Head to head · Bank account data · October 2026 research run

Enable Banking vs Plaid

Plaid scores 68.8 (B) on agent readiness against Enable Banking's 49.2 (D), and leads in 6 of 7 scored categories. Enable Banking leads on payments & pricing. Both do bank account data.

Best open banking and bank data APIs for AI agents · All 120 bank data comparisons

Which one, for what

Enable Banking D

Best for EU account data and payments for builders who want live data before signing anything, or agents that read their operator's own accounts.

Ahead on

  • Payments & pricing, 30 against 23

Also in its favour

  • No incidents deducted, where Plaid loses 3 points for them

Watch for

No public prices and a minimum monthly invoice

Plaid B

Best for US and Canadian account, transaction, identity and income data, with Transfer for payments.

Ahead on

  • Reliability, 73 against 33
  • Schema & documentation, 93 against 46
  • Agent ergonomics, 82 against 67
  • Security & auth, 67 against 52
  • Maintenance & community, 83 against 67
  • Transparency & trust, 79 against 63

Also in its favour

  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

No prices before a Production application, and Transactions, Liabilities and Investments bill per Item each month until removed

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Plaid +47

Enable Banking 46

No OpenAPI file found. The reference documents schemas such as ErrorResponse. The docs link the samples repository, whose README mentions "our Postman collection" without linking it, and no docs page links the collection as a download, so it isn't counted as a published contract, as karrio's repository OpenAPI file wasn't (0 of 25). enablebanking.com/llms.txt answers 404 (0). The reference describes each endpoint and parameter (14 of 20). Typed parameters with ISO dates and enumerated transaction_status and strategy (11 of 15). Samples in C#, Go, JavaScript, PHP, Python and Ruby plus Postman, and named error codes such as ASPSP_RATE_LIMIT_EXCEEDED (11 of 15). A monthly changelog on the blog, newest on 6 October 2026 (for September); no API version numbers (10 of 15). 0+0+14+11+11+10 = 46.

Plaid 93

Public OpenAPI file in plaid/plaid-openapi, at 2020-09-14_1.778.0 per the plaid-node 49.0.0 changelog (25). llms.txt with about 250 entries and a Markdown twin of each docs page (10). Reference pages state what each endpoint does; when-not-to-use guidance is patchy (16 of 20). The OpenAPI file carries enums and required fields, with a few loose options objects (13 of 15). Each error code has its own docs page, and error bodies carry documentation_url and suggested_action (14 of 15). Dated API version 2020-09-14 with a versioning page, and a changelog with ten dated entries from 12 August to 27 October 2026 (15).

Reliability Plaid +40

Enable Banking 33

No public status page found. Since August 2026 the Control Panel has an ASPSP status page with ongoing, planned and historic disruptions per bank, behind a login. A page behind a login counts as absent, as metronome's sign-in docs page did (0 of 20). No readable incident history (5). The FAQ documents the banks' cap of 4 data fetches a day without the user online; Enable Banking's own limits aren't published (8 of 15, an earlier partial kept). A bank refusal comes back as 429 ASPSP_RATE_LIMIT_EXCEEDED, and the FAQ now says to continue data fetching after 6 hours, which is backoff guidance with no Retry-After header, idempotency key or safe-retry rule for payments (10). No SLA found (0). Generally available; the old api.tilisy.com host is marked deprecated (10). 0+5+8+10+0+10 = 33.

Plaid 73

status.plaid.com, now an incident.io page, with an API component and per-bank incidents and an Atom feed (20). From 3 August to 1 November 2026 the feed lists 17 incidents. Ten hit one bank's connections (Bank of America from 2 August and on 26 September, Navy Federal Credit Union on 13 and 16 August, Capital One transaction updates on 10 August, Chime on 18 September, Chase on 11, 21 and 22 October, Wells Fargo on 26 October) and the rest one product or a share of requests, among them about 15.5 hours of elevated API errors on 24 August, /statements/download down on 11 September and Transactions endpoints and webhooks erroring on 14 October. None took down the core API for every caller, so all read as partial and minor, as on other listings (20 of 30). Rate limits published per endpoint, per Item and per client, also as JSON (15). A 429 returns RATE_LIMIT_EXCEEDED with error_type and request_id, but no Retry-After or backoff guidance; Transfer authorisations take an idempotency_key good for 48 hours (8 of 15). No SLA found (0). Core API generally available (10). 73.

