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

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: llama3.1:8b, gpt-4o-mini, claude-haiku-4-5-20251001 Example: llama3.1:8b
maxTokens	number	Optional	4096	Maximum tokens for the LLM response (1–32000) Example: 4096

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.

Request Examples

cURL — local Ollama (default, no API key)

terminalBash

TypeScript — OpenAI with schema

extractWithLlm.tsTypescript

Python — Anthropic

extract_with_llm.pyPython

Response Example

200 OK1.4s

{
  "success": true,
  "data": {
    "provider_used": "ollama",
    "model_used": "llama3.1:8b",
    "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

3 credits

3 credits per request

Flat 3 credits whether you use local Ollama, OpenAI, or Anthropic.

Tip: Use list_ollama_models first to discover which local models are available before sending an extraction.

Related Tools

list_ollama_models

Discover available local Ollama models

extract_structured

Schema-driven extraction with selector fallback (3 credits)

Ready to run LLM extractions on your own machine? Sign up for free and get 1,000 credits.