{
  "data": {
    "a": {
      "slug": "databento",
      "name": "Databento",
      "vendor": "Databento, Inc.",
      "vendorUrl": "https://databento.com",
      "kind": "http-api",
      "category": "market-data",
      "summary": "Databento is a market data platform with historical and live tick, order book and bar data for US and European equities, futures, options and indices, through HTTP and streaming APIs with Python, C++ and Rust clients.",
      "url": "https://www.anchorterminal.com/tools/databento",
      "markdownUrl": "https://www.anchorterminal.com/tools/databento.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/databento.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/databento.json",
      "dns": "databento.grade.anchorterminal.com",
      "repo": "https://github.com/databento/databento-python",
      "license": "Apache-2.0 (clients)",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://hist.databento.com",
      "packages": [
        {
          "registry": "pypi",
          "name": "databento"
        }
      ],
      "auth": "api-key",
      "authNotes": "API key (32 characters starting `db-`) created in the portal, up to 100 per account with unique names, rotated or deleted from the portal, and sent as the username in HTTP Basic auth (`-u $KEY:`). Team members can be given per-member permissions. The vendor revokes keys it finds published. No query-string option.",
      "pricing": "usage",
      "pricingNotes": "Historical data is metered per GB of uncompressed binary data at rates per dataset in the portal catalogue, with no subscription; batch jobs are billed once and streams per byte sent. New users get $125 of credits valid six months, one set per team, for historical data or the first month of a plan. Live data needs a plan, Standard at $199 a month (no licence fees), Plus $1,750 and Unlimited $4,500 a month in licence fees on annual contracts by sales. Metadata, symbology and account calls are free.",
      "priceSummary": "$199 / mo",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the docs, llms.txt, pricing page or release notes (checked 2026-11-03).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 309,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-03"
      },
      "docsUrl": "https://databento.com/docs/",
      "llmsTxt": "https://databento.com/docs/llms.txt",
      "capabilities": [
        "market.prices",
        "market.history",
        "market.indices",
        "data.markets"
      ],
      "tags": [
        "official",
        "hosted",
        "usage",
        "usage-priced",
        "free-tier",
        "llms-txt",
        "status-page",
        "pre-1.0",
        "python",
        "rust",
        "closed-source"
      ],
      "lastRelease": "2026-10-28",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 60.3,
        "grade": "C",
        "agentReady": false,
        "rank": 592,
        "ranked": true,
        "rankOf": 1349,
        "categoryRank": 4,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 80,
          "maintenance": 84,
          "payments": 22,
          "reliability": 50,
          "schema": 75,
          "security": 61,
          "transparency": 49
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-03"
        },
        "negative": 0,
        "verdict": "Exchange-level tick and order book data metered per GB, with published per-IP rate limits, Retry-After on 429, dated release notes and clients in three languages. The HTTP API is still at major version 0, the status page lists two critical and several major incidents in 90 days, there is no OpenAPI document, and the legal pages were unreadable.",
        "bestFor": "An agent that needs exchange-level trades, quotes, order book and bar data for US and European futures, options and equities, or corporate actions and a security master, and can budget per GB.",
        "strengths": [
          "Per-IP rate limits published with numbers, 429 with Retry-After, and a documented error format with a code, a message and a docs link",
          "`metadata.get_cost` quotes a request before it is billed, batch jobs are billed once with 30 days of re-download, and a monthly historical spending limit can be set in the portal",
          "Dated release notes per component with breaking changes and deprecations called out, and Python 0.85.0 to 0.89.0 released between 25 August and 28 October 2026",
          "Up to 100 named API keys per account with rotation, per-member permissions, and keys found in public revoked by the vendor",
          "$125 of credits at signup and metered historical pricing with no subscription; metadata and symbology calls are free"
        ],
        "weaknesses": [
          "Two critical and several major incidents on the status page in the 90 days to 3 November 2026, mostly Historical API outages and batch job delays",
          "The HTTP API is at major version 0 and the docs say it is not considered stable",
          "No OpenAPI document; per-GB rates sit in the portal catalogue behind a login, and the pricing page shows plans only",
          "The terms and privacy policy are drawn by script and could not be read, and no security.txt, SOC 2 or ISO 27001 was found",
          "Live data and the Plus and Unlimited plans need a subscription on an annual contract by sales, and signup is in a browser"
        ],
        "agentNotes": [
          "Call `metadata.get_cost` before `timeseries.get_range`, and set a monthly historical limit in the portal; a duplicate streaming request is charged twice",
          "Send the key as the Basic auth username (`-u $DATABENTO_API_KEY:`) to hist.databento.com/v0; never put it in the URL or source code",
          "On 429 wait for the Retry-After header; keep under 100 time series requests a second and 20 batch submissions a minute per IP",
          "Check status.databento.com before retrying a slow or 504 Historical request, since several incidents since August were API outages or batch delays",
          "Use batch download for requests over 5 GB, split by time range or `limit`, and read `schema` and `stype_in` from the dataset page before querying"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "C",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 60.3
          }
        ],
        "editorialScores": {
          "ergonomics": 80,
          "maintenance": 84,
          "payments": 22,
          "reliability": 50,
          "schema": 75,
          "security": 61,
          "transparency": 28
        },
        "provenanceScore": 70,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-03",
            "maintenance": "2026-11-03",
            "payments": "2026-11-03",
            "reliability": "2026-11-03",
            "schema": "2026-11-03",
            "security": "2026-11-03",
            "transparency": "2026-11-03"
          },
          "last": "2026-11-03",
          "oldest": "2026-11-03",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install databento",
        "http": "curl -G 'https://hist.databento.com/v0/metadata.list_datasets' -u $DATABENTO_API_KEY:"
      },
      "letme": {
        "capability": "https://letme.dev/market.prices",
        "tool": "https://letme.dev/databento"
      },
      "area": "domain-data",
      "unitPrices": [
        {
          "item": "Standard plan",
          "unit": "month",
          "usd": 199,
          "note": "live data, no licence fees, monthly"
        },
        {
          "item": "Plus plan licence fees",
          "unit": "month",
          "usd": 1750,
          "note": "annual contract, by sales"
        },
        {
          "item": "Unlimited plan licence fees",
          "unit": "month",
          "usd": 4500,
          "note": "annual contract, by sales"
        }
      ],
      "provenance": {
        "legalEntity": "Databento, Inc.",
        "domain": "databento.com",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://databento.com/legal/terms",
        "privacy": "https://databento.com/legal/privacy",
        "statusPage": "https://status.databento.com",
        "changelog": "https://databento.com/docs/release-notes",
        "securityTxt": "none",
        "checked": "2026-11-03",
        "notes": [
          "Databento, Inc. is named in the about page footer and as the GitHub organisation's name. The legal pages at databento.com/legal, /legal/terms and /legal/privacy answer 200 with a script shell and no text, so the terms, privacy policy, legal entity details and any automated-access clause are unread.",
          "databento.com/robots.txt disallows only /portal for all crawlers. status.databento.com and roadmap.databento.com allow reading.",
          "RDAP for databento.com was refused (403 from rdap.org), so the registration date is unchecked.",
          "/.well-known/security.txt returns 404.",
          "The status page is an Atlassian Statuspage at status.databento.com with Portal, Historical, FTP and seven live-feed components."
