How to Use GPT-5.6 Terra in Instinct
GPT-5.6 Terra fits everyday coding, document analysis, and scoped agent tasks. Choose it for routine work; Terra Pro applies additional model work to difficult problems.
Prompts to try with GPT-5.6 Terra in Instinct
Copy an example into Instinct, or ask in your own words.
Each morning, use GPT-5.6 Terra to summarize the support conversations supplied for this run. Group recurring issues and include representative conversation IDs.
Every Friday, use GPT-5.6 Terra to compare this week's status updates with last week's supplied summary. Report changed deadlines, new blockers, and resolved issues.
On each run, use GPT-5.6 Terra with low reasoning to classify new customer comments into the established categories. Flag comments that do not fit.
Each evening, use GPT-5.6 Terra to extract decisions, owners, and due dates from the meeting text supplied for this run. Mark missing owners or dates explicitly.
Every Monday at 9am: ask GPT-5.6 Terra through Spiral to review the diff on this branch and list the three riskiest changes.
How to set up GPT-5.6 Terra 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-5.6 Terra
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-5.6-terra", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Instinct finds GPT-5.6 Terra on Spiral, shows the price and runs it.
GPT-5.6 Terra providers and prices
Spiral runs GPT-5.6 Terra through OpenAI. Open a card for today's price, with every fee included.
Up to $0.064012 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $15.60 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-5.6 Terra is on its tool page: open its card above.
What can you do with GPT-5.6 Terra in Instinct?
Produce recurring summaries and classifications from each run's supplied information. Keep the criteria consistent so changes and exceptions are easy to inspect.
Scoped code changes
Give Terra a concrete bug or implementation request. Ask for the relevant patch and validation results.
Document comparisons
Compare supplied material against explicit criteria. Request supporting passages for each finding and mark missing evidence.
Customer conversation classification
Group conversations into defined categories, summarize recurring issues, and separate ambiguous cases for review.
Difficult analytical reviews
Use Terra Pro to examine a complex proposal, identify conflicting assumptions, and produce a recommendation with supporting evidence.
Repeatable extraction
Turn supplied text into consistent records with explicit rules for missing values and conflicting information.
Implementation planning
Ask Terra to turn a bounded engineering requirement into a plan with acceptance criteria and relevant checks.
More on GPT-5.6 Terra and Instinct
Overview
GPT-5.6 Terra in other agents
Questions about GPT-5.6 Terra in Instinct
Can Instinct use GPT-5.6 Terra?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GPT-5.6 Terra like any built-in tool.
How much does GPT-5.6 Terra cost in Instinct?
Up to $0.064012 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $15.60 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-5.6 Terra in Instinct?
You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT-5.6 Terra on its own OpenAI account.
How long does it take to set up GPT-5.6 Terra in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while GPT-5.6 Terra runs?
GPT-5.6 Terra runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-5.6 Terra good at?
Use it for everyday implementation, document analysis, and classifying customer conversations. Keep requests scoped around a clear deliverable, such as a patch, comparison table, or categorized summary.
How does Terra Pro differ from Terra?
Terra Pro uses the same underlying model with Pro reasoning mode for complex tasks. Choose it for difficult analysis where additional model work may improve the answer.
How much material can Terra handle?
Terra has a 1,050,000-token context window and a maximum output allowance of 128,000 tokens. Internal reasoning also consumes the generation allowance, so visible answers can be shorter than that ceiling.
Can Terra analyze images, audio, or video?
Terra accepts images for analysis. Audio and video are not natively supported.
Which reasoning setting should I start with?
Start with medium reasoning. Try low for straightforward tasks where response time matters, then compare results on examples from your actual workload.
Start using GPT-5.6 Terra 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


