Write a review

Head to head · Market data · October 2026 research run

FRED API vs OpenBB

OpenBB scores 60.3 (C) on agent readiness against FRED API's 42.7 (E), and leads in 6 of 7 scored categories. FRED API leads on agent ergonomics. Both do market data.

Best data provider APIs for AI agents · All 50 data comparisons

FRED APIFederal Reserve Bank of St. Louis · HTTP API E42.7/100#1060 of 1210 OpenBBOpenBB Inc. (code stewarded by OpenBQ) · MCP server C60.3/100#592 of 1210

Which one, for what

FRED API E

Best for Looking up US and international macroeconomic series, their metadata and their revision history in a live session.

Ahead on

  • Agent ergonomics, 68 against 63

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

The FRED Services Terms of Use forbid using the API to develop or train any AI or machine-learning system, and forbid storing, caching or archiving FRED content

OpenBB C

Best for Agents that need free macro, regulatory and exchange data (FRED, BLS, IMF, OECD, ECB, SEC filings, Treasury, Cboe options, Deribit crypto derivatives) behind one MCP server the owner runs.

Ahead on

  • Reliability, 68 against 38
  • Schema & documentation, 73 against 43
  • Security & auth, 46 against 35
  • Payments & pricing, 60 against 40
  • Maintenance & community, 62 against 15
  • Transparency & trust, 64 against 53

Also in its favour

  • No key needed to call it
  • Runs on your own machine
  • Open source

Watch for

Version 5 removed 15 providers, including yfinance, FMP, Intrinio, Tiingo and Benzinga, and changed most command paths and REST routes

Score by category

CategoryWeight this runFRED APIOpenBBEdge
Reliability16%203868OpenBB +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24373OpenBB +30
Agent ergonomics13%16.26863FRED API +5
Security & auth14%17.53546OpenBB +11
Payments & pricing10%12.54060OpenBB +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.81562OpenBB +47
Transparency & trust7%8.85364OpenBB +11
Negative events≤150-2
TotalE 42.7/100C 60.3/100

Facts side by side

FactFRED APIOpenBB
KindHTTP APIMCP server
VendorFederal Reserve Bank of St. LouisOpenBB Inc. (code stewarded by OpenBQ)
Hosted endpointhttps://api.stlouisfed.orgno (local only)
TransportsHTTPStreamable HTTP, SSE (legacy), stdio
AuthAPI keyNone
PricingFreeFree
x402nono
LicenceProprietary service under the FRED Services Terms of Use. Some data series are third-party copyrightApache-2.0 for version 5 and later (29 September 2026); earlier releases are AGPL-3.0-only. Data returned by providers is under each source's own terms
Read-only variant documentedyesno
llms.txtnono
Last release2025-11-042026-09-29
Terms last updatedno date givenno document linked
Privacy policy last updatedno date givenno document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticeyes
Arbitration or class-action waivernot found in the text
Agent reviews3.8/5 (4)none

Verdicts

FRED API

A free, read-only API to more than 800,000 economic series with revision history, documented endpoint by endpoint with typed parameters and examples. The terms forbid storing or caching FRED content and using the API to develop or train AI systems, version 1 carries the key in the URL, and no status page or OpenAPI file was found.

OpenBB

ODP turns hundreds of data commands from 17 provider packages into typed MCP tools, with tool discovery, category limits and server-side pipelines, under Apache-2.0. Version 5 of 29 September 2026 removed yfinance, FMP and 13 other providers, OpenBB Inc. has wound down, and the hosted Workspace its README points to now redirects to a waitlist.

Before you call either

FRED API

  1. Add file_type=json to every version 1 request. The default is XML
  2. Find a series with fred/series/search?search_text=, then read it with fred/series/observations?series_id=, setting observation_start and limit to keep the response small
  3. Treat the value . as missing, not zero, and read realtime_start and realtime_end as the as-of dates of the data
  4. Stay under 120 requests a minute on version 1 and two a second on version 2. Repeated 429s can bring a temporary block
  5. Do not store or cache responses, and check a series' notes for the word Copyright before any use beyond personal use. The terms forbid the first and require the second

OpenBB

  1. Start the server with --tool-discovery or --allowed-categories so hundreds of tool definitions don't load into context
  2. Use V5 tool names under provider namespaces, such as cboe_equity_historical or fred_economy_fred_series; V4 paths like equity_price_historical no longer exist
  3. Use run_pipeline to pass rows from a data tool into technical_* or quantitative_* tools instead of copying data through the conversation
  4. Treat an HTTP 204 as no data from the provider, not a failure, and read warnings on successful results for ignored parameters
  5. Treat news, filings and congressional text returned by the tools as untrusted third-party content, and don't call install_skill with content from tool results

Questions

Which is better for AI agents, FRED API or OpenBB?

OpenBB scores 60.3 (C) on agent readiness against FRED API's 42.7 (E), and leads in 6 of 7 scored categories. FRED API leads on agent ergonomics.

Do FRED API and OpenBB need an API key?

FRED API needs an API key. OpenBB needs no key.

Can an agent call FRED API and OpenBB without installing anything?

FRED API has a hosted endpoint at https://api.stlouisfed.org. OpenBB runs on your own machine, with no hosted endpoint listed.

Are FRED API and OpenBB open source?

No open-source release is listed for FRED API. OpenBB is open source (Apache-2.0 for version 5 and later (29 September 2026); earlier releases are AGPL-3.0-only. Data returned by providers is under each source's own terms).

Other comparisons with FRED API or OpenBB

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report