google Antigravity?**

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

**Does Google Antigravity wait while GPT-5.2 runs?**

GPT-5.2 runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-5.2 useful for?**

Use GPT-5.2 for code changes, comparisons across long documents, spreadsheet analysis, and presentation drafts. Give it a concrete deliverable, such as a patch, a comparison table, or a slide outline.

**How does GPT-5.2 Pro differ from GPT-5.2?**

GPT-5.2 Pro targets difficult questions where greater precision matters, including complex programming work. GPT-5.2 offers more flexibility for simpler requests because it can disable reasoning.

**How much text can GPT-5.2 handle?**

GPT-5.2 and GPT-5.2 Pro each have a 400,000-token context window and a maximum output of 128,000 tokens. Treat these as ceilings, and request a specific answer length suited to the task.

**How should I prompt GPT-5.2?**

State the task, relevant evidence, scope, and required answer length. For extraction, specify what to return when information is missing; for coding, explicitly limit changes to the requested behavior.

**Does GPT-5.2 know about recent events?**

GPT-5.2 and GPT-5.2 Pro have an August 31, 2025 knowledge cutoff. Supply current evidence when asking about later events, and ask the model to distinguish supplied facts from assumptions.