        ],
        "score": 70
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/databento.json",
      "live": {
        "slug": "databento",
        "probe": {
          "target": "https://hist.databento.com",
          "method": "get",
          "lastAt": "2026-11-04T21:27:45.7725368Z",
          "lastOk": true,
          "lastStatus": 200,
          "lastMs": 368,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 339,
          "p95ms24h": 1514,
          "samples24h": 62,
          "samples30d": 62,
          "days": [
            {
              "date": "2026-11-04",
              "probes": 62,
              "ok": 62
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.databento.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-04T21:25:39.981075462Z"
        },
        "versions": [
          {
            "registry": "github",
            "name": "databento/databento-python",
            "version": "v0.90.0",
            "released": "2026-11-03",
            "seenAt": "2026-11-04T20:10:26.351171807Z"
          },
          {
            "registry": "pypi",
            "name": "databento",
            "version": "0.90.0",
            "released": "2026-11-03",
            "seenAt": "2026-11-04T20:10:26.154676361Z"
          }
        ],
        "githubStars": 309,
        "pypiWeekly": 274335,
        "securityTxt": {
          "url": "https://databento.com/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-11-04T15:54:13.184390241Z"
        },
        "updatedAt": "2026-11-04T21:27:45.7725368Z"
      }
    },
    "answer": "Databento scores 60.3 (C) on agent readiness against Financial Modeling Prep's 48.7 (D), and leads in 4 of 7 scored categories. Financial Modeling Prep leads on payments \u0026 pricing and transparency \u0026 trust.",
    "b": {
      "slug": "financial-modeling-prep",
      "name": "Financial Modeling Prep",
      "vendor": "Financial Modeling Prep",
      "vendorUrl": "https://site.financialmodelingprep.com",
      "kind": "http-api",
      "category": "market-data",
      "summary": "Financial Modeling Prep (FMP) is a market data API for financial statements, earnings, quotes, price history, filings, news and economic series across stocks, ETFs, funds, forex and crypto. Agents call the REST endpoints under /stable or the hosted MCP server.",
      "url": "https://www.anchorterminal.com/tools/financial-modeling-prep",
      "markdownUrl": "https://www.anchorterminal.com/tools/financial-modeling-prep.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/financial-modeling-prep.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/financial-modeling-prep.json",
      "dns": "financial-modeling-prep.grade.anchorterminal.com",
      "transports": [
        "http",
        "streamable-http"
      ],
      "remoteUrl": "https://financialmodelingprep.com/stable",
      "packages": [],
      "auth": "api-key",
      "authNotes": "One API key per account, shown in the dashboard after a browser signup. The docs accept it as an `apikey` request header or as `?apikey=` in the query string. The hosted MCP server's documented address carries the key in the URL, `https://financialmodelingprep.com/mcp?apikey=KEY`; the same host also publishes OAuth 2 metadata (authorisation code with PKCE, scopes openid, email and profile) that the MCP page does not mention. No scopes, expiry or rotation guidance found.",
      "pricing": "freemium",
      "pricingNotes": "Basic plan free at 250 calls a day with end-of-day data and 5 years of history, no card stated. Personal plans Starter $29, Premium $69 and Ultimate $139 a month (about $19, $49 and $99 a month billed annually) at 300, 750 and 3,000 calls a minute, with trailing 30-day bandwidth caps of 500 MB, 20 GB, 50 GB and 150 GB. Commercial and display use need a separate licence with no public price (https://site.financialmodelingprep.com/pricing-plans, checked 2026-11-03).",
      "priceSummary": "$29 / mo",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the API docs, api-docs.md, pricing pages, the MCP page or the OAuth metadata (checked 2026-11-03). A call without a key returns HTTP 401 with an `Error Message` field.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-03"
      },
      "docsUrl": "https://site.financialmodelingprep.com/developer/docs",
      "llmsTxt": "https://site.financialmodelingprep.com/llms.txt",
      "capabilities": [
        "market.fundamentals",
        "market.prices",
        "market.history",
        "market.filings",
        "market.news",
        "market.indices",
        "market.crypto",
        "data.company",
        "data.markets"
      ],
      "tags": [
        "hosted",
        "freemium",
        "api-key",
        "mcp",
        "remote-mcp",
        "llms-txt",
        "no-card",
        "free-tier",
        "closed-source",
        "status-page",
        "stocks",
        "forex",
        "crypto",
        "personal-use"
      ],
      "lastRelease": "2026-11-02",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 48.7,
        "grade": "D",
        "agentReady": false,
        "rank": 1020,
        "ranked": true,
        "rankOf": 1349,
        "categoryRank": 8,
        "methodology": "0.7",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 59,
          "maintenance": 60,
          "payments": 30,
          "reliability": 50,
          "schema": 61,
          "security": 30,
          "transparency": 57
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-03"
        },
        "negative": 0,
        "verdict": "About 199 stable REST endpoints with Markdown docs for agents, a dated changelog and a free key at 250 calls a day. The one key travels in the query string on the documented MCP address, error responses and 429 handling are undocumented, the status history could not be read, and personal plans forbid any company use.",
        "bestFor": "Agents doing company research on statements, ratios, DCF, filings, transcripts and calendars with one key, and US coverage on cheap plans.",
        "strengths": [
          "api-docs.md and pricing.md give agents every stable endpoint with parameters, an example response and the plan that unlocks it",
          "Changelog entries dated by day through 2 November 2026",
          "Free Basic plan at 250 calls a day with no card stated, and plan prices published without login",
          "A public status page and a help centre with FAQs on keys, limits and errors",
          "Hosted MCP server that reuses the REST key and limits, with OAuth metadata published on the same host"
        ],
        "weaknesses": [
          "The documented MCP connection URL puts the API key in the query string, and the REST docs accept `?apikey=` too",
          "No OpenAPI document, no documented error responses and no 429 or Retry-After guidance found",
          "Status page data did not load for our reader, so the incident record is unknown",
