Frequently Asked Questions

Below is a list of common questions from users. For any additional questions, please email commercial@kensho.com.

Solution Overview

What makes the API LLM-ready?

The Kensho LLM-Ready API is specifically designed for seamless interaction with large language models (LLMs). Unlike typical APIs, it is optimized for LLMs by offering a simplified structure that supports function calling patterns. Kensho provides a Python library (kFinance) that streamlines everything from authentication to LLM integrations shown in the Playground Notebooks (opens in a new tab), making it easy for users to start implementing their LLM solutions. The API is compatible with user-built clients or direct LLM function calls.

How Does It Work?

The LLM-ready API can be accessed through a Python client or MCP (Model Context Protocol) server, enabling large language models to interact with the API. API endpoints connect directly to S&P Global's Xpressfeed database, allowing for financial data retrieval and analytics generation. Every query is translated into traceable, reproducible function calls or code.

Does S&P Global provide an LLM as part of the solution? / What Large Language Model is included in the LLM-ready API service?

There are no AI models used or provided by Kensho and S&P Global as part of the LLM-ready API service. This service is a data retrieval tool purpose-built to work seamlessly with LLMs, but it uses no models itself. Any use of AI models occurs on the customer side, and customers are welcome to use the model of their choosing or no model at all.

General Information

What is the purpose of this API? What can I do with it?

The LLM-ready API serves as a simplified access method for S&P Global datasets. The LLM-ready API is purpose-built in such a way that both humans and LLMs can easily understand it.

We created a Python library called "kFinance" that supports function calling. Included in the library are the tools needed by an LLM to successfully retrieve data. Customers making use of this solution will be required to “bring their own” LLM(s), orchestration layer, and user interface (UI); or leverage third-party platforms.

The Kensho LLM-ready API is intended to help end users such as investment bankers, equity analysts, consultants, and other professionals who frequently need to retrieve financial data such as financial statement line items, security identifiers, and market data to create pitch books, research reports, or market positioning presentations.

What types of questions or workflows does this solution support?

The LLM-ready API is designed for company-specific research and analysis. Queries require specific company names to effectively use the API. The solution excels at delivering detailed data about particular companies and performing comparative analyses across multiple companies. For broad industry research rather than company-specific analysis, other S&P Global solutions may be better suited.

Company Financials: Answer questions about company financials, such as: "Compare the gross margins and EBITDA trends for Amazon, Google, and Meta over the past 5 years" or "Summarize the key takeaways from Apple's latest earnings call, focusing on guidance and capital allocation."

Financial Research: Access crucial financial data for company and market research tasks such as creating pitch books, research reports, and market positioning presentations.

Investment Banking Analysis: Develop due-diligence briefs in a fraction of the normal time—pulling key financials, generating comps tables, benchmarking peers, and flagging risks in minutes.

What are other use cases beyond LLMs and GenAI?

While designed with LLMs in mind, the solution can also be used by Python developers for general engineering purposes or as a software development kit (SDK) for S&P Global datasets.

What's the difference between the Kensho LLM-ready API and kFinance?

The Kensho LLM-ready API consists of a REST API and a Python client. The Kensho LLM-ready API is the distribution channel and display name for the tile on S&P Global Marketplace. kFinance is the name for the Python client included as part of the Kensho LLM-ready API product. The kFinance name appears on Python Package Index and is referenced in the developer documentation.

Where can I find the latest updates and announcements?

All product updates will be documented in our public repository Releases (opens in a new tab) and S&P Global Marketplace (opens in a new tab).

Technical Details

What are the Setup and Authentication Requirements?

API access requires web browser login through Kensho's authentication system (Okta). Upon signing up for a trial or subscription, an email invitation will be sent to activate the account.

What large language models does the LLM-ready API support?

We have designed the API to support a variety of leading models from vendors such as OpenAI, Google, Anthropic, and more, but it is compatible with any LLM.

Is an LLM required?

The LLM-ready API and its Python library (kensho_finance.kfinance) can be used with or without an LLM. Although these tools are designed with LLMs in mind, the API and Python library are straightforward and are useful on their own.

Which languages are supported?

Since the LLM Ready API leverages the intelligence of Large Language Models (LLMs), you can use any language that the LLM you choose supports. Leading models such as OpenAI's GPT will perform well for all major written languages, programming and otherwise.

Data & Accuracy

What data is available via LLM-ready API?

Current subscription includes:

New datasets are regularly added. Check the Kensho LLM-ready API Marketplace (opens in a new tab) page for the latest updates.

How often is the data included in the LLM-ready API service updated?

The LLM-ready API serves as a distribution channel for S&P Global Data feeds and therefore report update frequency varies depending on when underlying datasets are updated; this could be daily, weekly, and monthly. For more information on the timeliness of individual S&P Global datasets, please refer to S&P Global Marketplace's (opens in a new tab) tiles and support guides.

How can Data Accuracy be Verified?

For LLM integrations, accuracy depends on the specific model and architecture used. The API itself is deterministic, meaning it returns consistent results, but users can view and audit the Python code generated by the LLM. This allows verification of which steps were taken to retrieve the answer directly from the S&P Global database.

How can other datasets be made LLM-ready?

Optimizing data for LLMs is a major focus of Kensho and S&P Global. For more information about specific datasets or to explore collaboration, please contact commercial@kensho.com.

What identifiers should I use for best results?

For the most accurate results when querying company data, we recommend using these identifier types in the following order:

CapIQ Company ID (S&P Capital IQ identifier e.g. "C_<ciq_identifier>")
Ticker symbol (for current public companies e.g., "AAPL", "MSFT")
ISIN (International Securities Identification Number)
CUSIP (Committee on Uniform Securities Identification Procedures number)
Legal company name (e.g., "Apple Inc.", "Microsoft Corporation")

Using these specific identifiers will help ensure you get the most accurate and relevant data from the API.

Privacy and Security

What privacy and security measures are in place?

S&P Global does not receive or see natural language questions—only the code used to make API calls. This approach limits exposure of confidential information. For additional information about data privacy, please see the S&P Global Data Processing Policy.

Does Kensho have visibility into prompts or LLM applications?

No. The LLM-ready API is a data retrieval tool designed to be deployed in customer LLM applications or third-party applications. Kensho and S&P Global have no way to track users' prompts or other material non-public information (MNPI).

What security protocols protect data?

HTTPS encryption is used (with TLS 1.2 or later) for all data in transit. All API calls are authenticated via standard authentication protocols. Queries remain secure on the client side—only data requests are received, not original questions.

How do I get access?

To get started with a trial or explore purchasing, contact us at market.intelligence@spglobal.com.