[Integrations](https://spiral.ai/integrations) › [dots](https://spiral.ai/integrations/dots) › [Claude Sonnet Latest](https://spiral.ai/integrations/dots/claude-sonnet-latest)

# How to Use Claude Sonnet Latest in dots

Use Claude Sonnet Latest for scoped coding, code review, and document drafts. Anthropic positions Claude Sonnet 5.5 for everyday work and Claude Opus 5.5 for complex, open-ended tasks.

|  |  |
| --- | --- |
| Model | Claude Sonnet Latest |
| Available through | Anthropic |
| Category | LLM |
| Price | Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.13 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, $0.26 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 Latest in dots

- Each morning, use Claude Sonnet Latest to summarize the support conversations supplied for this run. Identify recurring problems, quote supporting messages, and list unanswered questions without inventing causes.
- Every Friday, use Claude Sonnet Latest to draft release notes from the completed change descriptions supplied for this run. Include only changes completed during the reporting period and cite the supporting descriptions.
- Each day, use Claude Sonnet Latest to compare the previous and current policy text supplied for this run. Quote changed commitments and summarize their practical effects in a table.
- Each week, use Claude Sonnet Latest to turn the supplied project updates into a brief under 400 words. Separate completed work, stated blockers, and next steps; preserve the original owners and dates.
- For each scheduled support review, use Claude Sonnet Latest to draft replies from the supplied customer messages and approved policy text. Keep each reply under 150 words and mark unanswered policy questions for review.

## How to set up Claude Sonnet Latest in dots

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send dots 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 your dot. Copy it.

2. **Send your dot this message**: Your dot reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give your dot the key**: When your dot asks for the key, add it where your dot 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 Latest**: 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-latest",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

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

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

## Claude Sonnet Latest tools and prices

- [Claude Sonnet Latest](https://spiral.ai/tools/anthropic/~anthropic/claude-sonnet-latest) (Anthropic): Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.13 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, $0.26 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 Latest in dots?

Use Claude Sonnet to produce recurring briefs, feedback summaries, and draft replies from each run's supplied material. Define the reporting period, required evidence, and handling of missing information.

### Fix a reproducible bug

Give Claude Sonnet the failing behavior, expected result, and relevant code. Request a focused patch and a check that exercises the failure.

### Review a proposed code change

Ask Claude Sonnet to inspect a diff for correctness problems and missing edge cases. Require each finding to identify the affected code and explain a concrete failure.

### Explain an unfamiliar codebase

Have Claude Sonnet trace one request through the relevant modules. Ask for entry points, data transformations, and the code supporting each explanation.

### Compare source documents

Ask Claude Sonnet to compare requirements or proposals, quoting the passages behind each difference. Separate explicit commitments from missing information.

### Draft support replies

Provide a customer message and approved policy text. Ask Claude Sonnet for a concise draft that answers the question and flags anything the policy does not establish.

### Translate product communications

Ask Claude Sonnet to translate release announcements or support replies into a specified language. Supply terminology to preserve and review the result with a fluent speaker.

### Write release notes from completed work

Give Claude Sonnet completed change descriptions and ask for user-facing release notes. Require every statement to trace back to a supplied change.

### Analyze customer feedback

Ask Claude Sonnet to organize supplied feedback into recurring problems, supporting examples, and unresolved questions. Keep observations separate from proposed explanations.

## Overview

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

## Claude Sonnet Latest in other agents

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

## More dots guides

- [Claude Sonnet 5.5](https://spiral.ai/integrations/dots/claude-sonnet-5-5)
- [Codestral 2508](https://spiral.ai/integrations/dots/codestral-2508)
- [Claude Sonnet 5](https://spiral.ai/integrations/dots/claude-sonnet-5)
- [Command A](https://spiral.ai/integrations/dots/command-a)
- [Claude Sonnet 4.6](https://spiral.ai/integrations/dots/claude-sonnet-4-6)
- [Command A Plus](https://spiral.ai/integrations/dots/command-a-plus)

## Questions about Claude Sonnet Latest in dots

**Can dots use Claude Sonnet Latest?**

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

**How much does Claude Sonnet Latest cost in dots?**

Up to $0.05343 per run at the default inputs. $2.60 per 1M input tokens, $0.13 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, $0.26 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 dots plan is separate.

**Do I need an Anthropic account to use Claude Sonnet Latest in dots?**

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

**How long does it take to set up Claude Sonnet Latest in dots?**

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

**Does dots wait while Claude Sonnet Latest runs?**

Claude Sonnet Latest runs in the background. dots starts the run, checks on it and gives you the text, json when it's ready.

**What is Claude Sonnet good at?**

Claude Sonnet is useful for everyday development, including feature work, bug fixes, and code review. Document drafting and data analysis are also documented uses for Claude Sonnet 5.5.

**Where does Claude Sonnet fall short?**

Anthropic finds Claude Opus 5.5 stronger than Claude Sonnet 5.5 on complex, open-ended work requiring sustained judgment. Give Claude Sonnet a defined task and a clear completion condition.

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

Anthropic documents a 1 million-token context window and a 128,000-token maximum output for Claude Sonnet 5.5.

**Which reasoning effort should I use?**

For Claude Sonnet 5.5 coding and multistep tool tasks, start with medium effort when the task is well specified. Move to high for harder or longer work, and compare results on representative tasks.

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

Yes. Claude processes and generates text in most world languages using standard Unicode characters, although performance varies by language. Check examples in the languages your work requires.