          "Personal plans are for individuals only; any use on behalf of a company, and any display, needs a separate agreement with no public price",
          "Terms name no legal entity, and the privacy policy carries no date and no retention periods"
        ],
        "agentNotes": [
          "Send the key as an `apikey` header, not in the URL, and treat the MCP `?apikey=` address as a secret",
          "Use the /stable paths from api-docs.md; /api/v3 and /v4 are discontinued even though the FAQ still shows a v3 example",
          "On the free plan expect 5 results and page 0 on many list endpoints; read pricing.md before planning a crawl",
          "A missing or wrong key returns HTTP 401 with an `Error Message` field; stop and ask the user rather than retry",
          "Do not display or pass on the data in a product; personal plans forbid it"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.7",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 48.7
          }
        ],
        "editorialScores": {
          "ergonomics": 59,
          "maintenance": 60,
          "payments": 30,
          "reliability": 50,
          "schema": 61,
          "security": 30,
          "transparency": 33
        },
        "provenanceScore": 81,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-03",
            "maintenance": "2026-11-03",
            "payments": "2026-11-03",
            "reliability": "2026-11-03",
            "schema": "2026-11-03",
            "security": "2026-11-03",
            "transparency": "2026-11-03"
          },
          "last": "2026-11-03",
          "oldest": "2026-11-03",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "http": "curl -H \"apikey: $FMP_API_KEY\" \"https://financialmodelingprep.com/stable/quote?symbol=AAPL\"",
        "config": {
          "mcpServers": {
            "fmp": {
              "url": "https://financialmodelingprep.com/mcp?apikey=YOUR_FMP_API_KEY"
            }
          }
        }
      },
      "letme": {
        "capability": "https://letme.dev/market.fundamentals",
        "tool": "https://letme.dev/financial-modeling-prep"
      },
      "area": "domain-data",
      "unitPrices": [
        {
          "item": "Starter, 300 calls a minute",
          "unit": "month",
          "usd": 29,
          "note": "personal use, about $19 a month billed annually"
        },
        {
          "item": "Premium, 750 calls a minute",
          "unit": "month",
          "usd": 69,
          "note": "personal use, about $49 a month billed annually"
        },
        {
          "item": "Ultimate, 3,000 calls a minute",
          "unit": "month",
          "usd": 139,
          "note": "personal use, about $99 a month billed annually"
        }
      ],
      "provenance": {
        "legalEntity": "Financial Modeling Prep",
        "domain": "financialmodelingprep.com",
        "domainRegistered": "2018-02-19",
        "endpointOnVendorDomain": true,
        "terms": "https://site.financialmodelingprep.com/terms-of-service",
        "privacy": "https://site.financialmodelingprep.com/privacy-policy",
        "statusPage": "https://status.financialmodelingprep.com",
        "changelog": "https://site.financialmodelingprep.com/developer/docs/changelog",
        "securityTxt": "none",
        "checked": "2026-11-03",
        "notes": [
          "The terms of service, last updated 1 August 2023, are written between FMP and the customer and name no legal form, address or governing law. The footer reads Financial Modeling Prep.",
          "The privacy policy carries no date and names Google AdSense and Google Analytics. It keeps data for as long as necessary and promises breach notice within 7 business days.",
          "site.financialmodelingprep.com/robots.txt allows all crawlers and disallows /contact-card/. The terms contain no clause on automated access to the website.",
          "RDAP gives financialmodelingprep.com a registration date of 19 February 2018 at Amazon Registrar.",
          "/.well-known/security.txt and /security.txt return 404 on site.financialmodelingprep.com. The footer's Trust Center link returns 404.",
          "The status page is an Endpoint Uptime Status page at status.financialmodelingprep.com whose data loads by script; our reader got an error instead of the uptime figures.",
          "The hosted MCP server's host publishes OAuth 2 metadata at /.well-known/oauth-authorization-server with a Google service-account JWKS."
        ],
        "score": 81
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/financial-modeling-prep.json",
      "live": {
        "slug": "financial-modeling-prep",
        "probe": {
          "target": "https://financialmodelingprep.com/stable",
          "method": "get",
          "lastAt": "2026-11-04T21:27:49.382188244Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 367,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 398,
          "p95ms24h": 507,
          "samples24h": 62,
          "samples30d": 62,
          "days": [
            {
              "date": "2026-11-04",
              "probes": 62,
              "ok": 62
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.financialmodelingprep.com",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-04T21:25:50.965139403Z"
        },
        "securityTxt": {
          "url": "https://financialmodelingprep.com/.well-known/security.txt",
          "state": "unknown",
          "checkedAt": "2026-11-04T15:54:45.259926529Z"
        },
        "updatedAt": "2026-11-04T21:27:49.382188244Z"
      }
    },
    "edges": [
      {
        "by": 31,
        "category": "security",
        "leads": "databento",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "Named API keys, up to 100 per account, rotated or deleted in the portal, with per-member permissions, sent only as the Basic auth username; no scopes per key and no expiry (25 of 30). Every API call is a read, and a monthly historical limit caps what a leaked key can spend; live usage is not capped (14 of 20). The API returns market data and reference records, not free text from third parties (10). A data usage page in the portal and a billing page per cycle, with no per-key call log documented (8 of 15). The vendor revokes keys it finds in public and documents key hygiene; security.txt returns 404 and no bounty, SOC 2 or ISO 27001 was found on readable pages (4 of 20). Total 61.",
          "b": "One key per account with no scopes, accepted as a header or as `?apikey=`, and the documented MCP address carries it in the URL (20 less 10 for the query string, so 10). Every endpoint is a read (15 of 20). News, press releases, transcripts and filings are third-party text and no guidance on treating them as untrusted was found (5 of 15). No usage log or per-call record for the key holder was found (0 of 15). security.txt returns 404, the Trust Center link returns 404, and no disclosure policy, bug bounty or certification was found (0 of 20). 10 + 15 + 5 + 0 + 0 = 30."
