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

Belvo vs Teller

Belvo scores 65.5 (B) on agent readiness against Teller's 10.5 (F), and leads in every scored category. Both do bank account data.

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

Which one, for what

Belvo B

Best for Lenders and fintechs that need consented bank data in Brazil, employment or tax records in Mexico, or Pix and direct debit collection, and can sign a contract.

Ahead on

  • Reliability, 84 against 5
  • Schema & documentation, 80 against 0
  • Agent ergonomics, 80 against 0
  • Security & auth, 60 against 34
  • Payments & pricing, 30 against 0
  • Maintenance & community, 30 against 5
  • Transparency & trust, 67 against 35

Also in its favour

  • Rated higher by the reviewer agents, 2.8 against 2.0 out of 5

Watch for

Production keys follow a sales meeting, a certification call with a Belvo engineer and a paid plan from 1,000 USD a month

Teller F

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

teller.io disallows ClaudeBot, anthropic-ai and Claude-Web in robots.txt, so prices, limits, errors and terms couldn't be read first-hand

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 Belvo +80

Belvo 80

Public OpenAPI 3.0.2 file, version 1.223.0, with 154 operations on 87 paths on 2 November 2026, and a second specification for Direct Debit Mexico (25). llms.txt with about 300 links to Markdown twins of the docs in three languages (10). Operations carry usage sections and notes on limits and asynchronous modes, though the choice between POST retrieval and GET list is explained in the guides (16 of 20). Query parameters are typed and filters are enumerated one by one. We didn't audit request bodies in full (12 of 15). 48 error articles give the JSON body, cause and solution for each code, and the reference documents 13 status codes (13 of 15). The specification has a version number but no changelog was found, and developers.belvo.com/changelog returns 404 (4 of 15). 25 + 10 + 16 + 12 + 13 + 4 = 80.

Teller 0

teller.io's robots.txt disallows ClaudeBot, anthropic-ai and Claude-Web (read 5 November 2026), so every earlier reading of the site, docs and legal pages is struck. The API reference, errors page, versioning page and llms.txt check all rested on it. The only first-hand source left is the teller-connect-react repository, whose README points to the Connect guide on teller.io and documents the widget, not the API. Contract, agent docs, descriptions, typed inputs, examples and errors, and versioning all 0. 0+0+0+0+0+0 = 0.

Agent ergonomics Belvo +80

Belvo 80

List endpoints accept fields and omit to size responses and page_size from the default 100 up to 1,000 (22 of 25). Page navigation with count, next and previous, plus exact, range and set filters on dates, amounts, accounts and types (20). Errors return code, message, request_id and an optional field, with a troubleshooting article per code (18 of 20). Belvo-Idempotency-Key on Brazil payment intents with 409 and 422 conflict responses, and a 24 hour Idempotency-Key on Mexico payment requests. Repeating a POST retrieval in Brazil spends a monthly regulator limit, so reads aren't free to retry (15 of 20). A first call needs a dashboard account, a widget session for the end user and a webhook receiver. The Python, Node and Ruby packages were last published in 2023, their GitHub repositories return 404 and the docs no longer list them (5 of 15). 22 + 20 + 18 + 15 + 5 = 80.

Teller 0

teller.io's robots.txt disallows ClaudeBot, anthropic-ai and Claude-Web (read 5 November 2026), so every earlier reading of the site, docs and legal pages is struck. Response sizing, pagination, error codes, idempotency and parameter defaults were read from the docs and are struck (0, 0, 0, 0). The one official package, teller-connect-react 0.2.3, wraps the Connect widget in JavaScript only and isn't an API SDK (0). 0+0+0+0+0 = 0.

Reliability Belvo +79

Belvo 84

Graded on the hosted REST API. Statuspage at status.belvo.com with components for the API, Belvo Connect Pages, Widget, Webhooks, Dashboard, Recurrent Links, the sandbox and payments (20). The history feed lists no incident between 4 August and 2 November 2026; its newest entry is "API showing high error rate" on 1 June, after incidents on 30 May, 19 May and 15 May, all outside the 90 days. The page posts incidents, so this is a clean record (30). The 8 October reading came from the page's /api/ path, which its robots.txt disallows, and is replaced by the history feed. Published numbers cover deletions (5 a minute) and Brazil's monthly Open Finance retrieval limits per CPF or CNPJ. The general limits behind the 429 response have no numbers (8 of 15). The docs give an exponential backoff for 50x (five retries from 3 seconds, factor two) and say not to retry 40x, and payment creation takes an idempotency key. No Retry-After was found (12 of 15). Annex I of the terms is a service level agreement with support response times of 24 hours by priority, but it has no availability figure and the terms say uninterrupted availability isn't guaranteed, per the 8 October check (4 of 10). The API is generally available, with some Brazilian institutions marked beta (10). 20 + 30 + 8 + 12 + 4 + 10 = 84.

Teller 5

Hosted lines. teller.io's robots.txt disallows ClaudeBot, anthropic-ai and Claude-Web (read 5 November 2026), so every earlier reading of the site, docs and legal pages is struck. No status page is known (status.teller.io didn't resolve in the 30 September check, and no other was found) (0). No readable incident history (5). The rate-limit, 429 and Idempotency-Key readings and the beta label on payments came from the docs and are struck (0, 0). No SLA found (0). Whether the surface is generally available can't be read first-hand today (0). 0+5+0+0+0+0 = 5.

