[Integrations](https://spiral.ai/integrations) › [Cursor](https://spiral.ai/integrations/cursor) › [GPT-5.6 Luna](https://spiral.ai/integrations/cursor/gpt-5-6-luna)

# 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.

|  |  |
| --- | --- |
| Model | GPT-5.6 Luna |
| Available through | OpenAI |
| Category | LLM |
| Price | 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. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-5.6 Luna in Cursor

- 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

1. **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):

```json
{
  "mcpServers": {
    "spiral": { "url": "https://api.spiral.ai/mcp" }
  }
}
```

2. **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

1. **Send Cursor this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GPT-5.6 Luna**: One request; the result comes back by polling or a webhook.

```bash
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.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/cursor

## GPT-5.6 Luna tools and prices

- [GPT-5.6 Luna](https://spiral.ai/tools/openai/openai/gpt-5.6-luna) (OpenAI): 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

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| top_p | … to 1 | — | Taken only with reasoning effort "none". |
| logprobs |  | — | Taken only with reasoning effort "none". |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 16 to 128000 | — | The most output tokens to generate. |

## 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.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All Cursor guides](https://spiral.ai/integrations/cursor)

## GPT-5.6 Luna in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-5-6-luna)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-5-6-luna)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-5-6-luna)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-5-6-luna)
- [Cline](https://spiral.ai/integrations/cline/gpt-5-6-luna)
- [Codex](https://spiral.ai/integrations/codex/gpt-5-6-luna)
- [Devin](https://spiral.ai/integrations/devin/gpt-5-6-luna)
- [dots](https://spiral.ai/integrations/dots/gpt-5-6-luna)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-5-6-luna)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-5-6-luna)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-5-6-luna)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-5-6-luna)
- [goose](https://spiral.ai/integrations/goose/gpt-5-6-luna)
- [Grok](https://spiral.ai/integrations/grok/gpt-5-6-luna)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-5-6-luna)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-5-6-luna)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-5-6-luna)
- [Manus](https://spiral.ai/integrations/manus/gpt-5-6-luna)
- [Muse](https://spiral.ai/integrations/muse/gpt-5-6-luna)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-5-6-luna)
- [n8n](https://spiral.ai/integrations/n8n/gpt-5-6-luna)
- [Notion](https://spiral.ai/integrations/notion/gpt-5-6-luna)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-5-6-luna)
- [opencode](https://spiral.ai/integrations/opencode/gpt-5-6-luna)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-5-6-luna)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-5-6-luna)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-5-6-luna)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-5-6-luna)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-5-6-luna)

## More Cursor guides

- [GPT-5.5 Pro](https://spiral.ai/integrations/cursor/gpt-5-5-pro)
- [GPT-5.6 Luna Pro](https://spiral.ai/integrations/cursor/gpt-5-6-luna-pro)
- [GPT-5.5](https://spiral.ai/integrations/cursor/gpt-5-5)
- [GPT-5.6 Sol](https://spiral.ai/integrations/cursor/gpt-5-6-sol)
- [GPT-5.4 mini](https://spiral.ai/integrations/cursor/gpt-5-4-mini)
- [GPT-5.6 Sol Pro](https://spiral.ai/integrations/cursor/gpt-5-6-sol-pro)

## 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.

