How to Use GPT-5.4 in Instinct
GPT-5.4 handles coding, research synthesis, and work involving spreadsheets and documents. Choose it for general work; GPT-5.4 Pro spends more compute reasoning through difficult problems.
Prompts to try with GPT-5.4 in Instinct
Copy an example into Instinct, or ask in your own words.
Use GPT-5.4 each morning to summarize the updates supplied for this run. Return completed work, blockers, and next actions in under 300 words. Include the source update for every blocker.
Use GPT-5.4 each Friday to turn the supplied research excerpts into a weekly brief. Include new findings, contradictory evidence, and unanswered questions. Cite the supplied sources and state when there is no meaningful change.
Use GPT-5.4 after each reporting period to draft a six-slide leadership update from the supplied results. Cover progress, evidence, blockers, and decisions needed. Keep speaker notes to two sentences per slide.
Every Monday at 9am: ask GPT-5.4 through Spiral to review the diff on this branch and list the three riskiest changes.
Get a second opinion from GPT-5.4 on this function, then tell me what the call cost.
How to set up GPT-5.4 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-5.4
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-5.4", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds GPT-5.4 on Spiral, shows the price and runs it.
GPT-5.4 providers and prices
Spiral runs GPT-5.4 through OpenAI. Open a card for today's price, with every fee included.
Up to $0.079987 per run at the default inputs. $3.25 per 1M input tokens, $0.325 per 1M cached input tokens, $19.50 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 at reasoning effort "none", this model's default. | |
| Logprobs | on or off | Taken only at reasoning effort "none", this model's default. | |
| Max tokens | 16 to 128000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | Taken only at reasoning effort "none", this model's default. | |
| Top logprobs | 0 to 20 | Taken only at reasoning effort "none", this model's default. | |
| Presence penalty | -2 to 2 | Taken only at reasoning effort "none", this model's default. | |
| Reasoning effort | none, low, medium, high, or xhigh | none | How much the model reasons. |
| Frequency penalty | -2 to 2 | Taken only at reasoning effort "none", this model's default. | |
| Parallel tool calls | on or off |
Every API field of GPT-5.4 is on its tool page: open its card above.
What can you do with GPT-5.4 in Instinct?
Turn each run's supplied updates into a consistent operations brief with GPT-5.4. Define the comparison period, required evidence, and report length so each run answers the same practical questions.
Find the cause of a bug
Trace a failure through code and logs, propose a focused fix, and define a check that reproduces the original problem.
Review a migration plan
Compare the proposed changes with existing behavior. List dependencies, compatibility risks, and checks needed before rollout.
Compare competing proposals
Turn supplied proposals into a decision table using explicit criteria. Separate documented commitments from assumptions and unanswered questions.
Prepare a research brief
Combine supplied sources into a concise explanation with supporting passages, conflicting claims, and gaps that need further research.
Check spreadsheet logic
Review supplied formulas and assumptions for inconsistent units, missing dependencies, and totals that need reconciliation.
Draft a presentation
Turn a business brief into a slide outline with a clear recommendation, supporting evidence, and speaker notes.
Explain a difficult technical decision
Compare engineering approaches against stated constraints. Describe tradeoffs, identify missing measurements, and recommend the next experiment.
Produce a recurring operations brief
Summarize supplied updates into changes, blockers, and next actions. Keep each conclusion tied to the evidence available for that run.
More on GPT-5.4 and Instinct
Overview
GPT-5.4 in other agents
More Instinct guides
Questions about GPT-5.4 in Instinct
Can Instinct use GPT-5.4?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GPT-5.4 like any built-in tool.
How much does GPT-5.4 cost in Instinct?
Up to $0.079987 per run at the default inputs. $3.25 per 1M input tokens, $0.325 per 1M cached input tokens, $19.50 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-5.4 in Instinct?
You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT-5.4 on its own OpenAI account.
How long does it take to set up GPT-5.4 in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while GPT-5.4 runs?
GPT-5.4 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-5.4 good at?
GPT-5.4 combines coding and reasoning with document, spreadsheet, and presentation work. Useful tasks include investigating bugs, comparing evidence, and turning business requirements into a draft deliverable.
How much can GPT-5.4 read and write?
GPT-5.4 and GPT-5.4 Pro each have a 1,050,000-token context window and a 128,000-token maximum output. Internal reasoning also uses the output budget, so that ceiling does not mean 128,000 tokens of visible text.
Does GPT-5.4 know recent events?
GPT-5.4 and GPT-5.4 Pro have an August 31, 2025 knowledge cutoff. Supply current source material when asking about later events or changes.
What does reasoning effort change?
It controls how much internal reasoning the model does before answering. Compare results on your actual task, and leave enough output space for both reasoning and the final answer.
How should I prompt GPT-5.4?
State the deliverable, the required sections, and a length limit. For example, ask for a recommendation, its supporting evidence, and unresolved questions in under 500 words.
Start using GPT-5.4 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


