Pricing

from $20.00 / 1,000 results

Go to Apify Store

Fable Distiller

Try for free

Bundle the Claude Fable 5 system prompt and apply it to any LLM model via your own API key.

Pricing

from $20.00 / 1,000 results

Rating

0.0

(0)

Developer

Safwan Kazi

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Fable Distiller - Apify Actor

Bundle the Claude Fable 5 system prompt (3,825 lines) and apply it to any LLM model via your own API key.

How It Works

Select your provider (OpenAI, Anthropic, OpenRouter, or a custom OpenAI-compatible endpoint)
Enter your API key and choose a model
Provide your messages as a JSON array
The Actor prepends the entire Fable 5 system prompt and sends the request
The response is returned with token usage and metadata

Input

Field	Type	Required	Description
`provider`	select	Yes	`openai`, `anthropic`, `openrouter`, or `custom`
`model`	string	Yes	Model name/ID (e.g., `gpt-4o`, `claude-sonnet-4-20250514`)
`apiKey`	secret string	Yes	Your API key for the chosen provider
`messages`	JSON array	Yes	`[{"role": "user", "content": "..."}]`
`apiBaseUrl`	string	No	Custom base URL (required for `custom` provider)
`maxTokens`	integer	No (default: 4096)	Max response tokens
`temperature`	number	No (default: 1.0)	Response temperature (0.0–2.0)

Output

Success:

{
  "success": true,
  "provider": "openai",
  "model": "gpt-4o",
  "content": "...",
  "usage": { "inputTokens": 1000, "outputTokens": 500, "totalTokens": 1500 },
  "finishReason": "stop",
  "id": "chatcmpl-xxx"
}

Error:

{
  "success": false,
  "provider": "openai",
  "model": "gpt-4o",
  "error": { "type": "auth_error", "message": "Invalid API key", "statusCode": 401 }
}

Development

# Copy the Fable 5 prompt into this directory
cp ../../claude-fable-5.md ./claude-fable-5.md

# Install dependencies
npm install

# Type-check
npm run typecheck

# Run tests
npm test

# Build
npm run build

# Run locally (requires a sample INPUT.json in the actor directory)
npx apify run

Deployment

npx apify login
npx apify push

Distiller Reviews Scraper

getdataforme/distiller-reviews-scraper

The Distiller Reviews Scraper efficiently extracts detailed reviews and ratings from the Distiller website, ideal for market research and trend analysis....

GetDataForMe

Distiller Discovery Scraper

getdataforme/distiller-discovery-scraper

The Distiller Discovery Scraper extracts detailed spirit information from the Distiller website, ideal for connoisseurs and analysts. It features customizable searches, efficient data handling, proxy support, and reliable performance. Use it for market research, competitive intelligence, and more.

GetDataForMe

Llm Prompt Optimizer API

vivid_astronaut/llm-prompt-optimizer

Fabio Suizu

Distiller Scraper — Spirits Ratings & Reviews

crawlerbros/distiller-scraper

Scrape Distiller (distiller.com) for spirits data. Search for whisky, bourbon, gin, rum, vodka, tequila, and more. Get Distiller scores, community ratings, ABV, tasting notes, flavor profiles, price history, and detailed metadata.

Crawler Bros

Humble Bundle Scraper

crawlerbros/humble-bundle-scraper

Scrape Humble Bundle with browse current game, book, and software bundles; search the store; or fetch any bundle/product URL. Extracts tier prices, items, end dates, and partner details without any login.

Crawler Bros

Humble Bundle Scraper

crawlergang/humble-bundle-scraper

Crawler Gang

5.0

Video → LLM Analyzer

grizzlygriff/video-llm-analyzer

Drop a video, give it a prompt, and have an LLM analyze it. Results land in your Notion page so Claude Code can pick up where you left off. Uses Apify MCP Connectors to write to Notion on your behalf — no Notion API key required.

Griffin Trent

4.0

LLM Prompt Response

jakubsuchy/llm-prompt-response

Submits prompts to LLM providers (ChatGPT, Perplexity) via Camoufox anti-detect browser and captures structured responses with sources.

Jakub Suchy

5.0

Multi-Model LLM Compare - GPT, Claude, Gemini & Llama

seemuapps/multi-model-llm-compare

Run one prompt across many language models at once and get every response side by side, with token counts, cost, and latency per model in a single dataset.