[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Claude Sonnet 4.6](https://spiral.ai/integrations/instinct/claude-sonnet-4-6)

# How to Use Claude Sonnet 4.6 in Instinct

Use Claude Sonnet 4.6 to debug code, build interfaces, and analyze long documents. Compared with Claude Sonnet 4.5, early users reported better context-aware edits and less duplicated logic.

|  |  |
| --- | --- |
| Model | Claude Sonnet 4.6 |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.080145 per run at the default inputs. $3.90 per 1M input tokens, $0.39 per 1M cached input tokens, $4.875 per 1M cache write tokens, $7.80 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens; for a prompt above 200,000 tokens, $7.80 per 1M input tokens, $0.78 per 1M cached input tokens, $9.75 per 1M cache write tokens, $15.60 per 1M 1-hour cache write tokens, $29.25 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 4.6 in Instinct

- Each morning, use Claude Sonnet 4.6 to summarize the research excerpts supplied for that run. Return five findings with source labels and supporting quotations.
- Every Friday, use Claude Sonnet 4.6 to compare the current and previous policy text supplied for that run. Report changed obligations, deadlines, and unresolved questions.
- Each day, use Claude Sonnet 4.6 to review the customer messages supplied for that run. Summarize recurring problems and quote one representative message for each.
- Every Monday, use Claude Sonnet 4.6 to translate the approved announcements supplied for that run from English into French. Preserve product names and return each translation beside its original.
- Each week, use Claude Sonnet 4.6 with high reasoning effort to compare the progress updates supplied for that run against the stated plan. List supported achievements, dependencies, and unanswered questions.

## How to set up Claude Sonnet 4.6 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 4.6**: 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-4.6",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Instinct finds Claude Sonnet 4.6 on Spiral, shows the price and runs it.

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

## Claude Sonnet 4.6 tools and prices

- [Claude Sonnet 4.6](https://spiral.ai/tools/anthropic/anthropic/claude-sonnet-4.6) (Anthropic): Up to $0.080145 per run at the default inputs. $3.90 per 1M input tokens, $0.39 per 1M cached input tokens, $4.875 per 1M cache write tokens, $7.80 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens; for a prompt above 200,000 tokens, $7.80 per 1M input tokens, $0.78 per 1M cached input tokens, $9.75 per 1M cache write tokens, $15.60 per 1M 1-hour cache write tokens, $29.25 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — | Taken only at reasoning effort "none", this model's default. |
| 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). |
| temperature | 0 to 1 | — | Taken only at reasoning effort "none", this model's default. |

## What can you do with Claude Sonnet 4.6 in Instinct?

Turn recurring batches of supplied text into research briefs, comparisons, and translated drafts with Claude Sonnet 4.6. Define the evidence required for each finding and the format each run should return.

### Fix bugs with project context

Use Claude Sonnet 4.6 to trace a reported failure through the relevant code, make a focused repair, and explain the verification results.

### Consolidate duplicated code

Ask Claude Sonnet 4.6 to find repeated logic, propose a shared implementation, and check that the callers keep their existing behavior.

### Build an interface from requirements

Give Claude Sonnet 4.6 a user flow and acceptance criteria to turn into frontend code, including loading, empty, and error states.

### Compare contract language

Use Claude Sonnet 4.6 to compare supplied contract text, quote changed clauses, and list questions for a reviewer.

### Synthesize research excerpts

Ask Claude Sonnet 4.6 to compare supplied research passages, separate agreements from disagreements, and support each finding with a quotation.

### Translate customer communications

Use Claude Sonnet 4.6 to translate supplied messages for a named language and audience while preserving product names and technical terms.

