How to Use GPT-5.5 Pro in Google Antigravity
Choose GPT-5.5 Pro for difficult research and detailed technical reviews. It uses more compute than GPT-5.5 to work through harder questions.
Prompts to try with GPT-5.5 Pro in Google Antigravity
Copy an example into Google Antigravity, or ask in your own words.
Use GPT-5.5 Pro with high reasoning effort to review our event-processing code for duplicate delivery bugs. Identify a concrete failing sequence, explain its impact, and propose the smallest correction.
Use GPT-5.5 Pro to assess the proposed database migration against the schema and callers in this repository. Produce a migration plan covering compatibility, backfill validation, failure recovery, and unresolved decisions.
Ask GPT-5.5 Pro 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 Pro on this function, then tell me what the call cost.
Summarize these release notes with GPT-5.5 Pro in five bullet points.
How to set up GPT-5.5 Pro in Google Antigravity
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- 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.
- Add the server
Add Spiral under mcpServers:
{ "mcpServers": { "spiral": { "serverUrl": "https://api.spiral.ai/mcp" } } } - 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
- Send Google Antigravity this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run GPT-5.5 Pro
One request; the result comes back by polling or a webhook.
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-pro", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Google Antigravity finds GPT-5.5 Pro on Spiral, shows the price and runs it.
GPT-5.5 Pro providers and prices
Spiral runs GPT-5.5 Pro through OpenAI. Open a card for today's price, with every fee included.
Up to $0.959829 per run at the default inputs. $39.00 per 1M input tokens, $234.00 per 1M output tokens.
Settings you can ask for
Ask Google Antigravity for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Reasoning effort | medium, high, or xhigh | high | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of GPT-5.5 Pro is on its tool page: open its card above.
What can you do with GPT-5.5 Pro 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.
More on GPT-5.5 Pro and Google Antigravity
GPT-5.5 Pro in other agents
More Google Antigravity guides
Questions about GPT-5.5 Pro in Google Antigravity
Can Google Antigravity use GPT-5.5 Pro?
Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run GPT-5.5 Pro like any built-in tool.
How much does GPT-5.5 Pro cost in Google Antigravity?
Up to $0.959829 per run at the default inputs. $39.00 per 1M input tokens, $234.00 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 Pro in Google Antigravity?
No. Spiral runs GPT-5.5 Pro 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 Pro 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 Pro runs?
GPT-5.5 Pro 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.
Start using GPT-5.5 Pro in Google Antigravity
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Google Antigravity:
set up https://spiral.ai/SKILL.md


