How to Use Claude Opus 5 in Grok
Claude Opus 5 suits difficult debugging, large refactors, and tasks that span many steps. Compared with Claude Opus 4.8, its coding improvements are most useful for complex changes across multiple files.
Prompts to try with Claude Opus 5 in Grok
Copy an example into Grok, or ask in your own words.
Use Claude Opus 5 to compare the reports above. Identify three disagreements, cite supporting passages, and keep the answer under 300 words.
Use Claude Opus 5 to explain the formulas needed to connect monthly revenue, expenses, and cash balance across three spreadsheet sheets.
Use Claude Opus 5 to analyze the account-health figures above. Rank the five highest risks and explain each using the supplied evidence.
Use Claude Opus 5 to diagnose the bug from the code and error trace above. Explain the cause and propose a focused correction.
Use Claude Opus 5 with high reasoning effort to compare these architecture proposals. Recommend one in 200 words and state the deciding tradeoff.
How to set up Claude Opus 5 in Grok
Pick the way that suits you. Each takes about two minutes.
Use the Grok connector
- Add a custom connector
In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.
- Check that it is connected
Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.
Use the Spiral skill
- Send Grok 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 Opus 5
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-opus-5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Grok finds Claude Opus 5 on Spiral, shows the price and runs it.
Claude Opus 5 providers and prices
Spiral runs Claude Opus 5 through Anthropic. Open a card for today's price, with every fee included.
Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens.
Settings you can ask for
Ask Grok for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| 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). | |
| Reasoning effort | low, medium, high, xhigh, or max | high | How much the model reasons. |
| Parallel tool calls | on or off |
Every API field of Claude Opus 5 is on its tool page: open its card above.
What can you do with Claude Opus 5 in Grok?
Claude Opus 5 can turn extensive source material into comparisons and practical recommendations. Set a clear question and answer length to keep the discussion useful.
Fix bugs that survive an initial patch
Use Claude Opus 5 to trace a failure to its cause and address related edge cases.
Refactor code across multiple files
Use Claude Opus 5 for coordinated changes across modules while preserving the behavior you specify.
Implement a complete feature
Give Claude Opus 5 the behavior, constraints, and acceptance criteria for a feature spanning several parts of an application.
Compare lengthy reports
Use Claude Opus 5 to compare supplied reports, surface disagreements, and link conclusions to supporting passages.
Develop spreadsheet formulas
Ask Claude Opus 5 to design formulas across related sheets and explain their assumptions.
Review account health
Use Claude Opus 5 to turn account-health data into a prioritized risk summary and suggested next actions.
More on Claude Opus 5 and Grok
Overview
Claude Opus 5 in other agents
Questions about Claude Opus 5 in Grok
Can Grok use Claude Opus 5?
Yes. Add Spiral to Grok as an MCP server, and Grok can find and run Claude Opus 5 like any built-in tool.
How much does Claude Opus 5 cost in Grok?
Up to $0.133575 per run at the default inputs. $6.50 per 1M input tokens, $0.65 per 1M cached input tokens, $8.125 per 1M cache write tokens, $13.00 per 1M 1-hour cache write tokens, $32.50 per 1M output tokens; for a prompt above 200,000 tokens, $13.00 per 1M input tokens, $1.30 per 1M cached input tokens, $16.25 per 1M cache write tokens, $26.00 per 1M 1-hour cache write tokens, $48.75 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Grok plan is separate.
Do I need an Anthropic account to use Claude Opus 5 in Grok?
No. Spiral runs Claude Opus 5 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 Opus 5 in Grok?
About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.
Does Grok wait while Claude Opus 5 runs?
Claude Opus 5 runs in the background. Grok starts the run, checks on it and gives you the text, json when it's ready.
How much text can Claude Opus 5 handle?
Its context window holds up to 1 million tokens, and its standard maximum output is 128,000 tokens. These are token limits, so avoid treating them as fixed word or page counts.
Which reasoning effort should I use?
Start with high. Test xhigh on difficult coding or extended agent tasks, and compare low or medium on simpler work where your evaluations show acceptable results.
How do I get shorter answers?
Give Claude Opus 5 a concrete length target, such as 150 words or five bullets. Changing reasoning effort does not reliably shorten the visible answer.
How do I keep Claude Opus 5 focused on a small task?
State the exact deliverable and the boundary of the work. For example, ask it to fix one parsing bug while preserving the public interface.
Can Claude Opus 5 give incorrect answers?
Yes. For document analysis, ask for supporting passages and let it say when the supplied material does not establish an answer.
Start using Claude Opus 5 in Grok
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Grok:
set up https://spiral.ai/SKILL.md


