Today SPARKIT goes live: a scientific research agent in an API.
One call deploys an agent that retrieves and synthesizes the relevant literature, performs any analyses the question requires, and returns a Markdown report. On HLE-Gold, the gold-standard subset of Humanity's Last Exam, SPARKIT scores 53.0%, compared to 34.9% for both direct GPT-5.5 and Claude Opus 4.8.
The shape of the API is intentionally tiny:
SPARKITfrom sparkit_science import SparkitClient
client = SparkitClient(api_key="sk_sparkit_...")
report = client.research(
"What is the role of BRCA1 in homologous recombination?"
)
print(report)
Get an API key at app.sparkit.science/signup. Pricing is on /pricing, start with Try-it for $10 and 5 queries.
We'll post deeper writeups, benchmark updates, and engineering notes here. Star the GitHub org for release notifications.
A tighter pre-flight on every research query rolled out this week. Most users see no change. If a query is rejected, the API returns a structured error synchronously, your quota is not consumed, and no job row is created.
Read post →Perplexity, ChatGPT Deep Research, Gemini Deep Research, Claude Research, Elicit, SPARKIT — the deep-research category has converged on the basics. The remaining differences are about audience, deployment surface, and how each tool treats citations. A map of who builds what for whom, and where SPARKIT fits.
Read post →Drop a five-gene hereditary-cancer panel into SPARKIT and get back the unifying syndrome, lifetime cancer risks, mechanism, and the current surveillance guideline — every claim cited and pulled from primary sources, not from the model's training memory.
Read post →