Give AI a calculation layer you can trust
Capital markets firms are putting AI — Claude, Copilot and internal models — in the hands of analysts, portfolio managers, risk teams and traders. But AI is probabilistic, while pricing and risk must be deterministic, repeatable and auditable. That gap means an AI agent can produce a number no one can verify or reproduce.
Numerix closes that gap with NxCore Analytics Services (NAS): a cloud-hosted analytics API that delivers deterministic pricing and risk across every asset class, giving AI a reproducible foundation to build on. Firms can put AI to work across the desk, trust the numbers, and prove exactly how each one was produced. It exposes Numerix's market-leading analytics through a financial-language API that both people and AI tools read natively, integrating cleanly into existing systems with no bespoke infrastructure to build or maintain.
A calculation foundation the whole firm can build AI on
NAS speaks the language of trading and risk — instruments, curves and sensitivities — so AI agents can consume it directly, with LLMs.txt docs and an OpenAPI schema for easy integration.
Through a Model Context Protocol (MCP) server, agents such as Claude can price instruments in natural language and get back deterministic, auditable results — pricing in the chat window without giving up rigor.
Agent identity, audit trails and permission scoping are built in, so every AI-driven calculation is controlled, logged and reproducible — acceleration your firm can sign off on.
Built for the whole firm, from CTO to trader
NAS serves the leaders accountable for governance and consistency, and the teams who use analytics every day — through one engine and one endpoint.
For portfolio managers, traders and quant developers
Get pricing, risk and scenario analysis in the flow of work — and build on it fast.
For front-office and quant-development teams, NAS delivers analytics through an interactive Python API, a REST API and natural-language access, so users can self-serve instead of queuing behind scarce specialists.
Use NAS to:
- Run sub-second pre-trade pricing, risk and scenario analysis in interactive sessions
- Access analytics in natural language through the MCP server (valuation, beta at launch)
- Build pricing and risk apps quickly with a financial-language API that LLMs write correct calls against
- Go from idea to working app in hours rather than sprints — with or without financial-engineering expertise
- Combine NAS outputs with your own market data, or use built-in reference and market data
- Reduce manual exports, rekeying and one-off model rework
For technology and risk leaders
Deploy AI across the firm without losing control, audit or consistency.
For CTOs, heads of technology and heads of risk, NAS provides a single calculation standard: every desk and every AI tool calls the same engine and gets the same numbers, with a full audit trail behind each result.
Use NAS to:
- Establish one calculation standard across every desk and book
- Govern AI access to pricing and risk with agent identity, audit trails and permission scoping
- Reproduce and defend any number on demand via the diagnostics endpoint
- Eliminate key-person risk and in-house library maintenance
- Remove infrastructure burden with a cloud-hosted, SOC 2-certified service
- Keep numbers consistent from pre-trade through end-of-day risk
Powered by 30 years of Numerix analytics
NAS runs on Numerix's market-standard analytics libraries — three decades of financial engineering as best-practice, configurable defaults. It delivers dealer-quality coverage across equities, credit, interest rates, FX, inflation, fixed income (including MBS/ABS), commodities, hybrids and crypto, all behind a single high-level API, with more on the roadmap.
Use built-in reference and market data or bring your own (tri-party Bloomberg and Refinitiv supported). Changes flow through robust CI/CD with nightly numerical regression, a Preview environment ahead of Production, and a backward-compatibility guarantee.
Frequently asked questions
What is NAS?
NxCore Analytics Services is a cloud-hosted analytics API that delivers deterministic pricing and risk analytics across every asset class. It gives capital-markets and insurance firms scalable, auditable analytics — and a reproducible calculation foundation that AI applications can safely build on.
Which asset classes does NAS cover? NAS provides dealer-quality cross-asset analytics across equities, credit, interest rates, FX, inflation, fixed income (including MBS/ABS), commodities, hybrids and crypto, spanning valuations, Greeks, P&L, market risk and counterparty credit risk including XVA.
How does NAS work with AI and agents?
NAS exposes a high-level, financial-language API that LLMs read natively, alongside LLMs.txt documentation and an OpenAPI schema. Agents such as Claude can call NAS through an MCP server to price instruments in natural language, or integrate through the NAS Python API and REST API using conventional patterns. At launch, MCP coverage is valuation-only and available in beta, with broader coverage on the roadmap.
Is NAS secure and proven?
Yes. NAS is SOC 2-certified, with end-to-end encryption in transit and at rest, zero-downtime upgrades and a 99.9%+ uptime SLA. It has run in production for over six years, with more than 60 deployments a year and named live clients available on request.
How is NAS different from building in-house or using a trading platform?
NAS integrates with your existing systems rather than requiring rip-and-replace, and Numerix maintains the engine so you avoid key-person risk and library upkeep. Unlike a black-box calculation, a diagnostics endpoint reproduces any result on demand — one engine and one endpoint across every desk, with a centralized audit trail.
How do I get access?
Contact your Numerix representative to confirm the right tier, request access, or schedule a walkthrough. A trial environment is available with no infrastructure setup required.