How to Use Claude Opus 4.5 in Perplexity
Claude Opus 4.5 suits difficult software engineering and detailed research. Its 200,000-token context window and maximum 64,000-token output give it room for large code reviews and substantial reports.
Prompts to try with Claude Opus 4.5 in Perplexity
Copy an example into Perplexity, or ask in your own words.
Use Claude Opus 4.5 to compare the research pasted above. Extract the passages that address the main question, then explain where the sources agree, conflict, or leave gaps.
Use Claude Opus 4.5 to turn the business results above into an eight-slide presentation outline. Give each slide a headline, supporting evidence, and speaker notes; flag claims that need more evidence.
Use Claude Opus 4.5 to investigate the inconsistent totals in the tables and formulas above. Show the calculations you can verify and list any missing values needed to resolve the discrepancy.
Use Claude Opus 4.5 to compare the three proposals above against our stated requirements. Cite supporting passages, explain the tradeoffs, and write a recommendation in no more than 600 words.
Use Claude Opus 4.5 to summarize the research above in French for a nontechnical audience. Preserve the numbers and source references, and explain specialized terms on first use.
How to set up Claude Opus 4.5 in Perplexity
Pick the way that suits you. Each takes about two minutes.
Use the Perplexity connector
- Add a remote connector
In Perplexity, open Plugins in the sidebar (or Customize › Connectors if you don't see Plugins yet). Choose Add custom › Add MCP connector, then Remote. Name it Spiral and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Select the Spiral card on the Plugins page to start sign-in. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Perplexity 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 4.5
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-4.5", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Perplexity finds Claude Opus 4.5 on Spiral, shows the price and runs it.
Claude Opus 4.5 providers and prices
Spiral runs Claude Opus 4.5 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 Perplexity for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top p | 0 to 1 | ||
| Max tokens | 1 to 64000 | 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 | ||
| Parallel tool calls | on or off |
Every API field of Claude Opus 4.5 is on its tool page: open its card above.
What can you do with Claude Opus 4.5 in Perplexity?
Claude Opus 4.5 can turn lengthy evidence into a research brief or a presentation draft. Give it the relevant material and ask for source passages alongside its conclusions.
Investigate bugs across components
Use Claude Opus 4.5 to trace a failure through related code, explain the cause, and propose a focused fix with a regression check.
Review substantial code changes
Ask Claude Opus 4.5 to examine a change for correctness, identify affected behavior, and rank findings by impact.
Plan a code migration
Have Claude Opus 4.5 map dependencies, divide a migration into testable steps, and define checks for preserving existing behavior.
Reconcile conflicting research
Give Claude Opus 4.5 source material and ask for an evidence table that separates agreement, contradictions, and unanswered questions.
Explain spreadsheet discrepancies
Ask Claude Opus 4.5 to examine supplied tables and formulas, trace inconsistent totals, and explain which assumptions need checking.
Draft an evidence-based presentation
Use Claude Opus 4.5 to turn research and business results into slide headlines, supporting evidence, and speaker notes.
Adapt research for another language
Ask Claude Opus 4.5 to summarize supplied findings in a named language while preserving technical terms, numbers, and source references.
More on Claude Opus 4.5 and Perplexity
Claude Opus 4.5 in other agents
Questions about Claude Opus 4.5 in Perplexity
Can Perplexity use Claude Opus 4.5?
Yes. Add Spiral to Perplexity as an MCP server, and Perplexity can find and run Claude Opus 4.5 like any built-in tool.
How much does Claude Opus 4.5 cost in Perplexity?
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 Perplexity plan is separate.
Do I need an Anthropic account to use Claude Opus 4.5 in Perplexity?
No. Spiral runs Claude Opus 4.5 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 4.5 in Perplexity?
About two minutes: add a remote connector, then sign in to Spiral and approve.
Does Perplexity wait while Claude Opus 4.5 runs?
Claude Opus 4.5 runs in the background. Perplexity starts the run, checks on it and gives you the text, json when it's ready.
What is Claude Opus 4.5 good at?
Difficult software engineering, deep research, and analysis involving spreadsheets or presentations are documented strengths. Try it for a bug that crosses several components or a report that must reconcile conflicting evidence.
How much context and output can Claude Opus 4.5 handle?
It has a 200,000-token context window and can generate up to 64,000 output tokens. Treat these as token limits rather than fixed page counts.
Does Claude Opus 4.5 generate images or video?
Its output is text. Use it to write code, reports, presentation copy, or production briefs.
What limitations should I plan around?
Anthropic documents a tendency to overengineer code, so specify the exact scope and ask for minimal changes. Its reliable knowledge cutoff is May 2025; supply current evidence for questions about later events.
How should I prompt Claude Opus 4.5 for document analysis?
Ask it to extract relevant passages before drawing conclusions. Request a source reference beside each conclusion so you can check the reasoning against the supplied material.
Start using Claude Opus 4.5 in Perplexity
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Perplexity:
set up https://spiral.ai/SKILL.md


