Private beta · S&P 500 live

Financial data that's already AI-ready

Raw filings aren't model-ready. We ship earnings-call transcripts pre-embedded and signal-scored, plus a filing-change signal that flags the disclosure language companies quietly rewrite, all delivered to your RAG pipeline or warehouse without months of plumbing. We ship it done.

Get free API accessView docs →

250 free calls/mo · no credit card. Talk to sales for full coverage.

REST API: embeddings endpoint
curl https://api.vectorfinancials.com/v1/embeddings/AAPL \
  -H "X-API-Key: vf_a1b2c3d4_••••" \
  -G -d "fiscal_period=2024-Q3&limit=5"

# Returns: [{
#   ticker, fiscal_period, chunk_idx,
#   embedding[768], effective_ts, knowledge_ts
# }]

Browse the datasets

Embeddings

→

Earnings-call vectors across the S&P 500. See coverage and a sample ticker.

Signals

→

Quant Scores and market regime. See the fields and a sample ticker.

Filing Change Signal

→

Year-over-year narrative change on 10-K and 10-Q filings. Lexical vs semantic, point-in-time.

Not raw data. A finished product.

Embeddings and signals, normalized and scored for ML. You skip the scraping and the cleanup.

Embeddings for Financial RAG

Every earnings-call transcript, chunked per fiscal period and vectorized with Google gemini-embedding-2-preview (768-dimensional). SEC filing embeddings are in preview. A drop-in retrieval layer for financial Retrieval-Augmented Generation: citations come free because every vector maps back to ticker + fiscal_period + chunk_idx.

Derived Quant Signals

A composite score plus Piotroski F-score, Altman Z-score, Beneish M-score, Sloan accrual ratio, and an HMM market regime (bull/bear/sideways), updated weekly across the S&P 500 (beta). Delivered as Iceberg tables, ready for your factor stack and backtest. Every record is bitemporal: both effective_ts (when it was true) and knowledge_ts (when we learned it), so point-in-time backtests stay safe, with no lookahead bias and no data leakage.

Filing Change Signal

Companies edit their disclosures before they explain them. We read every new 10-K and 10-Q against the prior year and measure how far the language moved, lexically and semantically. The gap between the two, lex_sem_divergence, tells a real disclosure shift apart from a boilerplate reshuffle. Operationalizes the Lazy Prices anomaly. Point-in-time, weekly.

Native Iceberg Delivery

Data lives as Apache Iceberg tables on GCS, served via the Polaris catalog or shared as a bucket: the ready embeddings plus the raw transcript text. On Pro, query it in BigQuery (VECTOR_SEARCH) or Snowflake (preview), with no ETL and no replication.

Weekly pipeline: embeddings and signals refresh weekly as new transcripts become available upstream, and Iceberg tables are append-only, so your queries always see the latest snapshot.

Deliver to your warehouse — no ETL

REST API

JSON endpoints, every plan

Shared bucket

GCS bucket: embeddings + raw transcripts as Iceberg

BigQuery

Native VECTOR_SEARCH over shared embeddings

Snowflake

Polaris catalog + native VECTOR (preview)

Simple, transparent pricing

Start free. Upgrade when you need more tickers or warehouse delivery. See full pricing

Free

$0/forever

Evaluate VectorFin with the top 100 tickers. No credit card required.

Start for free

Starter

$100/per month

or $1,000 / year — 2 months free

For quant teams that need broad ticker coverage and bulk parquet delivery.

Get started
Most popular

Pro

$300/per month

or $3,000 / year — 2 months free

For hedge funds that need warehouse-native delivery and self-serve Iceberg access.

Get started

Enterprise

Custom/pricing

Dedicated infrastructure, SLAs, and white-glove onboarding.

Talk to sales

Stop building pipelines. Start building alpha.

Get your API key in minutes. 250 calls/mo and the top 100 tickers are free, no credit card required.

Get API access — freeTalk to sales →