        },
        "scores": {
          "a": 61,
          "b": 30
        }
      },
      {
        "by": 24,
        "category": "maintenance",
        "leads": "databento",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Python 0.89.0 on 28 October 2026 and data release notes dated 20 October (30). Python 0.85.0 (25 August), 0.86.0 (1 September), 0.87.0 (22 September), 0.88.0 (21 October) and 0.89.0, plus Rust 0.64.0 and C++ 0.69.0 on 27 October and four dated data notes since 8 August (20). A Slack community, Intercom chat, support@databento.com, a public roadmap and a public issue tracker linked from the release notes; GitHub issue replies were not read because the GitHub API rate limit was reached (12 of 15). Official clients in Python, C++ and Rust released the same week as each other (15). The Python client is Apache-2.0 with releases on GitHub and PyPI; CI and dependency pins were not checked (7 of 10). Total 84.",
          "b": "Read as a closed service. The changelog's newest entry is 2 November 2026 (30). Entries dated 6, 8, 12, 28 and 29 October and 2 November 2026, more than three in 90 days (20). A public changelog, a help centre, FAQs and a support address, with issues reported through a site chatbot per the FAQ (10 of 15). No official SDK; the FAQ points at third-party packages (0 of 15). No package to assess, and nothing else to show for CI or dependency health (0 of 10). 30 + 20 + 10 + 0 + 0 = 60."
        },
        "scores": {
          "a": 84,
          "b": 60
        }
      },
      {
        "by": 21,
        "category": "ergonomics",
        "leads": "databento",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "`limit`, time ranges to the nanosecond, schema choice from trades to daily bars, encoding choice and `metadata.get_cost` to size a request before paying (20 of 25). Symbol, date and schema filters, batch jobs listed and fetched by id, no cursor pagination because ranges are split by time (16 of 20). Errors carry an HTTP code, a named identifier, a message and a docs link, with 206 for partially resolved symbols (17 of 20). Reads only on the historical and reference APIs; a duplicate streaming request is charged twice, batch is billed once, and the portal can cap monthly spend (12 of 20). Few required parameters, and official clients in Python, C++ and Rust (15). Total 80.",
          "b": "The REST API is the surface graded. `limit` and `page` on list endpoints, `from` and `to` on series, and batch quote endpoints size responses, with no field selection (15 of 25). Page and limit parameters on lists and date filters on series, no cursor (15 of 20). A missing key returned 401 with an `Error Message` text field in our one test call, and no error reference exists (5 of 20). Every call is a GET read; the MCP server's annotations were not read (16 of 20). Few required parameters and sensible defaults, but no official SDK in any language (8 of 15). 15 + 15 + 5 + 16 + 8 = 59."
        },
        "scores": {
          "a": 80,
          "b": 59
        }
      },
      {
        "by": 14,
        "category": "schema",
        "leads": "databento",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "No OpenAPI document was found. The contract is the per-endpoint reference with typed parameters, the DBN schemas with field tables and enums, and a .http.md variant of every page (8 of 25). llms.txt and a Markdown twin of every page with language variants (10). Endpoint pages say what each call returns and the basics pages say when to use streaming against batch (15 of 20). Typed parameters with enums for schema, encoding, symbology type and split duration (13 of 15). Code in Python, C++, Rust and curl on every page, and an error table with codes, named error identifiers and a docs link in each body (14 of 15). Semantic versioning with dated release notes per component, breaking changes and deprecations called out (15). Total 75.",
          "b": "No OpenAPI document was found. The MCP page says the server supplies strict parameter definitions, but the tool list needs a key and was not read (5 of 25). llms.txt links api-docs.md and pricing.md, Markdown written for agents (10). Each of the 199 endpoints in api-docs.md has a purpose paragraph and a plan marker in pricing.md, with little on when not to use it (13 of 20). Parameters are tabled with type, example and a required star, but allowed values sit in prose and no enums are given (8 of 15). Every endpoint has an example request and response; no error responses are documented anywhere we read (10 of 15). A /stable path, legacy /v3 and /v4 marked discontinued, and a changelog dated by day through 2 November 2026 (15). 5 + 10 + 13 + 8 + 10 + 15 = 61."
        },
        "scores": {
          "a": 75,
          "b": 61
        }
      },
      {
        "by": 8,
        "category": "payments",
        "leads": "financial-modeling-prep",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402 (0). Plans are public ($199, $1,750 and $4,500 a month) and historical data is metered per GB, but the per-dataset rates are in the portal catalogue behind a login and the pricing page's estimator shows only an example (12 of 20). $125 of credits for every new user, expiring after six months; whether a card is needed at signup was not found on the pricing, credits or billing pages (10 of 20). A person signs up in a browser and creates keys in the portal; no key API (0). Total 22.",
          "b": "No x402, MPP or L402 (0). Four personal plans priced per month by calls a minute, public without login, with per-endpoint plan limits in pricing.md; commercial prices are by agreement (10). A free Basic plan at 250 calls a day with no card stated (20). The key comes from a browser signup and no key API was found (0). 0 + 10 + 20 + 0 = 30."
        },
        "scores": {
          "a": 22,
          "b": 30
        }
      },
      {
        "by": 8,
        "category": "transparency",
        "leads": "financial-modeling-prep",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "A closed service whose terms could not be read, because databento.com/legal and its /terms and /privacy pages are drawn by script; the client libraries are Apache-2.0 (10 of 30). The privacy policy was unread for the same reason, and the docs say nothing about retention of account data (0 of 30, unchecked). Dated release notes carry deprecations, and the versioning policy keeps a prior major version for a year after the next (18 of 20). No subprocessor list or data location statement was found on readable pages; the architecture docs name the company's own data centres (0 of 20). Total 28.",
          "b": "A closed service under terms that are clear on personal and commercial use and on display licensing, last updated 1 August 2023, but that name no legal entity, address or governing law (12 of 30). The privacy policy is undated, keeps data for as long as necessary with no periods, says no third parties receive data while naming Google AdSense and Analytics, and no DPA was found (8 of 30). The docs keep a Legacy section and api-docs.md says /v3 and /v4 are discontinued, with no notice period stated; behaviour changes such as the Economics Indicators default window appear in the dated changelog (8 of 20). Google services are the only processors named and no data location is given (5 of 20). 12 + 8 + 8 + 5 = 33."
