lightningrod-ai 0.2.0

Python SDK for dataset generation on LightningRod platform ⚡

Lightning Rod Python SDK

Foresight returns a calibrated probability for any question about the future through an OpenAI-compatible API.

Trusted for high-stakes predictions by Numinous, Shore Capital Partners, Awardable, ERIS Marketplace, and others. Foresight processes billions of tokens and serves 100k+ inference requests every day.

Documentation · Get an API key · Research paper

⚡ Better AI Predictions

Foresight is served behind an OpenAI-compatible endpoint, so any OpenAI client works — just point base_url at Lightning Rod.

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.lightningrod.ai/v1/openai",
)

completion = client.chat.completions.create(
    model="foresight-v4",
    messages=[
        {"role": "user", "content": "Will the Fed cut rates at its next meeting?"},
    ],
    extra_body={"research": True}, # Auto research the most relevant prediction context
)

print(completion.choices[0].message.content)

See the forecasting guides for how to write good forecasting prompts.

Prefer an SDK helper?

lr.predict() wraps the same API and parses the structured answer for you:

pip install lightningrod-ai

import lightningrod as lr

client = lr.LightningRod(api_key="your-api-key")
result = client.predict(
    "Will the Fed cut rates by 25bp in March 2026?",
    answer_type="binary",
    research=True,
)
print(result.binary.probability)  # e.g. 0.62

🏗️ Train an expert on your domain

Need a model tuned to your domain? Our platform turns raw sources into labeled datasets and fine-tuned models. Read the Future-as-Label paper or view public models and datasets on Hugging Face.

📅 Book a call with us

📚 Learn more

• Documentation — quickstart, guides, recipes, and the REST API reference
• Example notebooks — forecasting, dataset generation, training, and evaluation (runnable in Colab)
• SDK API reference — every class and method in this repo