[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [GPT-5.5](https://spiral.ai/integrations/antigravity/gpt-5-5)

# How to Use GPT-5.5 in Google Antigravity

Choose GPT-5.5 for coding, data analysis, and research that needs planning and verification. Unlike GPT-5.5 Pro, it can also run without reasoning for straightforward tasks.

|  |  |
| --- | --- |
| Model | GPT-5.5 |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.159972 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $39.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5.5 in Google Antigravity

- Use GPT-5.5 to investigate the intermittent test failure in this repository. Success means reproducing the failure, fixing its cause, and adding a regression check; report the evidence and test results.
- Use GPT-5.5 to implement pagination in this project's existing list endpoint. Follow the current conventions, preserve existing callers, and verify empty results, page boundaries, and invalid requests.
- Use GPT-5.5 to review our analysis script for inconsistent filters and double-counted records. Make the calculation reproducible and show which checks establish that its totals are correct.
- Ask GPT-5.5 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-5.5 on this function, then tell me what the call cost.

## How to set up GPT-5.5 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-5.5**: 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-5.5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds GPT-5.5 on Spiral, shows the price and runs it.

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

## GPT-5.5 tools and prices

- [GPT-5.5](https://spiral.ai/tools/openai/openai/gpt-5.5) (OpenAI): Up to $0.159972 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $39.00 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| top_p | … to 1 | — | Taken only with reasoning effort "none". |
| logprobs |  | — | Taken only with reasoning effort "none". |
| 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-5.5 in Google Antigravity?

Turn bug reports into tested changes and map the effects of a refactor with GPT-5.5. Give the agent a clear acceptance test and ask it to verify the result against the project's code.

### Debug an intermittent failure

Use GPT-5.5 to trace a failure across code and logs, test competing explanations, and propose a fix with a regression check.

### Review a refactor

Ask GPT-5.5 to map affected behavior, identify compatibility risks, and define checks before changing a shared component.

### Investigate a data discrepancy

Give GPT-5.5 conflicting totals and calculation rules. Ask it to identify missing records, inconsistent definitions, and assumptions that change the result.

### Build a research brief

Use GPT-5.5 to compare sources, reconcile disagreements, and produce a brief that connects each conclusion to supporting evidence.

### Challenge a technical argument

Ask GPT-5.5 to review a manuscript or design proposal for unsupported assumptions, counterexamples, and analyses needed to test its claims.

### Turn business notes into a plan

Give GPT-5.5 requirements, constraints, and operational notes. Request a plan with dependencies, decision points, and measurable completion criteria.

### Prepare recurring exception reports

Use GPT-5.5 to compare reporting periods, investigate meaningful changes, and explain which findings need attention and why.

## Overview

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

## GPT-5.5 in other agents

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

## More Google Antigravity guides

- [GPT-5.4 mini](https://spiral.ai/integrations/antigravity/gpt-5-4-mini)
- [GPT-5.5 Pro](https://spiral.ai/integrations/antigravity/gpt-5-5-pro)
- [GPT-5.4 Pro](https://spiral.ai/integrations/antigravity/gpt-5-4-pro)
- [GPT-5.6 Luna](https://spiral.ai/integrations/antigravity/gpt-5-6-luna)
- [GPT-5.4 Nano](https://spiral.ai/integrations/antigravity/gpt-5-4-nano)
- [GPT-5.6 Luna Pro](https://spiral.ai/integrations/antigravity/gpt-5-6-luna-pro)

## Questions about GPT-5.5 in Google Antigravity

**Can Google Antigravity use GPT-5.5?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run GPT-5.5 like any built-in tool.

**How much does GPT-5.5 cost in Google Antigravity?**

Up to $0.159972 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $39.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need an OpenAI account to use GPT-5.5 in Google Antigravity?**

No. Spiral runs GPT-5.5 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-5.5 in Google Antigravity?**

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

**Does Google Antigravity wait while GPT-5.5 runs?**

GPT-5.5 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-5.5 good at?**

GPT-5.5 is suited to coding, research, data analysis, and document work. Useful tasks include debugging a failure, comparing evidence, and turning messy business information into a decision brief.

**How much context and output can GPT-5.5 handle?**

OpenAI lists a 1,050,000-token context window and a maximum output of 128,000 tokens for both GPT-5.5 and GPT-5.5 Pro. Treat the output maximum as a ceiling, then request the length your task needs.

**Does GPT-5.5 know recent events?**

GPT-5.5 and GPT-5.5 Pro have a December 1, 2025 knowledge cutoff. For newer events or changing details, provide current source material and ask for citations.

**How should I prompt GPT-5.5?**

Describe the result you need, what counts as success, the constraints, and the evidence available. Specify what the final answer should contain without prescribing every intermediate step.

**Does more reasoning always improve the answer?**

No. Higher effort can cause overthinking, unnecessary searching, or worse results when the task has conflicting instructions or no clear stopping point.

