How to Use GPT-5.3-Codex in Instinct
GPT-5.3-Codex writes, reviews, and debugs code. Its scope also covers product requirements, tests, and monitoring, making it useful for work that continues beyond the code change.
Prompts to try with GPT-5.3-Codex in Instinct
Copy an example into Instinct, or ask in your own words.
Each morning, use GPT-5.3-Codex to triage new bug reports received since the previous run. Group apparent duplicates, summarize reproduction steps, and list missing details needed for investigation.
After each test run, use GPT-5.3-Codex to analyze the supplied failure summaries and recent change descriptions. Group failures by likely cause and recommend the next diagnostic check for each group.
Every hour, use GPT-5.3-Codex to review newly supplied monitoring alerts and log excerpts. Summarize observed failures, distinguish evidence from hypotheses, and suggest checks without changing the running service.
Every Friday, use GPT-5.3-Codex to compare new feature requests with the approved requirements supplied to this run. Identify conflicting behavior and draft acceptance criteria for requests that are sufficiently specified.
After each release, use GPT-5.3-Codex to compare the supplied change descriptions with the proposed release notes. Flag unsupported claims and rewrite the notes around confirmed behavior.
How to set up GPT-5.3-Codex 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-5.3-Codex
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-5.3-codex", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds GPT-5.3-Codex on Spiral, shows the price and runs it.
GPT-5.3-Codex providers and prices
Spiral runs GPT-5.3-Codex through OpenAI. Open a card for today's price, with every fee included.
Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 per 1M output tokens.
Settings you can ask for
Ask Instinct 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 | low, medium, high, or xhigh | How much the model reasons. | |
| Parallel tool calls | on or off |
Every API field of GPT-5.3-Codex is on its tool page: open its card above.
What can you do with GPT-5.3-Codex in Instinct?
Turn recurring bug reports, test results, and monitoring alerts into focused technical triage with GPT-5.3-Codex. Have each run separate evidence from hypotheses and identify the next useful check.
Reproduce and repair a bug
Give GPT-5.3-Codex the failure, expected behavior, and relevant code. Request a focused fix and a regression test.
Review a proposed change
Ask GPT-5.3-Codex to inspect a diff for behavior changes and explain each finding with a concrete failure scenario.
Design regression tests
Have GPT-5.3-Codex turn a bug report or requirement into tests with explicit inputs and expected results.
Implement a web feature
Ask GPT-5.3-Codex to write a feature with defined loading, empty, success, and error behavior.
Draft product requirements
Use GPT-5.3-Codex to turn a feature brief into requirements, acceptance criteria, and unresolved product decisions.
Triage monitoring alerts
Have GPT-5.3-Codex compare alert details, logs, and recent changes, then propose checks that distinguish possible causes.
Edit product copy
Ask GPT-5.3-Codex to revise interface messages against the specified behavior and flag claims the requirements do not support.
More on GPT-5.3-Codex and Instinct
Overview
GPT-5.3-Codex in other agents
More Instinct guides
Questions about GPT-5.3-Codex in Instinct
Can Instinct use GPT-5.3-Codex?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GPT-5.3-Codex like any built-in tool.
How much does GPT-5.3-Codex cost in Instinct?
Up to $0.074628 per run at the default inputs. $2.275 per 1M input tokens, $0.2275 per 1M cached input tokens, $18.20 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-5.3-Codex in Instinct?
You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT-5.3-Codex on its own OpenAI account.
How long does it take to set up GPT-5.3-Codex in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while GPT-5.3-Codex runs?
GPT-5.3-Codex runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-5.3-Codex useful for?
Use it to write, review, or debug code and to handle related work such as test design, product requirements, and monitoring analysis. Give it a concrete task and a clear definition of done.
How much text can GPT-5.3-Codex handle?
OpenAI lists a 400,000-token context window, a maximum of 272,000 input tokens, and up to 128,000 output tokens. Treat these as ceilings when deciding how much material to include.
Which reasoning effort should I use?
Start with medium for interactive coding. Try high or extra high for difficult debugging or other tasks where the first attempt needs deeper reasoning.
What should I include in a coding prompt?
Describe the expected behavior, provide the relevant code or reproduction steps, and state the constraints. Explain how to verify success, such as a failing test that should pass after the fix.
Is GPT-5.3-Codex intended for casual conversation?
OpenAI says it is not intended for conversational use. In a chat app, give it focused technical tasks such as reviewing pasted code, explaining a failure, or drafting test cases.
Start using GPT-5.3-Codex 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