## Overview

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

## Claude Sonnet 4.6 in other agents

- [Amp](https://spiral.ai/integrations/amp/claude-sonnet-4-6)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/claude-sonnet-4-6)
- [Claude](https://spiral.ai/integrations/claude-desktop/claude-sonnet-4-6)
- [Claude Code](https://spiral.ai/integrations/claude-code/claude-sonnet-4-6)
- [Cline](https://spiral.ai/integrations/cline/claude-sonnet-4-6)
- [Codex](https://spiral.ai/integrations/codex/claude-sonnet-4-6)
- [Cursor](https://spiral.ai/integrations/cursor/claude-sonnet-4-6)
- [Devin](https://spiral.ai/integrations/devin/claude-sonnet-4-6)
- [dots](https://spiral.ai/integrations/dots/claude-sonnet-4-6)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/claude-sonnet-4-6)
- [Gemini](https://spiral.ai/integrations/gemini/claude-sonnet-4-6)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/claude-sonnet-4-6)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/claude-sonnet-4-6)
- [goose](https://spiral.ai/integrations/goose/claude-sonnet-4-6)
- [Grok](https://spiral.ai/integrations/grok/claude-sonnet-4-6)
- [Grok Build](https://spiral.ai/integrations/grok-build/claude-sonnet-4-6)
- [Hermes](https://spiral.ai/integrations/hermes/claude-sonnet-4-6)
- [Manus](https://spiral.ai/integrations/manus/claude-sonnet-4-6)
- [Muse](https://spiral.ai/integrations/muse/claude-sonnet-4-6)
- [Muse Code](https://spiral.ai/integrations/muse-code/claude-sonnet-4-6)
- [n8n](https://spiral.ai/integrations/n8n/claude-sonnet-4-6)
- [Notion](https://spiral.ai/integrations/notion/claude-sonnet-4-6)
- [OpenClaw](https://spiral.ai/integrations/openclaw/claude-sonnet-4-6)
- [opencode](https://spiral.ai/integrations/opencode/claude-sonnet-4-6)
- [Perplexity](https://spiral.ai/integrations/perplexity/claude-sonnet-4-6)
- [Raycast](https://spiral.ai/integrations/raycast/claude-sonnet-4-6)
- [VS Code](https://spiral.ai/integrations/vscode/claude-sonnet-4-6)
- [Windsurf](https://spiral.ai/integrations/windsurf/claude-sonnet-4-6)
- [Zapier](https://spiral.ai/integrations/zapier/claude-sonnet-4-6)

## More Instinct guides

- [Claude Opus Latest](https://spiral.ai/integrations/instinct/claude-opus-latest)
- [Claude Sonnet 5](https://spiral.ai/integrations/instinct/claude-sonnet-5)
- [Claude Opus 5.5](https://spiral.ai/integrations/instinct/claude-opus-5-5)
- [Claude Sonnet 5.5](https://spiral.ai/integrations/instinct/claude-sonnet-5-5)
- [Claude Opus 5](https://spiral.ai/integrations/instinct/claude-opus-5)
- [Claude Sonnet Latest](https://spiral.ai/integrations/instinct/claude-sonnet-latest)

## Questions about Claude Sonnet 4.6 in Instinct

**Can Instinct use Claude Sonnet 4.6?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Claude Sonnet 4.6 like any built-in tool.

**How much does Claude Sonnet 4.6 cost in Instinct?**

Up to $0.080145 per run at the default inputs. $3.90 per 1M input tokens, $0.39 per 1M cached input tokens, $4.875 per 1M cache write tokens, $7.80 per 1M 1-hour cache write tokens, $19.50 per 1M output tokens; for a prompt above 200,000 tokens, $7.80 per 1M input tokens, $0.78 per 1M cached input tokens, $9.75 per 1M cache write tokens, $15.60 per 1M 1-hour cache write tokens, $29.25 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 4.6 in Instinct?**

You need no Anthropic account. Instinct uses one Spiral API key for every tool, and Spiral runs Claude Sonnet 4.6 on its own Anthropic account.

**How long does it take to set up Claude Sonnet 4.6 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 4.6 runs?**

Claude Sonnet 4.6 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 4.6 useful for?**

Use it for coding, interface development, document analysis, and planning tasks that require several steps. Give it a concrete deliverable, such as a tested bug fix or a comparison supported by quotations.

**How much text can Claude Sonnet 4.6 handle?**

Anthropic currently lists a 1 million token context window and up to 128K output tokens. Treat those as ceilings; ask for the sections and level of detail your task actually needs.

**When should I use more reasoning effort?**

Start with medium effort for coding and most other applications. Try high effort for difficult reasoning, then compare the results on representative tasks before keeping the higher setting.

**Can Claude Sonnet 4.6 work in languages other than English?**

Yes. Claude supports most world languages that use standard Unicode characters, although quality varies by language. Name the source language, target language, and intended audience in translation requests.

**How should I prompt Claude Sonnet 4.6 for long document analysis?**

Specify the question, required output, and evidence standard. Ask it to extract relevant quotations first, then build its analysis from those passages.

