[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [GPT-6.2 Sol](https://spiral.ai/integrations/muse-code/gpt-6-2-sol)

# How to Use GPT-6.2 Sol in Muse Code

GPT-6.2 Sol handles everyday coding, writing, and multistep tasks. Choose it for routine work; GPT-6.2 Sol Pro uses the same underlying model with additional reasoning for harder problems.

|  |  |
| --- | --- |
| Model | GPT-6.2 Sol |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-6.2 Sol in Muse Code

- Use GPT-6.2 Sol to review the current branch against main. Report actionable bugs with file locations, triggering conditions, and suggested checks.
- Use GPT-6.2 Sol to apply the review comments recorded in this project. Follow existing conventions, run the affected tests, and report any unresolved comments.
- Use GPT-6.2 Sol to update the README from the current implementation. Verify each example against the code and flag behavior you cannot confirm.
- Ask GPT-6.2 Sol 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-6.2 Sol on this function, then tell me what the call cost.

## How to set up GPT-6.2 Sol in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
muse mcp login spiral
```

### Use the Spiral skill

1. **Send Muse Code 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-6.2 Sol**: 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-6.2-sol",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Muse Code finds GPT-6.2 Sol on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## GPT-6.2 Sol tools and prices

- [GPT-6.2 Sol](https://spiral.ai/tools/openai/openai/gpt-6.2-sol) (OpenAI): Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 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 | 16 to 128000 | — | The most output tokens to generate. On a reasoning model the reasoning tokens count toward it: a cap too low for the effort can end with no answer (finish_reason length). |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with GPT-6.2 Sol in Muse Code?

Turn code review feedback into focused changes with GPT-6.2 Sol. Give the agent the relevant project files, expected behavior, and checks that define completion.

### Review a pull request

Check a proposed change for bugs and missed edge cases. Request findings tied to specific code, with an explanation of how each issue could occur.

### Apply code review feedback

Turn reviewer comments into focused edits and relevant checks. Provide the intended behavior and project conventions so the changes have a clear target.

### Review a database migration

Examine a migration plan for failure modes, recovery gaps, and missing validation. Use the pro reasoning option when the plan needs additional analysis.

### Turn meeting notes into a brief

Organize notes into decisions, next steps, owners, and unresolved questions. Ask for missing owners or dates to be marked explicitly.

### Draft technical documentation

Turn supplied implementation details into a guide for a defined audience. Request examples and explanations grounded in the supplied material.

### Prepare recurring operations summaries

Compare the latest status updates with the previous report. Request changed commitments, unresolved blockers, and questions that need an owner.

### Extract structured action items

Convert supplied notes or messages into structured records for downstream processing. Define the required information and how unknown values should be represented.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## GPT-6.2 Sol in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-6-2-sol)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-6-2-sol)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-6-2-sol)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-6-2-sol)
- [Cline](https://spiral.ai/integrations/cline/gpt-6-2-sol)
- [Codex](https://spiral.ai/integrations/codex/gpt-6-2-sol)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-6-2-sol)
- [Devin](https://spiral.ai/integrations/devin/gpt-6-2-sol)
- [dots](https://spiral.ai/integrations/dots/gpt-6-2-sol)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-6-2-sol)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-6-2-sol)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-6-2-sol)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-6-2-sol)
- [goose](https://spiral.ai/integrations/goose/gpt-6-2-sol)
- [Grok](https://spiral.ai/integrations/grok/gpt-6-2-sol)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-6-2-sol)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-6-2-sol)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-6-2-sol)
- [Manus](https://spiral.ai/integrations/manus/gpt-6-2-sol)
- [Muse](https://spiral.ai/integrations/muse/gpt-6-2-sol)
- [n8n](https://spiral.ai/integrations/n8n/gpt-6-2-sol)
- [Notion](https://spiral.ai/integrations/notion/gpt-6-2-sol)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-6-2-sol)
- [opencode](https://spiral.ai/integrations/opencode/gpt-6-2-sol)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-6-2-sol)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-6-2-sol)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-6-2-sol)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-6-2-sol)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-6-2-sol)

## More Muse Code guides

- [GPT-6.2 Astra Pro](https://spiral.ai/integrations/muse-code/gpt-6-2-astra-pro)
- [GPT-6.2 Sol Pro](https://spiral.ai/integrations/muse-code/gpt-6-2-sol-pro)
- [GPT-6.2 Astra](https://spiral.ai/integrations/muse-code/gpt-6-2-astra)
- [GPT-oss Safeguard 20B](https://spiral.ai/integrations/muse-code/gpt-oss-safeguard-20b)
- [GPT-6.1 Terra Pro](https://spiral.ai/integrations/muse-code/gpt-6-1-terra-pro)
- [GPT-oss-120B](https://spiral.ai/integrations/muse-code/gpt-oss-120b)

## Questions about GPT-6.2 Sol in Muse Code

**Can Muse Code use GPT-6.2 Sol?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run GPT-6.2 Sol like any built-in tool.

**How much does GPT-6.2 Sol cost in Muse Code?**

Up to $0.053363 per run at the default inputs. $2.60 per 1M input tokens, $0.13 per 1M cached input tokens, $3.25 per 1M cache write tokens, $13.00 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

**Do I need an OpenAI account to use GPT-6.2 Sol in Muse Code?**

No. Spiral runs GPT-6.2 Sol 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-6.2 Sol in Muse Code?**

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

**Does Muse Code wait while GPT-6.2 Sol runs?**

GPT-6.2 Sol runs in the background. Muse Code starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-6.2 Sol good at?**

Everyday coding, writing, and work that requires several steps. Useful starting points include reviewing a code change, drafting technical explanations, and turning notes into an actionable brief.

**How does GPT-6.2 Sol Pro differ from GPT-6.2 Sol?**

GPT-6.2 Sol Pro uses the same underlying model with pro reasoning. Choose it when a task warrants additional analysis, such as examining a migration plan for failure modes.

**How much text can GPT-6.2 Sol handle?**

The underlying model has a 1,050,000-token context window, with up to 922,000 input tokens and 128,000 output tokens. Treat the output ceiling as a budget for reasoning and the visible answer, rather than a guaranteed answer length.

**Does GPT-6.2 Sol know recent events?**

Its listed knowledge cutoff is June 1, 2026. Supply current sources when asking about later events, releases, or changing information.

**Should I ask GPT-6.2 Sol to think step by step?**

Use a direct task description instead. State the desired result, relevant constraints, and what the final answer should contain; OpenAI says step-by-step prompting may hinder reasoning models.

