How to Use GPT-5.6 Luna in Cursor
GPT-5.6 Luna fits document extraction, code retrieval, and routine implementation. Choose it over GPT-5.6 Luna Pro for everyday work that does not need extra model work on difficult problems.
Prompts to try with GPT-5.6 Luna in Cursor
Copy an example into Cursor, or ask in your own words.
Use GPT-5.6 Luna to trace how this project handles an expired session. Identify the relevant functions and tests, cite file paths, and explain the flow in under 300 words.
Use GPT-5.6 Luna to fix the failing test in this project. Keep the change limited to the demonstrated bug, run the relevant tests, and report the result.
Use GPT-5.6 Luna to implement pagination for the existing list endpoint using the project's conventions. Add tests for the first page, an empty result, and an invalid cursor.
Ask GPT-5.6 Luna through Spiral to review the diff on this branch and list the three riskiest changes. Save the result in ./assets.
Get a second opinion from GPT-5.6 Luna on this function, then tell me what the call cost.
How to set up GPT-5.6 Luna 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 Luna
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-luna", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Cursor finds GPT-5.6 Luna on Spiral, shows the price and runs it.
GPT-5.6 Luna providers and prices
Spiral runs GPT-5.6 Luna through OpenAI. Open a card for today's price, with every fee included.
Up to $0.006402 per run at the default inputs. $0.26 per 1M input tokens, $0.026 per 1M cached input tokens, $0.325 per 1M cache write tokens, $1.56 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 Luna is on its tool page: open its card above.
What can you do with GPT-5.6 Luna in Cursor?
Turn a defined requirement into a code change with tests, or locate the code responsible for a reported behavior. GPT-5.6 Luna can handle scoped implementation and code retrieval when you provide acceptance criteria.
Extract renewal terms
Turn supplied contract text into a table of renewal dates, notice periods, and supporting passages. Mark missing terms explicitly.
Find code behind a behavior
Trace a reported behavior to relevant functions and tests. Request file references and a concise explanation of the execution path.
Implement a scoped change
Apply a clearly specified code change, add a regression test, and check the result against acceptance criteria.
Classify support conversations
Sort supplied conversations by issue type and urgency, preserving a supporting passage for each classification.
Compare policy revisions
Compare two supplied policy texts and list changed obligations, exceptions, and unresolved conflicts with section references.
Check a decision against evidence
Evaluate a proposed decision against supplied requirements and evidence. Request unmet conditions, conflicting evidence, and questions that would change the recommendation.
More on GPT-5.6 Luna and Cursor
Overview
GPT-5.6 Luna in other agents
More Cursor guides
Questions about GPT-5.6 Luna in Cursor
Can Cursor use GPT-5.6 Luna?
Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run GPT-5.6 Luna like any built-in tool.
How much does GPT-5.6 Luna cost in Cursor?
Up to $0.006402 per run at the default inputs. $0.26 per 1M input tokens, $0.026 per 1M cached input tokens, $0.325 per 1M cache write tokens, $1.56 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 Luna in Cursor?
No. Spiral runs GPT-5.6 Luna 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 Luna in Cursor?
About two minutes: add the hosted server, then sign in.
Does Cursor wait while GPT-5.6 Luna runs?
GPT-5.6 Luna 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 Luna good at?
Document extraction, code retrieval, customer-interaction classification, and well-specified implementation are supported uses. Give it a defined task and an output you can check.
What does GPT-5.6 Luna Pro change?
It uses the same underlying model as GPT-5.6 Luna with pro reasoning mode. That mode applies extra model work to difficult tasks; reasoning effort remains a separate control.
How much text can GPT-5.6 Luna handle?
OpenAI documents a 1,050,000-token context window, with up to 922,000 input tokens and 128,000 generated tokens. Reasoning consumes part of the generated-token budget, so that maximum does not promise an equally long visible answer.
How should I prompt GPT-5.6 Luna?
State the task directly, supply the relevant material, and define what a successful answer must contain. Specify constraints such as length, required evidence, and how to handle missing information.
Which tasks deserve more reasoning?
Test extra reasoning on difficult tasks that require exploring alternatives, running checks, or revising an approach. Use representative examples to judge whether the extra work improves the result.
Start using GPT-5.6 Luna 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