        },
        "scores": {
          "a": 49,
          "b": 57
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "HTTP API",
        "name": "Kind"
      },
      {
        "a": "Databento, Inc.",
        "b": "Financial Modeling Prep",
        "name": "Vendor"
      },
      {
        "a": "https://hist.databento.com",
        "b": "https://financialmodelingprep.com/stable",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP, Streamable HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Freemium",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Apache-2.0 (clients)",
        "b": "none",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-28",
        "b": "2026-11-02",
        "name": "Last release"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Terms last updated"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Privacy policy last updated"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Customer content may train models"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Terms restrict automated access"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "couldn't be read",
        "b": "couldn't be read",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "309 stars",
        "b": "none",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "Databento scores 60.3 (C) on agent readiness against Financial Modeling Prep's 48.7 (D), and leads in 4 of 7 scored categories. Financial Modeling Prep leads on payments \u0026 pricing and transparency \u0026 trust.",
        "question": "Which is better for AI agents, Databento or Financial Modeling Prep?"
      },
      {
        "answer": "Both need an API key.",
        "question": "Do Databento and Financial Modeling Prep need an API key?"
      },
      {
        "answer": "Yes. Databento has a hosted endpoint at https://hist.databento.com and Financial Modeling Prep at https://financialmodelingprep.com/stable.",
        "question": "Can an agent call Databento and Financial Modeling Prep without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Schema \u0026 documentation, 75 against 61",
          "Agent ergonomics, 80 against 59",
          "Security \u0026 auth, 61 against 30",
          "Maintenance \u0026 community, 84 against 60"
        ],
        "also": null,
        "goodFor": "An agent that needs exchange-level trades, quotes, order book and bar data for US and European futures, options and equities, or corporate actions and a security master, and can budget per GB.",
        "slug": "databento",
        "watchFor": "Two critical and several major incidents on the status page in the 90 days to 3 November 2026, mostly Historical API outages and batch job delays"
      },
      {
        "aheadOn": [
          "Payments \u0026 pricing, 30 against 22",
          "Transparency \u0026 trust, 57 against 49"
        ],
        "also": [
          "Free to start without a card"
        ],
        "goodFor": "Agents doing company research on statements, ratios, DCF, filings, transcripts and calendars with one key, and US coverage on cheap plans.",
        "slug": "financial-modeling-prep",
        "watchFor": "The documented MCP connection URL puts the API key in the query string, and the REST docs accept `?apikey=` too"
      }
    ],
    "history": null,
    "job": {
      "capability": "market.prices",
      "name": "Market prices"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/alpha-vantage-vs-databento.json",
        "title": "Alpha Vantage vs Databento",
        "url": "https://www.anchorterminal.com/compare/alpha-vantage-vs-databento"
      },
      {
        "json": "https://www.anchorterminal.com/compare/alpha-vantage-vs-financial-modeling-prep.json",
        "title": "Alpha Vantage vs Financial Modeling Prep",
        "url": "https://www.anchorterminal.com/compare/alpha-vantage-vs-financial-modeling-prep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/benzinga-vs-databento.json",
        "title": "Benzinga vs Databento",
        "url": "https://www.anchorterminal.com/compare/benzinga-vs-databento"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-eodhd.json",
        "title": "Databento vs EODHD",
        "url": "https://www.anchorterminal.com/compare/databento-vs-eodhd"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-financial-datasets.json",
        "title": "Databento vs Financial Datasets",
        "url": "https://www.anchorterminal.com/compare/databento-vs-financial-datasets"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-finnhub.json",
        "title": "Databento vs Finnhub",
        "url": "https://www.anchorterminal.com/compare/databento-vs-finnhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-intrinio.json",
        "title": "Databento vs Intrinio",
        "url": "https://www.anchorterminal.com/compare/databento-vs-intrinio"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-massive.json",
        "title": "Databento vs Massive (formerly Polygon.io)",
        "url": "https://www.anchorterminal.com/compare/databento-vs-massive"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-tiingo.json",
        "title": "Databento vs Tiingo",
        "url": "https://www.anchorterminal.com/compare/databento-vs-tiingo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/databento-vs-twelve-data.json",
        "title": "Databento vs Twelve Data",
        "url": "https://www.anchorterminal.com/compare/databento-vs-twelve-data"
      },
      {
        "json": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-massive.json",
        "title": "Financial Modeling Prep vs Massive (formerly Polygon.io)",
        "url": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-massive"
      },
      {
        "json": "https://www.anchorterminal.com/compare/financial-datasets-vs-financial-modeling-prep.json",
        "title": "Financial Datasets vs Financial Modeling Prep",
        "url": "https://www.anchorterminal.com/compare/financial-datasets-vs-financial-modeling-prep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-finnhub.json",
        "title": "Financial Modeling Prep vs Finnhub",
        "url": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-finnhub"
      },
      {
        "json": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-intrinio.json",
        "title": "Financial Modeling Prep vs Intrinio",
        "url": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-intrinio"
      },
      {
        "json": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-tiingo.json",
        "title": "Financial Modeling Prep vs Tiingo",
        "url": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-tiingo"
      },
      {
        "json": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-twelve-data.json",
        "title": "Financial Modeling Prep vs Twelve Data",
        "url": "https://www.anchorterminal.com/compare/financial-modeling-prep-vs-twelve-data"
      },
      {
