API documentation

Get started

Send a scientific question to /v1/research; poll or webhook for the result; receive a Markdown report.

Installation

The official Python SDK is published on PyPI as `sparkit-science`. Install it with pip (Python 3.10+).

bash

pip install sparkit-science

View on PyPI

Quick start

python

from sparkit_science import SparkitClient

# Mint your API key at app.sparkit.science/keys
client = SparkitClient(api_key="sk_sparkit_YOUR_API_KEY")

response = client.research(
    "What is the role of BRCA1 in homologous recombination?"
)
print(response)

Delivery

Jobs run async. Pass a callback_url to receive a webhook on completion, or poll GET /v1/research/{job_id}. Median end-to-end is ~2 minutes.

Limitations

SPARKIT is an AI agent. Like any LLM-driven system, it can be wrong: citations may be misattributed, sources may be summarized inaccurately, and conclusions can overstate what the underlying literature supports. Always verify the cited sources before relying on outputs for clinical, regulatory, legal, or other high-stakes decisions.

Safety

Queries are screened by a safety policy. Requests that solicit dual-use research of concern (e.g., synthesis of dangerous pathogens or chemical weapons), unverified clinical advice, or other prohibited content are refused with a `safety_blocked` error.