Common questions

SPARKIT is an API-first research agent for evidence-heavy questions. You send a question over HTTP; an agent retrieves and synthesizes relevant sources, performs any analyses the question requires, and returns a Markdown report. When the question warrants it, the report includes inline citations and a structured list of sources.

SPARKIT is an API designed to be called from your own agent or application. It runs an asynchronous, multi-step research workflow and returns structured Markdown with citations. Other products offer changing combinations of chat, research, and API features, so SPARKIT only publishes benchmark comparisons against the exact systems and modes named in its methodology.

Plus is $50/month for 15 research queries. Pro is $100/month for 35 queries (most popular). Max is $300/month for 120 queries. Paid tiers are billed monthly on 12-month commitments that renew annually unless cancelled before the current term ends. Try-it is a one-time $10 purchase for 5 queries with no subscription. Enterprise is available for teams with custom support, custom agent design, or connections to proprietary data, email info@sparkit.science to scope an engagement.

Yes. Beyond the off-the-shelf research agent, SPARKIT works directly with teams on custom engagements — connecting the agent to proprietary databases, internal corpora, or paywalled sources; tuning prompts and tool sets for a specific domain; building bespoke evaluation harnesses; and designing institutional workflows where the agent is one component of a larger system. We also collaborate on applied research projects.

Median end-to-end time is approximately 110 seconds, depending on question complexity and how many sources the agent retrieves. Jobs run asynchronously, you get a job_id back immediately, then either poll GET /v1/research/{job_id} or pass a callback_url to receive a webhook when the report is ready.

When the question warrants literature evidence, claims in the returned Markdown report are followed by inline citations, and the response payload includes a structured `sources` array with title, URL, DOI, year, and citation count for each source. Not every question requires literature references, for purely computational or definitional questions, citations may not be included.

No. SPARKIT is an AI agent and, like any LLM-driven system, can be wrong: citations may be misattributed, sources may be summarized inaccurately, and conclusions can overstate what the literature supports. Always verify the cited sources before relying on outputs for clinical, regulatory, legal, or other high-stakes decisions.

Yes. 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.

The official Python SDK is on PyPI as `sparkit-science`. Install with `pip install sparkit-science` (Python 3.10+). Then mint an API key at app.sparkit.science/keys and call `client.research('your question')`.

No. SPARKIT does not use your research queries or returned reports to train models, and we do not opt customer content into provider model-training programs. To provide the service, SPARKIT sends questions and relevant context to Anthropic and, when fallback inference is needed, OpenAI. Derived search terms and source identifiers may also be sent to the search and scientific-data providers listed in our Privacy Policy. Provider-side security and abuse-monitoring retention is governed by each provider's API terms and the data controls available to SPARKIT.

Yes. Paid subscriptions are billed monthly during a 12-month commitment and automatically renew for another 12-month term unless you schedule cancellation before the current term ends. You can schedule cancellation at any time; service and monthly billing continue through your current commitment end date, then the subscription ends. Cancelling does not close your account. Try-it is a one-time purchase with no subscription.