[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [GPT-4.1](https://spiral.ai/integrations/instinct/gpt-4-1)

# How to Use GPT-4.1 in Instinct

GPT-4.1 is useful for code edits, detailed instructions, and analysis of long documents. Its 1,047,576-token context window is much larger than its 32,768-token output limit, so ask for focused results.

|  |  |
| --- | --- |
| Model | GPT-4.1 |
| Available through | OpenAI |
| Category | LLM |
| Price | Up to $0.04269 per run at the default inputs. $2.60 per 1M input tokens, $0.65 per 1M cached input tokens, $10.40 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-4.1 in Instinct

- Use GPT-4.1 on each scheduled run to summarize the supplied product updates. Select the five changes most relevant to developers, explain their practical effect, and retain each source reference. Skip claims the source text does not support.
- Use GPT-4.1 to review the customer messages supplied for this run. Sort them into bug reports, feature requests, and usage questions. Give each message one primary category and retain its original reference.
- Use GPT-4.1 to turn this run's meeting transcripts into an action list. Include the task, named owner, stated deadline, and supporting excerpt. Mark missing owners or deadlines as unstated.
- Use GPT-4.1 to compare the previous and current policy text supplied for this run. Report changes to requirements, exceptions, and dates, with evidence from both versions. If there are no substantive changes, say so.
- Use GPT-4.1 to rank the source passages supplied for this run against the tracked research question. Return up to five useful passages with references and brief relevance explanations. Return fewer when the evidence is weak.

## How to set up GPT-4.1 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-4.1**: 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-4.1",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds GPT-4.1 on Spiral, shows the price and runs it.

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

## GPT-4.1 tools and prices

- [GPT-4.1](https://spiral.ai/tools/openai/openai/gpt-4.1) (OpenAI): Up to $0.04269 per run at the default inputs. $2.60 per 1M input tokens, $0.65 per 1M cached input tokens, $10.40 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| logprobs |  | — |  |
| max_tokens | 16 to … | — | The most output tokens to generate. |

## What can you do with GPT-4.1 in Instinct?

GPT-4.1 can turn recurring batches of source text into digests, ranked queues, and structured summaries. Define relevance and missing-information rules so each run produces a consistent result.

### Focused bug fixes

Ask GPT-4.1 to trace a reported failure, change the relevant code, and return a patch with verification results.

### Pull request review

Give GPT-4.1 a diff and surrounding code. Request actionable findings with a concrete failure scenario for each.

### Questions across long documents

Use GPT-4.1 to locate relevant passages across supplied material and answer a narrow question with supporting excerpts.

### Structured record extraction

Have GPT-4.1 turn unstructured text into records, leaving unsupported values empty and retaining evidence for review.

### Policy-based response drafts

Ask GPT-4.1 to draft replies using supplied policies, explicit exceptions, and a defined response format.

### Recurring source digests

Use GPT-4.1 to select relevant updates from supplied text and produce a digest with source references.

### Search result ranking

Give GPT-4.1 a question and candidate passages. Request a ranked shortlist with a relevance explanation for each selection.

### Constrained text rewrites

Ask GPT-4.1 to rewrite supplied text while preserving specified facts, following a length target, and avoiding named terms.

## Overview

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

## GPT-4.1 in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-4-1)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-4-1)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-4-1)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-4-1)
- [Cline](https://spiral.ai/integrations/cline/gpt-4-1)
- [Codex](https://spiral.ai/integrations/codex/gpt-4-1)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-4-1)
- [Devin](https://spiral.ai/integrations/devin/gpt-4-1)
- [dots](https://spiral.ai/integrations/dots/gpt-4-1)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-4-1)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-4-1)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-4-1)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-4-1)
- [goose](https://spiral.ai/integrations/goose/gpt-4-1)
- [Grok](https://spiral.ai/integrations/grok/gpt-4-1)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-4-1)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-4-1)
- [Manus](https://spiral.ai/integrations/manus/gpt-4-1)
- [Muse](https://spiral.ai/integrations/muse/gpt-4-1)
- [Muse Code](https://spiral.ai/integrations/muse-code/gpt-4-1)
- [n8n](https://spiral.ai/integrations/n8n/gpt-4-1)
- [Notion](https://spiral.ai/integrations/notion/gpt-4-1)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-4-1)
- [opencode](https://spiral.ai/integrations/opencode/gpt-4-1)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-4-1)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-4-1)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-4-1)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-4-1)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-4-1)

## More Instinct guides

- [GPT-3.5 Turbo 0613](https://spiral.ai/integrations/instinct/gpt-3-5-turbo-0613)
- [GPT-4.1 mini](https://spiral.ai/integrations/instinct/gpt-4-1-mini)
- [GPT Terra Latest](https://spiral.ai/integrations/instinct/gpt-terra-latest)
- [GPT-4o](https://spiral.ai/integrations/instinct/gpt-4o)
- [GPT Sol Latest](https://spiral.ai/integrations/instinct/gpt-sol-latest)
- [GPT-4o 2024-08-06](https://spiral.ai/integrations/instinct/gpt-4o-2024-08-06)

## Questions about GPT-4.1 in Instinct

**Can Instinct use GPT-4.1?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run GPT-4.1 like any built-in tool.

**How much does GPT-4.1 cost in Instinct?**

Up to $0.04269 per run at the default inputs. $2.60 per 1M input tokens, $0.65 per 1M cached input tokens, $10.40 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-4.1 in Instinct?**

You need no OpenAI account. Instinct uses one Spiral API key for every tool, and Spiral runs GPT-4.1 on its own OpenAI account.

**How long does it take to set up GPT-4.1 in Instinct?**

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

**Does Instinct wait while GPT-4.1 runs?**

GPT-4.1 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is GPT-4.1 good at?**

GPT-4.1 is useful for code editing, code review, and tasks with detailed response requirements. Its training includes following code diff formats, which makes focused patches a practical use.

**How much can GPT-4.1 read and write?**

The context window is 1,047,576 tokens, while one response can contain at most 32,768 output tokens. A large input allowance does not mean it can reproduce an equally large document in one answer.

**Where does GPT-4.1 struggle with long documents?**

Retrieving many separate details from a long context can reduce accuracy. For exhaustive extraction, split the task into smaller sections and check the combined results against the source.

**How should I prompt GPT-4.1?**

State the task, required format, and exceptions explicitly because GPT-4.1 interprets instructions literally. Specify what it should return when information is missing.

**Does valid JSON mean GPT-4.1 extracted the right answer?**

No. Structured Outputs can enforce the requested schema, but the values can still be wrong; check extracted facts against the original text.