        "json": "https://www.anchorterminal.com/compare/eodhd-vs-financial-modeling-prep.json",
        "title": "EODHD vs Financial Modeling Prep",
        "url": "https://www.anchorterminal.com/compare/eodhd-vs-financial-modeling-prep"
      },
      {
        "json": "https://www.anchorterminal.com/compare/benzinga-vs-financial-modeling-prep.json",
        "title": "Benzinga vs Financial Modeling Prep",
        "url": "https://www.anchorterminal.com/compare/benzinga-vs-financial-modeling-prep"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 0,
        "databento": 50,
        "edge": "",
        "financial-modeling-prep": 50,
        "key": "reliability",
        "name": "Reliability",
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 14,
        "databento": 75,
        "edge": "databento",
        "financial-modeling-prep": 61,
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "weight": 13
      },
      {
        "by": 21,
        "databento": 80,
        "edge": "databento",
        "financial-modeling-prep": 59,
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "weight": 13
      },
      {
        "by": 31,
        "databento": 61,
        "edge": "databento",
        "financial-modeling-prep": 30,
        "key": "security",
        "name": "Security \u0026 auth",
        "weight": 14
      },
      {
        "by": 8,
        "databento": 22,
        "edge": "financial-modeling-prep",
        "financial-modeling-prep": 30,
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 24,
        "databento": 84,
        "edge": "databento",
        "financial-modeling-prep": 60,
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "weight": 7
      },
      {
        "by": 8,
        "databento": 49,
        "edge": "financial-modeling-prep",
        "financial-modeling-prep": 57,
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "weight": 7
      }
    ],
    "summary": "Databento scores 60.3 (C) on agent readiness against Financial Modeling Prep's 48.7 (D), and leads in 4 of 7 scored categories. Financial Modeling Prep leads on payments \u0026 pricing and transparency \u0026 trust. Both do market prices.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "databento": "Exchange-level tick and order book data metered per GB, with published per-IP rate limits, Retry-After on 429, dated release notes and clients in three languages. The HTTP API is still at major version 0, the status page lists two critical and several major incidents in 90 days, there is no OpenAPI document, and the legal pages were unreadable.",
      "financial-modeling-prep": "About 199 stable REST endpoints with Markdown docs for agents, a dated changelog and a free key at 250 calls a day. The one key travels in the query string on the documented MCP address, error responses and 429 handling are undocumented, the status history could not be read, and personal plans forbid any company use."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep",
    "json": "https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep.min.md"
  },
  "markdown": "Databento scores 60.3 (C) on agent readiness against Financial Modeling Prep's 48.7 (D), and leads in 4 of 7 scored categories. Financial Modeling Prep leads on payments \u0026 pricing and transparency \u0026 trust. Both do market prices.\n\n- Databento: grade C, 60.3/100, rank #592 of 1349. Markdown https://www.anchorterminal.com/tools/databento.md · JSON https://www.anchorterminal.com/api/v1/tools/databento.json\n- Financial Modeling Prep: grade D, 48.7/100, rank #1020 of 1349. Markdown https://www.anchorterminal.com/tools/financial-modeling-prep.md · JSON https://www.anchorterminal.com/api/v1/tools/financial-modeling-prep.json\n- Best financial market data APIs for AI agents: https://www.anchorterminal.com/best/market-data/index.md\n- All 55 markets comparisons: https://www.anchorterminal.com/compare/market-data/index.md\n\n## Which one, for what\n\n### Databento (C)\n\nGood for: An agent that needs exchange-level trades, quotes, order book and bar data for US and European futures, options and equities, or corporate actions and a security master, and can budget per GB.\n\nAhead on:\n- Schema \u0026 documentation, 75 against 61\n- Agent ergonomics, 80 against 59\n- Security \u0026 auth, 61 against 30\n- Maintenance \u0026 community, 84 against 60\n\nWatch for: Two critical and several major incidents on the status page in the 90 days to 3 November 2026, mostly Historical API outages and batch job delays\n\n### Financial Modeling Prep (D)\n\nGood for: Agents doing company research on statements, ratios, DCF, filings, transcripts and calendars with one key, and US coverage on cheap plans.\n\nAhead on:\n- Payments \u0026 pricing, 30 against 22\n- Transparency \u0026 trust, 57 against 49\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: The documented MCP connection URL puts the API key in the query string, and the REST docs accept `?apikey=` too\n\n\n## Why the edge\n\n### Security \u0026 auth: Databento +31\n\n- Databento (61): Named API keys, up to 100 per account, rotated or deleted in the portal, with per-member permissions, sent only as the Basic auth username; no scopes per key and no expiry (25 of 30). Every API call is a read, and a monthly historical limit caps what a leaked key can spend; live usage is not capped (14 of 20). The API returns market data and reference records, not free text from third parties (10). A data usage page in the portal and a billing page per cycle, with no per-key call log documented (8 of 15). The vendor revokes keys it finds in public and documents key hygiene; security.txt returns 404 and no bounty, SOC 2 or ISO 27001 was found on readable pages (4 of 20). Total 61.\n- Financial Modeling Prep (30): One key per account with no scopes, accepted as a header or as `?apikey=`, and the documented MCP address carries it in the URL (20 less 10 for the query string, so 10). Every endpoint is a read (15 of 20). News, press releases, transcripts and filings are third-party text and no guidance on treating them as untrusted was found (5 of 15). No usage log or per-call record for the key holder was found (0 of 15). security.txt returns 404, the Trust Center link returns 404, and no disclosure policy, bug bounty or certification was found (0 of 20). 10 + 15 + 5 + 0 + 0 = 30.\n\n### Maintenance \u0026 community: Databento +24\n\n- Databento (84): Python 0.89.0 on 28 October 2026 and data release notes dated 20 October (30). Python 0.85.0 (25 August), 0.86.0 (1 September), 0.87.0 (22 September), 0.88.0 (21 October) and 0.89.0, plus Rust 0.64.0 and C++ 0.69.0 on 27 October and four dated data notes since 8 August (20). A Slack community, Intercom chat, support@databento.com, a public roadmap and a public issue tracker linked from the release notes; GitHub issue replies were not read because the GitHub API rate limit was reached (12 of 15). Official clients in Python, C++ and Rust released the same week as each other (15). The Python client is Apache-2.0 with releases on GitHub and PyPI; CI and dependency pins were not checked (7 of 10). Total 84.