[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [GPT Sol Latest](https://spiral.ai/integrations/instinct/gpt-sol-latest)

# How to Use GPT Sol Latest in Instinct

Use GPT Sol Latest to write and debug code, understand documents, and work through business tasks with several steps. Give it a concrete deliverable and clear checks for a successful result.

|  |  |
| --- | --- |
| Model | GPT Sol Latest |
| 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, with a Spiral API key |

## Prompts to try with GPT Sol Latest in Instinct

- Every weekday, use GPT Sol Latest to summarize the project updates supplied for that run. Report completed work, blockers, and next actions in under 300 words. Attribute each item and mark missing information.
- Every Friday, use GPT Sol Latest with medium reasoning effort to compare the week's supplied progress reports with the stated milestones. Draft a status brief showing evidence for each milestone assessment.
- Each morning, use GPT Sol Latest to review the support summaries supplied for that run. Identify recurring problems, quote the supporting ticket references, and draft investigation questions without guessing causes.
- Each week, use GPT Sol Latest to compare the supplied procedure changes with the current procedure text. Draft a revised procedure and list any conflicting instructions that need a decision.
- At the end of each month, use GPT Sol Latest with high reasoning effort to compare the supplied proposals against our documented requirements. Prepare a decision memo with tradeoffs, evidence gaps, and next actions.

## How to set up GPT Sol Latest 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 Sol Latest**: 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-sol-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds GPT Sol Latest on Spiral, shows the price and runs it.

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

## GPT Sol Latest tools and prices

- [GPT Sol Latest](https://spiral.ai/tools/openai/~openai/gpt-sol-latest) (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. |
| tool_choice |  | — |  |
| response_format |  | — |  |

## What can you do with GPT Sol Latest in Instinct?

GPT Sol can prepare recurring briefs and draft follow-up work from updates supplied at each run. Define the reporting period, evidence requirements, and completion checks for each recurring task.

### Fix a reproducible bug

Trace a reported failure through the relevant code, make a focused correction, and test the behavior that originally failed.

### Build a feature from acceptance criteria

Turn a defined feature request into code and tests, with a final report showing which acceptance criteria were checked.

### Review a proposed code change

Compare a change with its intended behavior and identify concrete defects, missing tests, and cases the author should check.

### Write a decision memo

Compare proposals against supplied requirements, explain the tradeoffs, and identify evidence still needed before a decision.

### Draft an operating procedure

Turn process notes into ordered steps, responsibilities, exception handling, and completion checks.

### Prepare a recurring status brief

Summarize supplied updates into completed work, blockers, and next actions while preserving the source of each claim.

### Check a document against requirements

Compare a draft with an explicit checklist, identify unsupported statements, and propose revisions tied to the missing requirements.

## Overview

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

## GPT Sol Latest in other agents

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

## More Instinct guides

- [GPT Mini Latest](https://spiral.ai/integrations/instinct/gpt-mini-latest)
- [GPT Terra Latest](https://spiral.ai/integrations/instinct/gpt-terra-latest)
- [GPT Luna Latest](https://spiral.ai/integrations/instinct/gpt-luna-latest)
- [GPT-3.5 Turbo 0613](https://spiral.ai/integrations/instinct/gpt-3-5-turbo-0613)
- [GPT Chat Latest](https://spiral.ai/integrations/instinct/gpt-chat-latest)
- [GPT-4.1](https://spiral.ai/integrations/instinct/gpt-4-1)

## Questions about GPT Sol Latest in Instinct

**Can Instinct use GPT Sol Latest?**

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

**How much does GPT Sol Latest cost in Instinct?**

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 Instinct plan is separate.

**Do I need an OpenAI account to use GPT Sol Latest in Instinct?**

You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT Sol Latest on its own OpenAI account.

**How long does it take to set up GPT Sol Latest in Instinct?**

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

**Does Instinct wait while GPT Sol Latest runs?**

GPT Sol Latest runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT Sol good at?**

GPT Sol is useful for writing and debugging code, understanding documents, and completing work with several steps. Practical examples include a tested bug fix, a decision memo, or an operating procedure based on supplied requirements.

**Can GPT Sol make factual mistakes?**

Yes. Check factual claims against the source material, and ask it to distinguish supported conclusions from assumptions.

**How should I prompt GPT Sol?**

State the task, the constraints, and the result you want in direct language. For a code change, specify the behavior to preserve and the tests that should pass; for a document, specify the audience and required sections.

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

You do not need to. It reasons internally; ask for a useful explanation of the result, supporting evidence, or verification checks instead.

**How should I choose reasoning effort?**

Try lower effort for a narrow task where speed matters, then compare the result with medium or high effort for difficult debugging or planning. Judge the finished work against the same requirements before choosing.