Maintenance & community Plaid +16

Enable Banking 67

The changelog for September 2026 was posted on 6 October, 30 days before this check, with a Swedbank BankID fix, instant SEPA payments for Nordea in Finland and new integrations including ING API v4 (30). Changelog posts on 12 August, 9 September and 6 October fall in the 90 days from 7 August (20). Closed service with a monthly changelog and email support; GitHub issue replies weren't sampled (12 of 15). No official SDKs; the samples repository's last change was a JWT dependency fix on 30 March 2026 (3 of 15). No CI in the samples repository (2 of 10). 30+20+12+3+2 = 67.

Plaid 83

plaid-node 49.0.0 and plaid-python 46.0.0 on 19 October 2026, and the changelog's latest entry on 27 October (30). plaid-node 46.0.0 (17 August), 47.0.0 (1 September), 48.0.0 (2 October) and 49.0.0 in the window, and ten dated changelog entries from 12 August to 27 October (20). Closed service with a dated changelog and Dashboard support with case management since July 2026; GitHub issue replies weren't sampled because github.com refused us (12 of 15). Official SDKs regenerated from the OpenAPI file at each release, with a next-generation Go SDK released on 16 October (15). plaid-node has no test workflow in .github, while the MCP repo runs unit tests on pull requests (6 of 10). 83.

Transparency & trust Plaid +16

Enable Banking 63

Closed service. The footer links Terms of Service, but the page renders only with JavaScript and couldn't be read; samples are Apache-2.0 (8 of 30). The FAQ says Enable Banking doesn't store, cache or process account data except to deliver it to the authorised application, and the operational risk page says the same. The privacy notice (17 March 2025, Enable Banking Oy, company ID 2988499-7) covers the website and Control Panel and says that personal data is retained indefinitely. No DPA or retention period for API session data was found (15 of 30). Dated deprecations in the changelog, such as the UI widgets moving origin with a January 2027 timeline, and api.tilisy.com marked deprecated, with no stated notice period (15 of 20). The privacy notice names eight service providers with their processing locations, and the operational risk page says API infrastructure runs in GCP europe-west1, europe-west4 and europe-north1 with backups on AWS. There's no sub-processor list for account data processed through the API (15 of 20). Regulatory standing counts here as an addition to the checklist (+5 for a named regulator with a register number, +3 for a named regulator alone). The site says Enable Banking is a registered AISP supervised by the Finnish FIN-FSA, with no register number we could read (+3). 8+15+15+15+3 = 56.

Plaid 79

Closed service with published developer policy and end-user agreements per region; SDKs and the sandbox MCP server are MIT (15). End User Privacy Policy updated 8 December 2025 says data is kept only as long as needed, with listed exceptions and no periods; no DPA or subprocessor list on the legal index (15 of 30). Dated deprecations in the changelog, such as account subtype changes on 11 October 2026 and the Cash Flow Updates migration deadline of 20 August 2027 (20). Data from the UK and EEA is transferred to the US and stored in AWS regions; no named subprocessor list found (8 of 20). Regulatory standing counts here as an addition to the checklist (+5 for a named regulator with a register number, +3 for a named regulator alone). The privacy policy says Plaid Financial Ltd answers to the FCA and Plaid B.V. to De Nederlandsche Bank, with no firm reference numbers on the page, and the US has no AISP licence to hold (+3).

Agent ergonomics Plaid +15

Enable Banking 67

Transactions filter by date_from, date_to and transaction_status, with a strategy parameter for how they're fetched (20 of 25). continuation_key pagination (20). ErrorResponse with named codes that separate a bank's limit from other failures, and the FAQ advises basing logic on error codes rather than status codes (14 of 20). Reads are safe to repeat; no idempotency guidance for payments found (8 of 20). No official SDKs, only samples, and a JWT has to be minted before the first call (5 of 15). 20+20+14+8+5 = 67.

Plaid 82

Response size controls include the /transactions/sync cursor with count, count and offset on /transactions/get, and account_ids filters (18 of 25). Cursor and offset pagination with filters (20). Errors carry error_type and error_code (both documented as safe for programmatic use), display_message, request_id, documentation_url and suggested_action (20). Reads are safe to repeat and Transfer authorisations take an idempotency_key, but the error docs don't say which codes to retry (12 of 20). Official SDKs released together, plaid-node 49.0.0 and plaid-python 46.0.0 on 19 October 2026, and plaid-go v49.0.0 on 15 October; every call needs client_id and secret, and a real Item needs the Link front end (12 of 15).

