How to Use GPT-5.6 Terra in Cursor
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 Cursor
Copy an example into Cursor, or ask in your own words.
Use GPT-5.6 Terra to inspect the failing tests, fix the smallest relevant code path, and run the affected checks. Report the cause and validation results.
Use GPT-5.6 Terra to implement pagination in this project's existing list view. Follow its current conventions and verify empty, first-page, and last-page behavior.
Use GPT-5.6 Terra to compare the README with the current implementation. List outdated claims with file references and proposed corrections.
Use GPT-5.6 Terra with medium reasoning to review the current diff. Report actionable defects with file references, a concrete failure example, and a suggested fix.
Ask GPT-5.6 Terra through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
How to set up GPT-5.6 Terra in Cursor
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to Cursor on the console's Agents & MCP page, or add this to .cursor/mcp.json (one project) or ~/.cursor/mcp.json (every project):
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.
Use the Spiral skill
- Send Cursor 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-5.6 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: Cursor 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 Cursor 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 Cursor?
Turn project requirements into scoped patches, tests, and code reviews. Use Terra for everyday implementation and Terra Pro for difficult analysis.
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 Cursor
Overview
GPT-5.6 Terra in other agents
Questions about GPT-5.6 Terra in Cursor
Can Cursor use GPT-5.6 Terra?
Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run GPT-5.6 Terra like any built-in tool.
How much does GPT-5.6 Terra cost in Cursor?
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 Cursor plan is separate.
Do I need an OpenAI account to use GPT-5.6 Terra in Cursor?
No. Spiral runs GPT-5.6 Terra 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-5.6 Terra in Cursor?
About two minutes: add the hosted server, then sign in.
Does Cursor wait while GPT-5.6 Terra runs?
GPT-5.6 Terra runs in the background. Cursor 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 Cursor
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Cursor:
set up https://spiral.ai/SKILL.md


