How to Use Grok 4.6 in Claude Code
Grok 4.6 suits extended coding tasks, research synthesis, and turning product ideas into working applications. Compared with Grok 4.5, the maker reports stronger first passes on visual and interactive projects.
Prompts to try with Grok 4.6 in Claude Code
Copy an example into Claude Code, or ask in your own words.
Use Grok 4.6 with high reasoning effort to investigate the failing checkout test in this project. Reproduce the failure, fix its cause, and report the checks you ran.
Use Grok 4.6 to build a working appointment scheduler in this project. Include weekly navigation, appointment editing, and empty states. Check each interaction before finishing.
Use Grok 4.6 with extra-high reasoning effort to trace how permissions move through this codebase. Propose a refactor that preserves behavior and explain the tests needed.
Use Grok 4.6 to compare this project's implementation with its requirements. List gaps by user impact, implement the highest-impact gap, and verify the result.
Use Grok 4.6 to investigate the slow report-generation path in this project. Measure a baseline, test one focused improvement, and report the before-and-after results.
How to set up Grok 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 Grok 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": "openrouter", "model": "x-ai/grok-4.6", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Claude Code finds Grok 4.6 on Spiral, shows the price and runs it.
Grok 4.6 providers and prices
Spiral runs Grok 4.6 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 per 1M output tokens.
Settings you can ask for
Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | a number up to 1 | ||
| Max tokens | 1 to 450000 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Reasoning effort | low, medium, high, or xhigh | high | How much the model reasons. |
Every API field of SpaceXAI: Grok 4.6 is on its tool page: open its card above.
What can you do with Grok 4.6 in Claude Code?
Turn a product brief or difficult software issue into a concrete implementation with Grok 4.6. Give the agent acceptance criteria so it can inspect the project, make changes, and check its work.
Resolve a codebase issue
Have Grok 4.6 investigate a reported bug, propose a focused patch, and check the result against the original reproduction.
Build an interactive prototype
Give Grok 4.6 a product brief with concrete interactions and acceptance criteria, then iterate on a working first version.
Prepare a research brief
Ask Grok 4.6 to synthesize supplied evidence into findings, disagreements, and questions that need further investigation.
Analyze business data
Use Grok 4.6 to investigate changes in a data table and draft an explanation that separates observations from hypotheses.
Draft a decision memo
Turn requirements, constraints, and competing proposals into a recommendation with explicit tradeoffs and supporting evidence.
Interpret a visual reference
Ask Grok 4.6 to describe a supplied interface image and turn its visible interactions into an implementation brief.
Extract structured findings
Convert supplied text into consistently organized records for review, with missing information explicitly marked.
More on Grok 4.6 and Claude Code
Overview
Grok 4.6 in other agents
More Claude Code guides
Questions about Grok 4.6 in Claude Code
Can Claude Code use Grok 4.6?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Grok 4.6 like any built-in tool.
How much does Grok 4.6 cost in Claude Code?
Up to $0.03204 per run at the default inputs. $2.60 per 1M input tokens, $7.80 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 OpenRouter account to use Grok 4.6 in Claude Code?
No. Spiral runs Grok 4.6 on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Grok 4.6 in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Grok 4.6 runs?
Grok 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 Grok 4.6 best suited to?
Grok 4.6 is designed for difficult coding and knowledge-work tasks that require several steps and tool use. Practical examples include investigating a software issue, analyzing information, and developing a working application.
How much context can Grok 4.6 handle?
The maker documents a 500,000-token context window. It also lists no separate text output limit; that statement does not promise an unlimited response in a single request.
Can Grok 4.6 create images?
Grok 4.6 accepts images for analysis but produces text. Its visual-work strengths include writing application code and interpreting visual references.
When should I increase reasoning effort?
Increase effort for difficult analysis, debugging, or tasks with several dependent decisions. Extra-high effort provides deeper reasoning with higher latency, so reserve it for work where that tradeoff helps.
How should I prompt Grok 4.6?
State the task, constraints, and required output directly. For example, request a decision memo with a recommendation, supporting evidence, unresolved questions, and a clear word limit.
Start using Grok 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


