Pricing

from $5.00 / 1,000 prompt processed and analyseds

Claude Prompt Actor – GEO - API + Web Search, Citations

Sends prompts to Claude via the Anthropic API (BYOK) with web search enabled, and returns the answer as text + markdown, the cited sources and aggregated domains.

Pricing

from $5.00 / 1,000 prompt processed and analyseds

Rating

0.0

(0)

Developer

Egon Maier

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Categories

SEO tools

Automation

Prompts

prompts

Required

Questions/prompts to send to Claude. Each prompt runs in its own independent conversation.

Type:array

Default:

[
  "What are the most popular Nike products?"
]

Anthropic API key (BYOK)

apiKey

Required

Your own Anthropic API key (starts with 'sk-ant-'). Get one at https://platform.claude.com/settings/keys (Create Key). Safe to enter: this is a secret field — Apify stores it encrypted, it is never shown in the run input, log or dataset, and it is only used to call the Anthropic API. Tokens are billed to your own Anthropic account (BYOK, no markup); you can revoke or rotate the key anytime in the Anthropic console.

Type:string

Model

model

Optional

Which Claude model to use. Opus 4.8 is the most capable (default); switch to Sonnet or Haiku for lower cost. Fable 5 is the strongest and most expensive tier.

Type:string

Default:claude-opus-4-8

Options:

claude-opus-4-8claude-sonnet-5claude-haiku-4-5claude-fable-5

Override system prompt

overrideSystemPrompt

Optional

Leave empty to use the Actor's built-in Claude.ai/Desktop-style system prompt (warm tone, Jan 2026 knowledge cutoff, minimal formatting, web-search-aware) — it is applied automatically, so you don't need to paste it here. Set this only to REPLACE that default with your own system prompt. The token {{CURRENT_DATE}} is replaced with today's date at runtime.

Type:string

Enable web search

webSearch

Optional

Let Claude use Anthropic's server-side web search tool to ground answers in current information and produce cited sources. Turn off for pure model-knowledge answers (no sources).

Type:boolean

Default:true

Max web searches per prompt

maxSearchUses

Optional

Upper bound on how many web searches Claude may run while answering one prompt. Lower = cheaper and faster; higher = more thorough. Only applies when web search is enabled.

Type:integer

Minimum:1

Maximum:20

Default:5

Extended thinking

extendedThinking

Optional

Enable adaptive extended thinking (Claude reasons before answering). Improves hard questions at the cost of extra tokens/latency. Ignored for Haiku 4.5 (not supported).

Type:boolean

Default:false

Max output tokens

maxTokens

Optional

Maximum length of Claude's answer (in tokens). The request is streamed, so large values are safe from timeouts.

Type:integer

Minimum:256

Maximum:64000

Default:8192

Max concurrency (parallel prompts)

maxConcurrency

Optional

How many prompts to send to the API in parallel. Higher = faster; bounded by your Anthropic rate limits. No extra memory needed (no browser).

Type:integer

Minimum:1

Maximum:20

Default:3

Max retries per prompt

maxRequestRetries

Optional

How often to retry a prompt on a transient API error (rate limit / 5xx / connection). Reported per item as 'attempts'. Refusals and invalid requests are not retried.

Type:integer

Minimum:0

Maximum:8

Default:2

AI Visibility / GEO Monitor

westerly_breaker/ai-visibility-geo-monitor

Measure whether Claude mentions your brand in a live web-search-grounded answer, with sentiment and cited sources.

Daniel Posztos

Claude API Actor – BYOK Anthropic Claude AI Proxy for Apify

hgservices/claude-api-actor

Call Anthropic's Claude API directly from any Apify Actor or automation workflow. This Actor is a lightweight, BYOK (Bring Your Own Key) proxy that lets you integrate Claude AI, including Opus, Sonnet, and Haiku, into your Apify scraping pipelines, data extraction workflows, and AI automation tasks

Harish Garg

5.0

Claude AI Web Automation

dtrungtin/claude-ai-web-automation

A real browser with Anthropic's Claude models to navigate any website and extract structured data — no CSS selectors or page-specific scraping code required.

Tin

Chatgpt Prompt Actor - GEO Analyse with Citation Data

automation_nerd/chatgpt-prompt-actor

This Actor automates interactions with ChatGPT by sending prompts and extracting responses. it opens the web interface, dismisses pop-ups, sends prompts, waits for responses (up to 2 minutes), and extracts generated results including citations for further use.

Egon Maier

5.0

YouTube Claude Mentions Tracker

ianymu/youtube-claude-mentions

Track YouTube videos mentioning Claude Code, Claude AI, claude.ai, or Anthropic Claude. Pulls metadata + transcript, surfaces the mention sentence, tags sentiment (positive/neutral/negative), and ranks results. Brand monitoring, competitor analysis, and tutorial discovery in one scheduled run.

Yanlong Mu

Tolena Web Researcher

tolena/tolena-web-researcher

AI-powered research agent that searches the web, analyzes multiple sources with Claude AI, and delivers structured research reports with full citations. Supports basic (3-5 sources) and deep (8-12 sources) research modes.

John Detmers

GitHub Issue → Claude Code Prompt Pack

ianymu/gh-issue-to-claude-prompts

gh-issue-to-claude-prompts is an Apify Actor that picks the top open issues from any GitHub repo and returns ready-to-paste Claude Code prompts enforcing a 6-step workflow: investigate, plan-approval, implement, test, verify, stop. One paste, one fix.

Yanlong Mu

🧠 RAG Web Browser — Web Content for AI & LLMs

nexgendata/rag-web-browser

Web browser for RAG pipelines and AI agents. Search Google, scrape top results, return clean Markdown. Feed your LLM with real-time web data. Works with Claude, GPT, LangChain, CrewAI. No API key needed.

NexGenData

Claude code

agentify/claude-code

Instant access to Claude Code - Anthropic's AI coding assistant running on Apify.

agentify

5.5K

4.1

GEO Prompt Bank - Curated AI Prompts by Industry

dltik/geo-prompt-bank

Solve the cold-start of GEO/AEO: pre-built libraries of high-intent prompts per industry (e-commerce, SaaS, fintech, healthcare, real estate). Run them against ChatGPT/Claude/Gemini to find where your brand should appear. Built to chain with GEO Visibility Score.