TF Quant Finance — Derivatives Pricing Library
Google's Apache-2.0 TensorFlow library for quantitative finance — GPU-accelerated options pricing, rate models, Monte Carlo simulation, and autodiff Greeks.
TF Quant Finance — High-Performance Derivatives Pricing Library
TF Quant Finance is Google's open-source TensorFlow-based library for quantitative finance. It provides GPU/TPU-accelerated implementations of mathematical finance models — Black-Scholes, Heston, SABR, HJM, Hull-White — for fast option pricing, risk sensitivities (Greeks), curve calibration, and Monte Carlo simulation at scale.
Key Features
- Option pricing: European, American, Asian, barrier, digital
- Rate models: Hull-White 1F/2F, HJM, LMM
- Volatility surface calibration (SABR, SVI)
- GPU-accelerated Monte Carlo simulation
- Automatic differentiation for Greeks via TensorFlow AD
- Numerical methods: PDE solvers, quadrature, root-finding
Quick Start
import tensorflow as tf
import tf_quant_finance as tff
# Black-Scholes European call price
price = tff.black_scholes.option_price(
volatilities=tf.constant([0.2]),
strikes=tf.constant([100.0]),
expiries=tf.constant([1.0]),
spots=tf.constant([100.0]),
discount_factors=tf.constant([0.95]),
)
print(price.numpy()) # e.g. [8.916]
npx ai-supply add tf-quant-finance-derivatives-pricing
Curated mirror of the open-source TF Quant Finance (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/tf-quant-finance-derivatives-pricing/check). Click a policy:
Consume TF Quant Finance — Derivatives Pricing Library programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/tf-quant-finance-derivatives-pricing
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/tf-quant-finance-derivatives-pricing/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add tf-quant-finance-derivatives-pricing
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/tf-quant-finance-derivatives-pricing/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "tf-quant-finance-derivatives-pricing" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.