[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [GPT-6 Luna Pro](https://spiral.ai/integrations/instinct/gpt-6-luna-pro)

# How to Use GPT-6 Luna Pro in Instinct

GPT-6 Luna Pro suits difficult questions that benefit from extra model work. It uses the same underlying model as Luna, served with pro reasoning for higher-quality responses on complex tasks.

|  |  |
| --- | --- |
| Model | GPT-6 Luna Pro |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with GPT-6 Luna Pro in Instinct

- Every Friday, use GPT-6 Luna Pro to examine the week's incident summaries for recurring explanations and contradictions. Distinguish documented causes from hypotheses.
- Every Monday at 9am: ask GPT-6 Luna Pro through Spiral to review the diff on this branch and list the three riskiest changes.
- Get a second opinion from GPT-6 Luna Pro on this function, then tell me what the call cost.
- Summarize these release notes with GPT-6 Luna Pro in five bullet points.
- Ask GPT-6 Luna Pro to review this plan and list the three biggest risks, with a fix for each.

## How to set up GPT-6 Luna Pro in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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 Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

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

3. **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

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 Pro**: 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": "openrouter",
    "model": "openai/gpt-6-luna-pro",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## GPT-6 Luna Pro tools and prices

- [OpenAI: GPT-6 Luna Pro](https://spiral.ai/tools/openrouter/openai/gpt-6-luna-pro) (OpenRouter): Up to $0.002668 per run at the default inputs. $0.13 per 1M input tokens, $0.65 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 to 128000 | — | The most output tokens to generate. |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with GPT-6 Luna Pro in Instinct?

Convert recurring updates into consistent summaries and extractions on a schedule. Give each run a bounded question and require evidence from the material collected for that run.

### 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

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## GPT-6 Luna Pro in other agents

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

## More Instinct guides

- [GPT-6 Luna](https://spiral.ai/integrations/instinct/gpt-6-luna)
- [GPT-6 Sol](https://spiral.ai/integrations/instinct/gpt-6-sol)
- [GPT-6 Astra Pro](https://spiral.ai/integrations/instinct/gpt-6-astra-pro)
- [GPT-6 Sol Pro](https://spiral.ai/integrations/instinct/gpt-6-sol-pro)
- [GPT-6 Astra](https://spiral.ai/integrations/instinct/gpt-6-astra)
- [GPT-6.1 Sol](https://spiral.ai/integrations/instinct/gpt-6-1-sol)

## Questions about GPT-6 Luna Pro in Instinct

**Can Instinct use GPT-6 Luna Pro?**

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

**How much does GPT-6 Luna Pro cost in Instinct?**

Up to $0.002668 per run at the default inputs. $0.13 per 1M input 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 Instinct plan is separate.

**Do I need an OpenRouter account to use GPT-6 Luna Pro in Instinct?**

You need no OpenRouter account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT-6 Luna Pro on its own OpenRouter account.

**How long does it take to set up GPT-6 Luna Pro in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while GPT-6 Luna Pro runs?**

GPT-6 Luna Pro runs in the background. Instinct 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.