\n- Financial Modeling Prep (60): Read as a closed service. The changelog's newest entry is 2 November 2026 (30). Entries dated 6, 8, 12, 28 and 29 October and 2 November 2026, more than three in 90 days (20). A public changelog, a help centre, FAQs and a support address, with issues reported through a site chatbot per the FAQ (10 of 15). No official SDK; the FAQ points at third-party packages (0 of 15). No package to assess, and nothing else to show for CI or dependency health (0 of 10). 30 + 20 + 10 + 0 + 0 = 60.\n\n### Agent ergonomics: Databento +21\n\n- Databento (80): `limit`, time ranges to the nanosecond, schema choice from trades to daily bars, encoding choice and `metadata.get_cost` to size a request before paying (20 of 25). Symbol, date and schema filters, batch jobs listed and fetched by id, no cursor pagination because ranges are split by time (16 of 20). Errors carry an HTTP code, a named identifier, a message and a docs link, with 206 for partially resolved symbols (17 of 20). Reads only on the historical and reference APIs; a duplicate streaming request is charged twice, batch is billed once, and the portal can cap monthly spend (12 of 20). Few required parameters, and official clients in Python, C++ and Rust (15). Total 80.\n- Financial Modeling Prep (59): The REST API is the surface graded. `limit` and `page` on list endpoints, `from` and `to` on series, and batch quote endpoints size responses, with no field selection (15 of 25). Page and limit parameters on lists and date filters on series, no cursor (15 of 20). A missing key returned 401 with an `Error Message` text field in our one test call, and no error reference exists (5 of 20). Every call is a GET read; the MCP server's annotations were not read (16 of 20). Few required parameters and sensible defaults, but no official SDK in any language (8 of 15). 15 + 15 + 5 + 16 + 8 = 59.\n\n### Schema \u0026 documentation: Databento +14\n\n- Databento (75): No OpenAPI document was found. The contract is the per-endpoint reference with typed parameters, the DBN schemas with field tables and enums, and a .http.md variant of every page (8 of 25). llms.txt and a Markdown twin of every page with language variants (10). Endpoint pages say what each call returns and the basics pages say when to use streaming against batch (15 of 20). Typed parameters with enums for schema, encoding, symbology type and split duration (13 of 15). Code in Python, C++, Rust and curl on every page, and an error table with codes, named error identifiers and a docs link in each body (14 of 15). Semantic versioning with dated release notes per component, breaking changes and deprecations called out (15). Total 75.\n- Financial Modeling Prep (61): No OpenAPI document was found. The MCP page says the server supplies strict parameter definitions, but the tool list needs a key and was not read (5 of 25). llms.txt links api-docs.md and pricing.md, Markdown written for agents (10). Each of the 199 endpoints in api-docs.md has a purpose paragraph and a plan marker in pricing.md, with little on when not to use it (13 of 20). Parameters are tabled with type, example and a required star, but allowed values sit in prose and no enums are given (8 of 15). Every endpoint has an example request and response; no error responses are documented anywhere we read (10 of 15). A /stable path, legacy /v3 and /v4 marked discontinued, and a changelog dated by day through 2 November 2026 (15). 5 + 10 + 13 + 8 + 10 + 15 = 61.\n\n### Payments \u0026 pricing: Financial Modeling Prep +8\n\n- Databento (22): No x402, MPP or L402 (0). Plans are public ($199, $1,750 and $4,500 a month) and historical data is metered per GB, but the per-dataset rates are in the portal catalogue behind a login and the pricing page's estimator shows only an example (12 of 20). $125 of credits for every new user, expiring after six months; whether a card is needed at signup was not found on the pricing, credits or billing pages (10 of 20). A person signs up in a browser and creates keys in the portal; no key API (0). Total 22.\n- Financial Modeling Prep (30): No x402, MPP or L402 (0). Four personal plans priced per month by calls a minute, public without login, with per-endpoint plan limits in pricing.md; commercial prices are by agreement (10). A free Basic plan at 250 calls a day with no card stated (20). The key comes from a browser signup and no key API was found (0). 0 + 10 + 20 + 0 = 30.\n\n### Transparency \u0026 trust: Financial Modeling Prep +8\n\n- Databento (49): A closed service whose terms could not be read, because databento.com/legal and its /terms and /privacy pages are drawn by script; the client libraries are Apache-2.0 (10 of 30). The privacy policy was unread for the same reason, and the docs say nothing about retention of account data (0 of 30, unchecked). Dated release notes carry deprecations, and the versioning policy keeps a prior major version for a year after the next (18 of 20). No subprocessor list or data location statement was found on readable pages; the architecture docs name the company's own data centres (0 of 20). Total 28.\n- Financial Modeling Prep (57): A closed service under terms that are clear on personal and commercial use and on display licensing, last updated 1 August 2023, but that name no legal entity, address or governing law (12 of 30). The privacy policy is undated, keeps data for as long as necessary with no periods, says no third parties receive data while naming Google AdSense and Analytics, and no DPA was found (8 of 30). The docs keep a Legacy section and api-docs.md says /v3 and /v4 are discontinued, with no notice period stated; behaviour changes such as the Economics Indicators default window appear in the dated changelog (8 of 20). Google services are the only processors named and no data location is given (5 of 20). 12 + 8 + 8 + 5 = 33.