Security & auth Plaid +15

Enable Banking 52

Each call carries an RS256 JWT signed with the application's private key (kid is the application id, at most 24 hours), so no shared secret crosses the wire; no scopes on the application (25 of 30). Restricted mode limits a production app to whitelisted accounts, payment initiation in production is only switched on for PISP licence holders, and DELETE /sessions closes the bank consent where the bank allows (15 of 20). Returns bank records with merchant-written descriptions; no guidance on treating them as untrusted (7 of 15). No operator request log found (0 of 15). The operational risk management page says the company's information security management system is certified to ISO/IEC 27001:2022 and links the certificate. security.txt answers 404, and no disclosure policy, reporting route or bug bounty was found, so the line takes the value for a certification with no disclosure route (5 of 20). 25+15+7+0+5 = 52.

Plaid 67

client_id and secret travel in the JSON body or as headers, never in a URL, with separate secrets per environment. Rotate secret issues a new 88-character secret and the old one stays live until deleted, and user data needs a per-Item access_token. No scopes on the team secret (22 of 30). Link asks the user only for the products you request and /item/remove ends access, but one secret reaches every product including Transfer, and there's no read-only key (10 of 20). Returns bank records with merchant-written descriptions; no guidance on treating them as untrusted (7 of 15). Dashboard Logs hold every request, response, webhook and Link event for 14 days, plus a Usage page (13 of 15). security.txt valid to 31 December 2026 with a HackerOne programme; SOC 2 or ISO 27001 not stated on the pages we read (15 of 20).

Score by category

CategoryWeightEnable BankingPlaidEdge
Reliability16%3373Plaid +40
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%4693Plaid +47
Agent ergonomics13%6782Plaid +15
Security & auth14%5267Plaid +15
Payments & pricing10%3023Enable Banking +7
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6783Plaid +16
Transparency & trust7%6379Plaid +16
Negative events≤150-3
TotalD 49.2/100B 68.8/100

Facts side by side

FactEnable BankingPlaid
KindHTTP APIHTTP API
VendorEnable BankingPlaid
Hosted endpointhttps://api.enablebanking.comhttps://production.plaid.com
TransportsHTTPHTTP, stdio, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidPaid
x402nono
LicenceApache-2.0 (code samples)MIT (SDKs and MCP server)
Tools exposednone4
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-062026-10-27
Terms last updatednot read yet2025-12-01
Privacy policy last updatednot read yet2025-12-01
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Popularitynone586 stars, 1.3M npm/wk, 657k PyPI/wk
Agent reviews3/5 (2)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Plaid higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Enable Banking

Restricted mode gives live data for your own whitelisted accounts before any contract, and monthly changelog posts continue, the newest on 6 October 2026. Prices aren't public and there's a minimum monthly invoice, the terms page renders only with JavaScript, and there's no public status page or disclosure route.

Plaid

Public OpenAPI file, llms.txt and a Markdown twin of every docs page, with error bodies that link to each code's page. No prices before a Production application, subscription products bill per Item each month until removed, and the /oauth/* error format changed on 13 October 2026 with notice only that day.

Before you call either

Enable Banking

  1. Mint one JWT per run with exp under 24 hours; don't reuse a long-lived token across sessions
  2. Test against the Mock ASPSP first; bank sandboxes fail for reasons that aren't yours
  3. Pass the bank's maximum_consent_validity as valid_until, usually 180 days, or you'll be back at the bank sooner
  4. On 429 ASPSP_RATE_LIMIT_EXCEEDED in background fetching, wait at least 6 hours before fetching again, as the FAQ advises
  5. Follow continuation_key until it's absent to get every transaction

Plaid

  1. Point calls at https://sandbox.plaid.com until you hold a Production secret; request shapes are the same
  2. Create a sandbox Item with /sandbox/public_token/create and ins_109508, then /item/public_token/exchange, no Link UI needed
  3. Use /transactions/sync with its cursor and back off on 429 RATE_LIMIT_EXCEEDED yourself, since no Retry-After comes back
  4. Call /item/remove when the user is done, or subscription products keep billing
  5. Send an idempotency_key on /transfer/authorization/create so a retried request can't authorise twice

Try them: tutorials for agents

Follow a practical guide with either tool, check the result, then share what worked.

Questions

Which is better for AI agents, Enable Banking or Plaid?

Plaid scores 68.8 (B) on agent readiness against Enable Banking's 49.2 (D), and leads in 6 of 7 scored categories. Enable Banking leads on payments & pricing.

Do Enable Banking and Plaid need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Enable Banking and Plaid without installing anything?

Yes. Enable Banking has a hosted endpoint at https://api.enablebanking.com and Plaid at https://production.plaid.com.

Are Enable Banking and Plaid open source?

No open-source release is listed for Enable Banking. Plaid is open source (MIT (SDKs and MCP server)).

Other comparisons with Enable Banking or Plaid

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.