extract_with_llm

AI-powered extraction that runs on a local Ollama model by default — no API key required and nothing leaves your machine. Optionally route to OpenAI or Anthropic when you need a hosted model. Give it a prompt (and optionally a JSON Schema) and get back structured data.

Use Cases

Local-First Extraction

Run extractions against Ollama on your own machine — zero LLM API costs and private by default.

Schema-Driven Data Lakes

Combine a prompt with a JSON Schema to populate typed rows for your warehouse or graph store.

Multi-Provider Failover

Start on local Ollama, fall back to OpenAI or Anthropic for higher-stakes pages by toggling one parameter.

Endpoint

POST/api/v1/tools/extract_with_llm

Auth Required

2 req/s on Free plan

3 credits

Parameters

Ollama is the default: Leave provider unset (or use "auto") and the tool runs on your local Ollama install — no LLM API key required. Set provider to "openai" or "anthropic" to use a hosted model instead.

Name	Type	Required	Default	Description
url	string	Optional	-	URL to fetch and extract from. Either url or content is required. Example: https://example.com/article/42
content	string	Optional	-	Raw text or HTML content to extract from. Either url or content is required. Example: "<html>...</html>"
prompt	string	Required	-	Natural-language instructions guiding the LLM extraction Example: Extract the headline, author, and three key takeaways
schema	object	Optional	-	Optional JSON Schema describing the data structure to extract Example: {"type":"object","properties":{"title":{"type":"string"}},"required":["title"]}
provider	string	Optional	auto	LLM provider: "ollama" (local, default), "openai", "anthropic", or "auto" Example: ollama
model	string	Optional	-	Model identifier. Defaults per provider: llama3.2, gpt-4o-mini, claude-haiku-4-5-20251001 Example: llama3.2
maxTokens	number	Optional	4096	Maximum tokens for the LLM response (1–32000) Example: 4096

Request Examples

cURL — local Ollama (default, no API key)

terminalBash

curl -X POST https://crawlforge.dev/api/v1/tools/extract_with_llm \
  -H "X-API-Key: cf_test_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/article/42",
    "prompt": "Extract the headline, author, and three key takeaways",
    "provider": "ollama"
  }'

TypeScript — OpenAI with schema

extractWithLlm.tsTypescript

const response = await fetch('https://crawlforge.dev/api/v1/tools/extract_with_llm', {
  method: 'POST',
  headers: {
    'X-API-Key': process.env.CRAWLFORGE_API_KEY!,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    url: 'https://example.com/product/123',
    prompt: 'Extract product name, price in USD, and stock status',
    provider: 'openai',
    model: 'gpt-4o-mini',
    schema: {
      type: 'object',
      properties: {
        title: { type: 'string' },
        price: { type: 'number' },
        in_stock: { type: 'boolean' },
      },
      required: ['title', 'price'],
    },
  }),
});

const data = await response.json();
if (data.success) {
  console.log(data.data.extracted);
  console.log('Tokens used:', data.data.tokens_used);
}

Python — Anthropic

extract_with_llm.pyPython

import requests, os

response = requests.post(
    'https://crawlforge.dev/api/v1/tools/extract_with_llm',
    headers={
        'X-API-Key': os.environ['CRAWLFORGE_API_KEY'],
        'Content-Type': 'application/json',
    },
    json={
        'url': 'https://example.com/article/42',
        'prompt': 'Extract headline, author, publish date (ISO 8601), and tags',
        'provider': 'anthropic',
        'model': 'claude-haiku-4-5-20251001',
        'schema': {
            'type': 'object',
            'properties': {
                'headline': {'type': 'string'},
                'author': {'type': 'string'},
                'published_at': {'type': 'string'},
                'tags': {'type': 'array'},
            },
            'required': ['headline'],
        },
    },
)

data = response.json()
if data['success']:
    print(data['data']['extracted'])

Response Example

200 OK1.4s

{
  "success": true,
  "data": {
    "provider_used": "ollama",
    "model_used": "llama3.2",
    "tokens_used": 842,
    "extracted": {
      "headline": "How Local LLMs Are Changing Data Pipelines",
      "author": "Jane Doe",
      "takeaways": [
        "Lower cost",
        "Better privacy",
        "Faster iteration"
      ]
    },
    "prompt_used": "Extract the headline, author, and three key takeaways"
  },
  "credits_used": 3,
  "credits_remaining": 997,
  "processing_time": 1420
}

Field Descriptions

data.provider_usedResolved provider — "ollama" when provider is "auto"

data.model_usedDefault model per provider unless you specify one

data.tokens_usedTokens consumed for this extraction

credits_usedFlat 3 credits regardless of provider

Credit Cost