\n\n## Score by category\n\n| Category | Weight | Databento | Financial Modeling Prep | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 50 | 50 | even |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 75 | 61 | Databento +14 |\n| Agent ergonomics | 13% (16.2 this run) | 80 | 59 | Databento +21 |\n| Security \u0026 auth | 14% (17.5 this run) | 61 | 30 | Databento +31 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 22 | 30 | Financial Modeling Prep +8 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 84 | 60 | Databento +24 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 49 | 57 | Financial Modeling Prep +8 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **60.3 · C** | **48.7 · D** | |\n\n## Facts side by side\n\n| Fact | Databento | Financial Modeling Prep |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Databento, Inc. | Financial Modeling Prep |\n| Hosted endpoint | `https://hist.databento.com` | `https://financialmodelingprep.com/stable` |\n| Transports | HTTP | HTTP, Streamable HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 (clients) | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-28 | 2026-11-02 |\n| Terms last updated | couldn't be read | couldn't be read |\n| Privacy policy last updated | couldn't be read | couldn't be read |\n| Customer content may train models | couldn't be read | couldn't be read |\n| Terms restrict automated access | couldn't be read | couldn't be read |\n| Terms restrict benchmarking | couldn't be read | couldn't be read |\n| Terms or service can change without notice | couldn't be read | couldn't be read |\n| Arbitration or class-action waiver | couldn't be read | couldn't be read |\n| Popularity | 309 stars | none |\n\n## Verdicts\n\n**Databento.** Exchange-level tick and order book data metered per GB, with published per-IP rate limits, Retry-After on 429, dated release notes and clients in three languages. The HTTP API is still at major version 0, the status page lists two critical and several major incidents in 90 days, there is no OpenAPI document, and the legal pages were unreadable.\n\n**Financial Modeling Prep.** About 199 stable REST endpoints with Markdown docs for agents, a dated changelog and a free key at 250 calls a day. The one key travels in the query string on the documented MCP address, error responses and 429 handling are undocumented, the status history could not be read, and personal plans forbid any company use.\n\n## Before you call either\n\n### Databento\n\n1. Call `metadata.get_cost` before `timeseries.get_range`, and set a monthly historical limit in the portal; a duplicate streaming request is charged twice\n2. Send the key as the Basic auth username (`-u $DATABENTO_API_KEY:`) to hist.databento.com/v0; never put it in the URL or source code\n3. On 429 wait for the Retry-After header; keep under 100 time series requests a second and 20 batch submissions a minute per IP\n4. Check status.databento.com before retrying a slow or 504 Historical request, since several incidents since August were API outages or batch delays\n5. Use batch download for requests over 5 GB, split by time range or `limit`, and read `schema` and `stype_in` from the dataset page before querying\n\n### Financial Modeling Prep\n\n1. Send the key as an `apikey` header, not in the URL, and treat the MCP `?apikey=` address as a secret\n2. Use the /stable paths from api-docs.md; /api/v3 and /v4 are discontinued even though the FAQ still shows a v3 example\n3. On the free plan expect 5 results and page 0 on many list endpoints; read pricing.md before planning a crawl\n4. A missing or wrong key returns HTTP 401 with an `Error Message` field; stop and ask the user rather than retry\n5. Do not display or pass on the data in a product; personal plans forbid it\n\n## Questions\n\n### Which is better for AI agents, Databento or Financial Modeling Prep?\n\nDatabento scores 60.3 (C) on agent readiness against Financial Modeling Prep's 48.7 (D), and leads in 4 of 7 scored categories. Financial Modeling Prep leads on payments \u0026 pricing and transparency \u0026 trust.\n\n### Do Databento and Financial Modeling Prep need an API key?\n\nBoth need an API key.\n\n### Can an agent call Databento and Financial Modeling Prep without installing anything?\n\nYes. Databento has a hosted endpoint at https://hist.databento.com and Financial Modeling Prep at https://financialmodelingprep.com/stable.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep.json, and with the fewest tokens: https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"databento\", \"b\": \"financial-modeling-prep\"}`. From a terminal: `anchor compare databento financial-modeling-prep`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/databento.json and https://www.anchorterminal.com/api/v1/tools/financial-modeling-prep.json\n\n## Other comparisons with Databento or Financial Modeling Prep\n\n- [Alpha Vantage vs Databento](https://www.anchorterminal.com/compare/alpha-vantage-vs-databento.md)\n- [Alpha Vantage vs Financial Modeling Prep](https://www.anchorterminal.com/compare/alpha-vantage-vs-financial-modeling-prep.md)\n- [Benzinga vs Databento](https://www.anchorterminal.com/compare/benzinga-vs-databento.md)\n- [Databento vs EODHD](https://www.anchorterminal.com/compare/databento-vs-eodhd.md)\n- [Databento vs Financial Datasets](https://www.anchorterminal.com/compare/databento-vs-financial-datasets.md)\n- [Databento vs Finnhub](https://www.anchorterminal.com/compare/databento-vs-finnhub.md)\n- [Databento vs Intrinio](https://www.anchorterminal.com/compare/databento-vs-intrinio.md)\n- [Databento vs Massive (formerly Polygon.io)](https://www.anchorterminal.com/compare/databento-vs-massive.md)\n- [Databento vs Tiingo](https://www.anchorterminal.com/compare/databento-vs-tiingo.md)\n- [Databento vs Twelve Data](https://www.anchorterminal.com/compare/databento-vs-twelve-data.md)\n- [Financial Modeling Prep vs Massive (formerly Polygon.io)](https://www.anchorterminal.com/compare/financial-modeling-prep-vs-massive.md)\n- [Financial Datasets vs Financial Modeling Prep](https://www.anchorterminal.com/compare/financial-datasets-vs-financial-modeling-prep.md)\n- [Financial Modeling Prep vs Finnhub](https://www.anchorterminal.com/compare/financial-modeling-prep-vs-finnhub.md)\n- [Financial Modeling Prep vs Intrinio](https://www.anchorterminal.com/compare/financial-modeling-prep-vs-intrinio.md)\n- [Financial Modeling Prep vs Tiingo](https://www.anchorterminal.com/compare/financial-modeling-prep-vs-tiingo.md)\n- [Financial Modeling Prep vs Twelve Data](https://www.anchorterminal.com/compare/financial-modeling-prep-vs-twelve-data.md)\n- [EODHD vs Financial Modeling Prep](https://www.anchorterminal.com/compare/eodhd-vs-financial-modeling-prep.md)\n- [Benzinga vs Financial Modeling Prep](https://www.anchorterminal.com/compare/benzinga-vs-financial-modeling-prep.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.7",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Databento vs Financial Modeling Prep",
        "url": ""
      }
    ],
    "description": "Databento scores 60.3 (C) to Financial Modeling Prep's 48.7 (D) for market prices. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Databento C 60.3",
      "Financial Modeling Prep D 48.7",
      "scores"
    ],
    "h1": "Databento vs Financial Modeling Prep",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/databento-vs-financial-modeling-prep",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Databento vs Financial Modeling Prep for AI agents (2026)",
    "toc": null,
    "updated": "2026-11-04",
    "url": "https://www.anchorterminal.com/compare/databento-vs-financial-modeling-prep"
  },
  "tokens": {
    "markdown": 4450,
    "slim": 2580
  },
  "version": 1
}
