[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Claude Opus 4.7](https://spiral.ai/integrations/instinct/claude-opus-4-7)

# How to Use Claude Opus 4.7 in Instinct

Claude Opus 4.7 fits complex coding, debugging, and work that takes several steps to finish. Compared with Claude Opus 4.6, it improves advanced software engineering and follows instructions more literally.

|  |  |
| --- | --- |
| Model | Claude Opus 4.7 |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Claude Opus 4.7 in Instinct

- Use Claude Opus 4.7 on each scheduled run to review new incident summaries. Identify recurring failure patterns, cite the relevant entries, and return a digest under 500 words.
- Use Claude Opus 4.7 with extra-high reasoning effort each week to compare the supplied architecture decisions with current requirements. Report conflicts and the questions needed to resolve them.
- Use Claude Opus 4.7 each morning to analyze the supplied error summaries. Group related symptoms, propose causes, and recommend one diagnostic check per proposed cause.
- Use Claude Opus 4.7 each Friday to review the week's technical proposals. Compare their assumptions and dependencies, then list decisions that require an explicit owner.
- Use Claude Opus 4.7 on each scheduled run to check new specification text against the approved requirements supplied with it. Quote contradictions and return a concise review with proposed corrections.

## How to set up Claude Opus 4.7 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 Claude Opus 4.7**: 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": "anthropic",
    "model": "anthropic/claude-opus-4.7",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Claude Opus 4.7 on Spiral, shows the price and runs it.

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

## Claude Opus 4.7 tools and prices

- [Claude Opus 4.7](https://spiral.ai/tools/anthropic/anthropic/claude-opus-4.7) (Anthropic): Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| reasoning |  | — | Reasoning effort; reasoning tokens count toward max_tokens. |
| max_tokens | 1 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 Claude Opus 4.7 in Instinct?

Claude Opus 4.7 can produce recurring technical reviews and investigate problems that require several reasoning steps. Define the evidence to examine and the completion criteria for each run.

### Trace a bug across services

Ask Claude Opus 4.7 to follow a failing request through the relevant code, identify the cause, and propose a fix with a regression check.

### Review a substantial code change

Have Claude Opus 4.7 examine a change across files and report concrete failure scenarios, affected locations, and suggested corrections.

### Plan a legacy code migration

Give Claude Opus 4.7 the current design and compatibility requirements, then request migration stages with acceptance criteria for each stage.

### Compare technical proposals

Ask Claude Opus 4.7 to compare supplied proposals against explicit requirements and produce a decision table with unresolved questions.

### Turn an incident timeline into a review

Provide Claude Opus 4.7 with the incident narrative and diagnostic evidence, then request a causal analysis and proposed follow-up checks.

### Check a specification for contradictions

Use Claude Opus 4.7 to compare requirements across a long specification and flag conflicting statements before implementation.

### Draft a technical handoff

Ask Claude Opus 4.7 to turn a completed investigation into a concise handoff covering the problem, findings, remaining questions, and next actions.

## Overview

- [Anthropic Claude](https://spiral.ai/providers/anthropic)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## Claude Opus 4.7 in other agents

- [Amp](https://spiral.ai/integrations/amp/claude-opus-4-7)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/claude-opus-4-7)
- [Claude](https://spiral.ai/integrations/claude-desktop/claude-opus-4-7)
- [Claude Code](https://spiral.ai/integrations/claude-code/claude-opus-4-7)
- [Cline](https://spiral.ai/integrations/cline/claude-opus-4-7)
- [Codex](https://spiral.ai/integrations/codex/claude-opus-4-7)
- [Cursor](https://spiral.ai/integrations/cursor/claude-opus-4-7)
- [Devin](https://spiral.ai/integrations/devin/claude-opus-4-7)
- [dots](https://spiral.ai/integrations/dots/claude-opus-4-7)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/claude-opus-4-7)
- [Gemini](https://spiral.ai/integrations/gemini/claude-opus-4-7)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/claude-opus-4-7)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/claude-opus-4-7)
- [goose](https://spiral.ai/integrations/goose/claude-opus-4-7)
- [Grok](https://spiral.ai/integrations/grok/claude-opus-4-7)
- [Grok Build](https://spiral.ai/integrations/grok-build/claude-opus-4-7)
- [Hermes](https://spiral.ai/integrations/hermes/claude-opus-4-7)
- [Manus](https://spiral.ai/integrations/manus/claude-opus-4-7)
- [Muse](https://spiral.ai/integrations/muse/claude-opus-4-7)
- [Muse Code](https://spiral.ai/integrations/muse-code/claude-opus-4-7)
- [n8n](https://spiral.ai/integrations/n8n/claude-opus-4-7)
- [Notion](https://spiral.ai/integrations/notion/claude-opus-4-7)
- [OpenClaw](https://spiral.ai/integrations/openclaw/claude-opus-4-7)
- [opencode](https://spiral.ai/integrations/opencode/claude-opus-4-7)
- [Perplexity](https://spiral.ai/integrations/perplexity/claude-opus-4-7)
- [Raycast](https://spiral.ai/integrations/raycast/claude-opus-4-7)
- [VS Code](https://spiral.ai/integrations/vscode/claude-opus-4-7)
- [Windsurf](https://spiral.ai/integrations/windsurf/claude-opus-4-7)
- [Zapier](https://spiral.ai/integrations/zapier/claude-opus-4-7)

## More Instinct guides

- [Claude Opus 4.6](https://spiral.ai/integrations/instinct/claude-opus-4-6)
- [Claude Opus 4.8](https://spiral.ai/integrations/instinct/claude-opus-4-8)
- [Claude Opus 4.5](https://spiral.ai/integrations/instinct/claude-opus-4-5)
- [Claude Opus 5](https://spiral.ai/integrations/instinct/claude-opus-5)
- [Claude Haiku Latest](https://spiral.ai/integrations/instinct/claude-haiku-latest)
- [Claude Opus 5.5](https://spiral.ai/integrations/instinct/claude-opus-5-5)

## Questions about Claude Opus 4.7 in Instinct

**Can Instinct use Claude Opus 4.7?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Claude Opus 4.7 like any built-in tool.

**How much does Claude Opus 4.7 cost in Instinct?**

Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 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 Anthropic account to use Claude Opus 4.7 in Instinct?**

You need no Anthropic account. Instinct uses one Spiral API key for every tool, and Spiral runs Claude Opus 4.7 on its own Anthropic account.

**How long does it take to set up Claude Opus 4.7 in Instinct?**

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

**Does Instinct wait while Claude Opus 4.7 runs?**

Claude Opus 4.7 runs in the background. Instinct starts the run, checks on it and gives you the text, json when it's ready.

**What is Claude Opus 4.7 best suited for?**

Complex coding, debugging, and reviews that require following a problem across several files. Anthropic also recommends it for multistep work that previously needed close supervision.

**How much context and output can Claude Opus 4.7 handle?**

It has a one-million-token context window and supports up to 128,000 output tokens per standard response. Those are token limits, not word counts.

**Should I always choose maximum reasoning effort?**

Start with extra-high effort for coding and agent work. Maximum effort can overthink structured-output tasks, so use it when testing shows a useful improvement.

**What should I include in a coding prompt?**

State the goal, constraints, acceptance criteria, and relevant file locations in the first request. Give the model enough context to complete the task without piecing together requirements across many turns.

**How should I organize a long document prompt?**

Put the source material first and the question afterward. Include an example when the answer needs a particular format or voice.

