[Integrations](https://spiral.ai/integrations) › [Windsurf](https://spiral.ai/integrations/windsurf) › [GPT-6 Luna](https://spiral.ai/integrations/windsurf/gpt-6-luna)

# How to Use GPT-6 Luna in Windsurf

GPT-6 Luna suits repeatable document summaries, information extraction, and focused coding tasks. Choose it for everyday work; Luna Pro uses the same model with pro reasoning for harder problems.

|  |  |
| --- | --- |
| Model | GPT-6 Luna |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.002669 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.65 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-6 Luna in Windsurf

- Use GPT-6 Luna to summarize this repository's request validation flow. Cite the relevant files and functions, and keep the explanation under 400 words.
- Use GPT-6 Luna to inspect the failing parser test, propose the smallest fix, and add a regression test. Report which tests actually ran.
- Use GPT-6 Luna with high reasoning effort to review the database migration in this branch. Identify data-loss risks and suggest concrete validation queries.
- Use GPT-6 Luna to extract the public function signatures from this package and draft concise reference documentation. Flag behavior the implementation does not establish.
- Ask GPT-6 Luna 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-6 Luna in Windsurf

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Open the Customize page from the Agents window and click MCPs. Under This computer, open the config file, or edit it directly: `~/.config/devin/mcp_config.json` on macOS and Linux, `%APPDATA%\devin\mcp_config.json` on Windows. Add this:

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

2. **Sign in**: Click Authenticate on the Spiral server in Customize › MCPs, or let the agent call Spiral once: your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key.

```bash
devin mcp login spiral
```

3. **Check it**: Spiral is listed under This computer in Customize › MCPs. From the terminal:

```bash
devin mcp list
```

### Use the Spiral skill

1. **Send Windsurf 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-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-6-luna",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Windsurf finds GPT-6 Luna on Spiral, shows the price and runs it.

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

## GPT-6 Luna tools and prices

- [GPT-6 Luna](https://spiral.ai/tools/openai/openai/gpt-6-luna) (OpenAI): Up to $0.002669 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.65 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-6 Luna in Windsurf?

Turn project files into focused explanations, patches, and testable debugging hypotheses. Use Luna for bounded tasks and Luna Pro when the problem needs closer examination.

### Extract facts from repeated documents

Use Luna to pull dates, commitments, and named parties from a set of documents. Request a supporting passage for each extracted item and mark missing information explicitly.

### Turn long material into a focused brief

Ask Luna to summarize decisions, unresolved questions, and next actions. Specify the audience and a word limit so the result answers a concrete need.

### Investigate a difficult software defect

Use Luna Pro to examine competing explanations for a failing test. Request a reproducible case, a proposed fix, and evidence that distinguishes the explanations.

### Review a complicated plan

Ask Luna Pro to inspect a migration or rollout plan for conflicting assumptions, missing dependencies, and failure cases. Require each finding to reference the supplied plan.

### Read information from an image

Give Luna an image containing useful text or visual information. Ask for a bounded extraction and have it flag anything it cannot read confidently.

### Prepare recurring operational summaries

Have a scheduled agent send Luna the latest updates and request a short summary of changes, unresolved issues, and questions requiring human attention.

## Overview

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

## GPT-6 Luna in other agents

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

## More Windsurf guides

- [GPT-6 Astra Pro](https://spiral.ai/integrations/windsurf/gpt-6-astra-pro)
- [GPT-6 Luna Pro](https://spiral.ai/integrations/windsurf/gpt-6-luna-pro)
- [GPT-6 Astra](https://spiral.ai/integrations/windsurf/gpt-6-astra)
- [GPT-6 Sol](https://spiral.ai/integrations/windsurf/gpt-6-sol)
- [GPT-5.6 Terra Pro](https://spiral.ai/integrations/windsurf/gpt-5-6-terra-pro)
- [GPT-6 Sol Pro](https://spiral.ai/integrations/windsurf/gpt-6-sol-pro)

## Questions about GPT-6 Luna in Windsurf

**Can Windsurf use GPT-6 Luna?**

Yes. Add Spiral to Windsurf as an MCP server, and Windsurf can find and run GPT-6 Luna like any built-in tool.

**How much does GPT-6 Luna cost in Windsurf?**

Up to $0.002669 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.65 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Windsurf plan is separate.

**Do I need an OpenAI account to use GPT-6 Luna in Windsurf?**

No. Spiral runs GPT-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-6 Luna in Windsurf?**

About two minutes: add the server, then sign in, then check it.

**Does Windsurf wait while GPT-6 Luna runs?**

GPT-6 Luna runs in the background. Windsurf starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-6 Luna best used for?**

Start with repeatable work: document summaries, extracting information, and answering focused questions. It also produces code and can tackle software engineering tasks.

**How is GPT-6 Luna Pro different from Luna?**

Both use the same underlying model. Luna Pro enables pro reasoning for complex tasks, making it a candidate for difficult debugging or reviewing a complicated plan.

**How much text can GPT-6 Luna handle and generate?**

Luna has a 1,050,000-token context window and a maximum output of 128,000 tokens. Reasoning also consumes the generation budget, so leave room for it when requesting a long answer.

**Can GPT-6 Luna understand images?**

Yes. It accepts images and text and produces text, including code, so you can ask it to extract information from an image or explain what it shows.

**How should I prompt GPT-6 Luna?**

Give it a clear task, the relevant source material, and a specific definition of a successful answer. OpenAI recommends brief, direct instructions for reasoning models; asking for step-by-step internal reasoning is unnecessary.

