How to Use GPT-5.5 in Instinct
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 Instinct
Copy an example into Instinct, or ask in your own words.
Every Monday, use GPT-5.5 to compare the latest weekly operating metrics with the previous four weeks. Report the three changes most worth investigating, show the calculations, and flag missing data.
Each evening, use GPT-5.5 to analyze the day's incoming error summaries. Group related failures, identify recurring patterns, and prepare a concise investigation queue with evidence for each priority.
At the end of each month, use GPT-5.5 to reconcile the supplied operational totals against their underlying records. Report discrepancies, affected calculations, and the evidence needed to resolve them.
Every Monday at 9am: ask GPT-5.5 through Spiral to review the diff on this branch and list the three riskiest changes.
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 Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct 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 Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
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: Instinct 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 Instinct 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 Instinct?
Turn recurring business data and research updates into exception reports with GPT-5.5. Define which changes deserve attention and what evidence each report must include.
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 Instinct
Overview
GPT-5.5 in other agents
More Instinct guides
Questions about GPT-5.5 in Instinct
Can Instinct use GPT-5.5?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GPT-5.5 like any built-in tool.
How much does GPT-5.5 cost in Instinct?
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 Instinct plan is separate.
Do I need an OpenAI account to use GPT-5.5 in Instinct?
You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT-5.5 on its own OpenAI account.
How long does it take to set up GPT-5.5 in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while GPT-5.5 runs?
GPT-5.5 runs in the background. Instinct 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 Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


