Pricing

Three infrastructure tiers plus a lightweight weekly digest. Every tier is billed monthly via Paddle; cancel anytime.

Data Platform

$500 / month, up to $5,000 (enterprise)

Unified query layer across public market and regulatory data — the infrastructure for deterministic signal extraction and entity indexing. Coming soon at production scale.

Unified interface across SEC EDGAR, CFTC, GDELT, AIS, and other regulated sources
Deterministic feature computation (BOCPD, HMM regime detection, spectral analysis) — the core of our anomaly detection
Entity indexing and cross-document relationship resolution — same engine that powers Entity Graph
Enterprise: custom data sources, batch pipelines, dedicated infra — contact us

Coming soon — enterprise deployment in progress

Entity Graph

$300 / month, up to $2,000 (enterprise)

A deterministic, no-LLM pipeline that extracts entities and relationships from ingested documents — PDF, news, CSV, plain text — with every mention and link tracing back to the exact source sentence it came from. Cross-document co-occurrence — the same pair recurring across sources, not just one — is the signal.

Entity search — every mention and relationship cites its source document and sentence; confidence scores are deterministic (co-occurrence-based), not model output
Cross-document co-occurrence analytics — surfaces entities and relationships that recur across the ingested corpus
Graph export (adjacency list) and degree-centrality / hub analysis
Real production entity graph — paginated entities and links from the same store the system's own graph model trains on (ids, canonical names, types, confidence, link type); raw signal/observation values are not exposed
Enterprise: custom entity types, private document ingestion, on-prem option

GET /evidence/graph?q=nvidia GET /evidence/analytics?q=nvidia GET /evidence/graph/centrality?top=10 GET /api/v1/entity-graph/entities?type=&limit=100 GET /api/v1/entity-graph/entity?id=<id> GET /api/v1/entity-graph/links?link_type=&min_confidence= Header: X-Brief-Key: <your key>

Scheduler

$50 / month, up to $2,000 (enterprise)

Read-only visibility into the DAG-based execution engine that runs our own pipeline in production — run history, status, and timing per DAG.

List recent runs by DAG name, with status and timing
Inspect a specific run's node-level results

GET /api/v1/dag/runs?dag_name=daily_collection&limit=20 Header: X-Brief-Key: <your key>

Brief

$19 / month

Weekly positioning and flow anomaly digest built on deterministic z-scores over multi-year baselines and Bayesian online changepoint detection (BOCPD). No LLM, no predictions — just the math. The entry rung of metered API access.

Positioning extremes and flow anomalies detected via BOCPD over multi-year CFTC commitment-of-traders baselines (up to ~160 weekly observations), DeFi TVL series of 1,000+ points, and instrument volatility
Weekly digest delivered as markdown and JSON — includes entity IDs, flagged timestamps, z-scores, and raw signal values for reproducibility
Metered API access: same subscriber key as other tiers; usage tracked in your account

GET /brief GET /brief.json GET /brief.md POST /api/v1/rotate-key GET /api/v1/usage Header: X-Brief-Key: <your key>

Questions

Can I combine tiers? Yes — each tier is billed and gated independently by your subscriber key. Contact us for a bundled rate across two or more tiers.

What does "up to $X enterprise" mean? The listed price is the entry point. Larger universes, custom integrations, dedicated support, or on-prem deployment move you up within that tier's range — priced per engagement.

Is any of this LLM-generated? No. Every tier you're billed for runs on deterministic math (BOCPD, HMM, spectral, graph analytics) or auditable rule-based scoring — nothing here hallucinates a fact, and none of today's tiers depend on our graph model's output. That model is still in training; we'll only sell a prediction tier once it clears an independent, walk-forward backtest against a naive baseline.