How to Use Claude Sonnet 4.6 in Claude Code
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.
Prompts to try with Claude Sonnet 4.6 in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Claude Sonnet 4.6 at medium reasoning effort to investigate the failing tests in this project. Read the relevant implementation first, fix the cause, and report which checks passed.
Use Claude Sonnet 4.6 to inspect this project's repeated validation logic. Propose one shared implementation, update the callers, and verify that their behavior stays consistent.
Use Claude Sonnet 4.6 to build the settings screen described in this project's requirements. Follow the existing components and include loading, empty, validation, and error states.
Use Claude Sonnet 4.6 at high reasoning effort to review this project's authentication flow. Trace the code paths, cite file locations for each finding, and rank concrete defects by impact.
Use Claude Sonnet 4.6 to compare this project's implementation with its documented requirements. Return a table of fulfilled requirements, missing behavior, and evidence from the code.
How to set up Claude Sonnet 4.6 in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Claude Sonnet 4.6
One request; the result comes back by polling or a webhook.
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: Claude Code finds Claude Sonnet 4.6 on Spiral, shows the price and runs it.
Claude Sonnet 4.6 providers and prices
Spiral runs Claude Sonnet 4.6 through Anthropic. Open a card for today's price, with every fee included.
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
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top p | 0 to 1 | Taken only at reasoning effort "none", this model's default. | |
| 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. | |
| Reasoning effort | none, minimal, low, medium, high, or max | none | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Sonnet 4.6 is on its tool page: open its card above.
What can you do with Claude Sonnet 4.6 in Claude Code?
Turn project requirements and existing code into focused fixes, shared components, and working interfaces with Claude Sonnet 4.6. Give the agent acceptance criteria and ask it to report what it verified.
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.
More on Claude Sonnet 4.6 and Claude Code
Claude Sonnet 4.6 in other agents
Questions about Claude Sonnet 4.6 in Claude Code
Can Claude Code use Claude Sonnet 4.6?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Claude Sonnet 4.6 like any built-in tool.
How much does Claude Sonnet 4.6 cost in Claude Code?
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 Claude Code plan is separate.
Do I need an Anthropic account to use Claude Sonnet 4.6 in Claude Code?
No. Spiral runs Claude Sonnet 4.6 on its own Anthropic account. You sign in to Spiral once and never paste a key.
How long does it take to set up Claude Sonnet 4.6 in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Claude Sonnet 4.6 runs?
Claude Sonnet 4.6 runs in the background. Claude Code 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.
Start using Claude Sonnet 4.6 in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


