[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Claude Opus 5.5](https://spiral.ai/integrations/instinct/claude-opus-5-5)

# How to Use Claude Opus 5.5 in Instinct

Claude Opus 5.5 is built for long coding tasks, large refactors, and detailed knowledge work. Compared with Claude Opus 5, it generates output more than 30% faster in Anthropic’s tests.

|  |  |
| --- | --- |
| Model | Claude Opus 5.5 |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Claude Opus 5.5 in Instinct

- Every Monday, use Claude Opus 5.5 to review the past week's official release notes for PostgreSQL. Produce a dated brief of relevant changes with source links, and say explicitly when no relevant release was found.
- Each weekday, use Claude Opus 5.5 to review newly available material from the connected research sources. Summarize evidence that changes our existing conclusions, cite the original passages, and list unresolved questions.
- Every Friday, use Claude Opus 5.5 to compare the week's connected project updates. Report conflicting deadlines, missing owners, and unresolved dependencies with supporting passages; finish only after checking all three categories.
- Each month, use Claude Opus 5.5 to check the connected operating report for inconsistent totals and assumptions. Show the calculation behind each finding, and mark unavailable evidence instead of estimating it.
- Every morning, use Claude Opus 5.5 to prepare a 400-word brief from new items in the connected industry sources. Include only supported developments, link each source, and check every claim before completing the report.

## How to set up Claude Opus 5.5 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 5.5**: 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-5.5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Claude Opus 5.5 on Spiral, shows the price and runs it.

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

## Claude Opus 5.5 tools and prices

- [Claude Opus 5.5](https://spiral.ai/tools/anthropic/anthropic/claude-opus-5.5) (Anthropic): Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 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 5.5 in Instinct?

Produce recurring research briefs and consistency checks with Claude Opus 5.5. Define what each report must contain and verify those requirements before marking a scheduled task complete.

### Migrate a large codebase

Use Claude Opus 5.5 to move deprecated interfaces to their replacements, update affected tests, and report any remaining blockers against a migration checklist.

### Refactor across modules

Ask Claude Opus 5.5 to trace dependencies, simplify duplicated logic, and verify that the affected behavior still passes its tests.

### Review a complicated change

Have Claude Opus 5.5 examine a patch and its surrounding code, then report reproducible defects with evidence and a suggested test.

### Prepare a research brief

Give Claude Opus 5.5 the source material and a specific decision to support. Request a concise brief with quotations for key claims and a list of unresolved questions.

### Check a financial analysis

Ask Claude Opus 5.5 to inspect supplied calculations, identify inconsistent assumptions, and explain how each proposed correction changes the result.

### Reconcile planning records

Use Claude Opus 5.5 to compare lengthy planning material, flag conflicting commitments, and produce a decision log with evidence for each entry.

## Overview

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

## Claude Opus 5.5 in other agents

- [Amp](https://spiral.ai/integrations/amp/claude-opus-5-5)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/claude-opus-5-5)
- [Claude](https://spiral.ai/integrations/claude-desktop/claude-opus-5-5)
- [Claude Code](https://spiral.ai/integrations/claude-code/claude-opus-5-5)
- [Cline](https://spiral.ai/integrations/cline/claude-opus-5-5)
- [Codex](https://spiral.ai/integrations/codex/claude-opus-5-5)
- [Cursor](https://spiral.ai/integrations/cursor/claude-opus-5-5)
- [Devin](https://spiral.ai/integrations/devin/claude-opus-5-5)
- [dots](https://spiral.ai/integrations/dots/claude-opus-5-5)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/claude-opus-5-5)
- [Gemini](https://spiral.ai/integrations/gemini/claude-opus-5-5)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/claude-opus-5-5)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/claude-opus-5-5)
- [goose](https://spiral.ai/integrations/goose/claude-opus-5-5)
- [Grok](https://spiral.ai/integrations/grok/claude-opus-5-5)
- [Grok Build](https://spiral.ai/integrations/grok-build/claude-opus-5-5)
- [Hermes](https://spiral.ai/integrations/hermes/claude-opus-5-5)
- [Manus](https://spiral.ai/integrations/manus/claude-opus-5-5)
- [Muse](https://spiral.ai/integrations/muse/claude-opus-5-5)
- [Muse Code](https://spiral.ai/integrations/muse-code/claude-opus-5-5)
- [n8n](https://spiral.ai/integrations/n8n/claude-opus-5-5)
- [Notion](https://spiral.ai/integrations/notion/claude-opus-5-5)
- [OpenClaw](https://spiral.ai/integrations/openclaw/claude-opus-5-5)
- [opencode](https://spiral.ai/integrations/opencode/claude-opus-5-5)
- [Perplexity](https://spiral.ai/integrations/perplexity/claude-opus-5-5)
- [Raycast](https://spiral.ai/integrations/raycast/claude-opus-5-5)
- [VS Code](https://spiral.ai/integrations/vscode/claude-opus-5-5)
- [Windsurf](https://spiral.ai/integrations/windsurf/claude-opus-5-5)
- [Zapier](https://spiral.ai/integrations/zapier/claude-opus-5-5)

## More Instinct guides

- [Claude Opus 5](https://spiral.ai/integrations/instinct/claude-opus-5)
- [Claude Opus Latest](https://spiral.ai/integrations/instinct/claude-opus-latest)
- [Claude Opus 4.8](https://spiral.ai/integrations/instinct/claude-opus-4-8)
- [Claude Sonnet 4.6](https://spiral.ai/integrations/instinct/claude-sonnet-4-6)
- [Claude Opus 4.7](https://spiral.ai/integrations/instinct/claude-opus-4-7)
- [Claude Sonnet 5](https://spiral.ai/integrations/instinct/claude-sonnet-5)

## Questions about Claude Opus 5.5 in Instinct

**Can Instinct use Claude Opus 5.5?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Claude Opus 5.5 like any built-in tool.

**How much does Claude Opus 5.5 cost in Instinct?**

Up to $0.10686 per run at the default inputs. $5.20 per 1M input tokens, $0.26 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $26.00 per 1M output tokens; for a prompt above 200,000 tokens, $10.40 per 1M input tokens, $0.52 per 1M cached input tokens, $13.00 per 1M cache write tokens, $20.80 per 1M 1-hour cache write tokens, $39.00 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 Anthropic account to use Claude Opus 5.5 in Instinct?**

You need no Anthropic account. Instinct uses one Spiral API key for every tool, and Spiral runs Claude Opus 5.5 on its own Anthropic account.

**How long does it take to set up Claude Opus 5.5 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 5.5 runs?**

Claude Opus 5.5 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 5.5 best suited for?**

Use it for work with several dependent steps, such as a large refactor, a code migration, or a detailed analysis. Give it a concrete deliverable and a clear completion checklist.

**How much text can Claude Opus 5.5 handle?**

It has a 1 million token context window and supports up to 128,000 output tokens in a standard response. Thinking also uses the output budget, so the full allowance is not available for the visible answer.

**Does higher effort always produce a better result?**

Test effort settings on your actual tasks before choosing one. For demanding work, leave enough output space for thinking and the answer, then compare correctness and completeness.

**How should I prompt Claude Opus 5.5?**

State the deliverable, constraints, and completion criteria explicitly. Include an example when the answer must follow a particular format or writing style.

**Can I trust every figure or citation it produces?**

Check important claims against their sources. Ask for supporting quotations, and tell it to mark missing evidence instead of filling gaps.

