How to Use GPT-5.5 in Claude Code
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.
Prompts to try with GPT-5.5 in Claude Code
Copy an example into Claude Code, or ask in your own words.
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 Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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
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", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds GPT-5.5 on Spiral, shows the price and runs it.
GPT-5.5 providers and prices
Spiral runs GPT-5.5 through OpenAI. Open a card for today's price, with every fee included.
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
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | a number up to 1 | Taken only with reasoning effort "none". | |
| Logprobs | on or off | Taken only with reasoning effort "none". | |
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | Taken only with reasoning effort "none". | |
| Top logprobs | 0 to 20 | Taken only with reasoning effort "none". | |
| Presence penalty | -2 to 2 | Taken only with reasoning effort "none". | |
| Reasoning effort | none, low, medium, high, or xhigh | medium | How much the model reasons. |
| Frequency penalty | -2 to 2 | Taken only with reasoning effort "none". | |
| Parallel tool calls | on or off |
Every API field of GPT-5.5 is on its tool page: open its card above.
What can you do with GPT-5.5 in Claude Code?
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 and Claude Code
Overview
GPT-5.5 in other agents
More Claude Code guides
Questions about GPT-5.5 in Claude Code
Can Claude Code use GPT-5.5?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run GPT-5.5 like any built-in tool.
How much does GPT-5.5 cost in Claude Code?
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 Claude Code plan is separate.
Do I need an OpenAI account to use GPT-5.5 in Claude Code?
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 Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while GPT-5.5 runs?
GPT-5.5 runs in the background. Claude Code 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 in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


