[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Claude Sonnet 5](https://spiral.ai/integrations/instinct/claude-sonnet-5)

# How to Use Claude Sonnet 5 in Instinct

Claude Sonnet 5 suits coding, debugging, and tasks that require several tool calls. Compared with Claude Sonnet 4.6, it improves reasoning, tool use, coding, and knowledge work.

|  |  |
| --- | --- |
| Model | Claude Sonnet 5 |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 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 Sonnet 5 in Instinct

- Each morning, use Claude Sonnet 5 to review the operational updates supplied to this run. Produce a brief of new blockers, named owners, and upcoming deadlines, with a source reference for every item.
- Every Friday, use Claude Sonnet 5 at high effort to compare this week's project updates with the previous week's. Identify changed commitments, unresolved dependencies, and decisions that need an owner.
- On each run, use Claude Sonnet 5 to extract every action item from the newly received meeting transcripts. Return the owner, action, deadline, and supporting sentence for every record.
- Each day, use Claude Sonnet 5 with the available search tools to check the official documentation for the technologies on my watchlist. Report only newly documented changes, with dates and links.
- Every Monday, use Claude Sonnet 5 at high effort to review the incident summaries supplied to this run. Identify recurring failure patterns and propose follow-up investigations, citing the incidents behind each proposal.

## How to set up Claude Sonnet 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 Sonnet 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-sonnet-5",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Claude Sonnet 5 on Spiral, shows the price and runs it.

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

## Claude Sonnet 5 tools and prices

- [Claude Sonnet 5](https://spiral.ai/tools/anthropic/anthropic/claude-sonnet-5) (Anthropic): Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 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 Sonnet 5 in Instinct?

Turn recurring updates into briefs and structured review queues with Claude Sonnet 5. Specify the reporting period and rules for every record so each scheduled run has a clear scope.

### Trace a bug to its cause

Use Claude Sonnet 5 to investigate a failing behavior, propose a fix, and check it against a reproducing test.

### Implement a change across a codebase

Give Claude Sonnet 5 the requirements and project constraints, then ask it to update the affected code and verify the result.

### Review code for behavioral bugs

Ask Claude Sonnet 5 to examine a change for incorrect behavior, explain each finding, and suggest a test that would expose it.

### Compare lengthy specifications

Have Claude Sonnet 5 compare supplied specifications, identify conflicting requirements, and produce a decision table with source references.

### Extract records from business text

Ask Claude Sonnet 5 to extract owners, deadlines, and commitments from supplied text, applying the same rules to every record.

### Research a technical decision

Use Claude Sonnet 5 with your agent's search tools to gather current documentation and compare implementation choices against explicit requirements.

### Prepare recurring operational briefs

Have Claude Sonnet 5 review newly supplied updates, identify unresolved issues, and draft a brief with evidence and proposed next actions.

## Overview

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

## Claude Sonnet 5 in other agents

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

## More Instinct guides

- [Claude Sonnet 4.6](https://spiral.ai/integrations/instinct/claude-sonnet-4-6)
- [Claude Sonnet 5.5](https://spiral.ai/integrations/instinct/claude-sonnet-5-5)
- [Claude Opus Latest](https://spiral.ai/integrations/instinct/claude-opus-latest)
- [Claude Sonnet Latest](https://spiral.ai/integrations/instinct/claude-sonnet-latest)
- [Claude Opus 5.5](https://spiral.ai/integrations/instinct/claude-opus-5-5)
- [Codestral 2508](https://spiral.ai/integrations/instinct/codestral-2508)

## Questions about Claude Sonnet 5 in Instinct

**Can Instinct use Claude Sonnet 5?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Claude Sonnet 5 like any built-in tool.

**How much does Claude Sonnet 5 cost in Instinct?**

Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.26 per 1M cached input tokens, $3.25 per 1M cache write tokens, $5.20 per 1M 1-hour cache write tokens, $13.00 per 1M output tokens; for a prompt above 200,000 tokens, $5.20 per 1M input tokens, $0.52 per 1M cached input tokens, $6.50 per 1M cache write tokens, $10.40 per 1M 1-hour cache write tokens, $19.50 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 Sonnet 5 in Instinct?**

You need no Anthropic account. Instinct uses one Spiral API key for every tool, and Spiral runs Claude Sonnet 5 on its own Anthropic account.

**How long does it take to set up Claude Sonnet 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 Sonnet 5 runs?**

Claude Sonnet 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 Sonnet 5 good at?**

Coding, debugging, reasoning, and work that takes several tool calls. Anthropic reports improvements over Claude Sonnet 4.6 in coding, tool use, reasoning, and knowledge work.

**How much text can Claude Sonnet 5 handle?**

It supports a 1 million token context window and up to 128,000 output tokens per response.

**Which effort level should I choose?**

Use high effort for complex reasoning and coding, and extra high for the hardest coding or agent tasks. Low effort fits short tasks where response speed matters more than deeper reasoning.

**Where can Claude Sonnet 5 fall short?**

Low effort can lead to shallow reasoning on moderately complex problems. It also interprets instructions literally, so explicitly say when a rule applies to every item or section.

**Does Claude Sonnet 5 know about recent events?**

Its reliable knowledge cutoff is January 2026. Supply current source material or ask your agent to retrieve it when an answer depends on newer information.