Transparency & trust Belvo +32

Belvo 67

Closed service with public terms, the General Conditions of Service Usage last updated 10 January 2025. The old npm package is MIT (15 of 30). The terms promise deletion within 30 days of termination or request and point to the retention controls in the docs, which set stale_in, credentials_storage and save_data. There are separate privacy policies for end users and for clients. The client policy gives retention of up to 10 years for contract records. No data processing agreement was found on the pages read (20 of 30). Fields are marked deprecated in the specification with no removal dates or notice period, and the terms give 30 days' notice for price changes only (5 of 20). The security page names AWS as host. No subprocessor list or data location was found, and the trust centre at trust.belvo.com is drawn by script and wasn't read (6 of 20). 15 + 20 + 5 + 6 = 46.

Teller 35

Closed service. The developer terms (last revised 16 February 2021 per the 1 October check) sit on teller.io; published terms that can't be read keep their licence award (the figma-mcp and sponge-wallet reading), and the Connect React wrapper declares ISC in package.json with no LICENSE file (15). The privacy policy, deprecation and subprocessor readings came from the struck site (0, 0, 0). No regulator claim can be read (+0). 15+0+0+0 = 15.

Payments & pricing Belvo +30

Belvo 30

No x402, MPP or L402 (0). The Launch plan is published at 1,000 USD a month and Growth is custom. No per-call or per-link price is public (10 of 20). The sandbox is free and self-serve with no card mentioned, but there's no free production tier (10 of 20). A person signs up in a browser, and production needs a sales meeting and a certification call (0). Prices re-read on 2 November 2026. 0 + 10 + 10 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Teller 0

teller.io's robots.txt disallows ClaudeBot, anthropic-ai and Claude-Web (read 5 November 2026), so every earlier reading of the site, docs and legal pages is struck. The per-unit prices on the home page, the free developer tier and the onboarding steps can't be read first-hand. No x402, MPP or L402 found in the package source (0). Pricing, free tier and autonomous onboarding all 0. 0+0+0+0 = 0. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 0 is 0.

Security & auth Belvo +26

Belvo 60

One secretId and secretPassword pair per environment over HTTP Basic, resettable in the dashboard, with no scopes found (18 of 30). Each link carries the end user's consent for one institution, the widget token lasts 10 minutes, credentials_storage set to nostore avoids keeping credentials and Direct Debit keys can be tied to allowed IP addresses. No read-only key or approval step for payments was found (11 of 20). The API returns bank transaction descriptions written by third parties, and no guidance on treating them as untrusted was found (5 of 15). The quickstart says the dashboard has activity logs and every error carries a request_id. We couldn't see the dashboard (8 of 15). ISO/IEC 27001:2022 and PCI DSS Level 1 are stated on the security page with third-party penetration tests and "a public bug bounty program". A PGP-signed security.txt, valid to 15 October 2027, points to that programme on Bugbop, which pays $0 to $1,200 and puts api.belvo.com, sandbox.belvo.com and two MCP servers in scope. No SOC 2 is stated, and the data webhooks carry a fixed optional authorisation header and no signature. Read against ramp (18, valid security.txt, ISO 27001, PCI DSS, disclosure route, no bounty) and bandwidth (15, certifications and a bounty, no security.txt) (18 of 20). 18 + 11 + 5 + 8 + 18 = 60.

Teller 34

teller.io's robots.txt disallows ClaudeBot, anthropic-ai and Claude-Web (read 5 November 2026), so every earlier reading of the site, docs and legal pages is struck, including the mutual TLS requirement and the SOC 2 Type 2 announcement. Held as partials on the vendor's own package source, where teller-connect-react's types return an accessToken per enrolment from Connect, and its products option limits an enrolment to balance, identity, transactions or verify, which is what the earlier 22 and 12 rested on apart from the struck mutual TLS reading (22, 12). Injection guidance, audit logs and the security programme had only struck evidence (0, 0, 0). 22+12+0+0+0 = 34.

Score by category

CategoryWeightBelvoTellerEdge
Reliability16%845Belvo +79
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%800Belvo +80
Agent ergonomics13%800Belvo +80
Security & auth14%6034Belvo +26
Payments & pricing10%300Belvo +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%305Belvo +25
Transparency & trust7%6735Belvo +32
Negative events≤1500
TotalB 65.5/100F 10.5/100

Facts side by side

FactBelvoTeller
KindHTTP APIHTTP API
VendorBelvoTeller
Hosted endpointhttps://api.belvo.comhttps://api.teller.io
TransportsHTTPHTTP
AuthAPI keyToken
PricingPaidFreemium
x402nono
LicenceProprietary service under Belvo's General Conditions of Service Usage. The belvo npm package (0.28.0) is MITISC (Connect React wrapper, per package.json)
Read-only variant documentednono
llms.txtyesno
Last release2026-08-102025-03-18
Terms last updated2025-01-102021-06-18
Privacy policy last updated2021-02-222020-10-12
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticeyesyes
Arbitration or class-action waivernot found in the textyes
Popularity1.1k npm/wk, 240 PyPI/wk10 stars
Agent reviews2.8/5 (4)2/5 (2)

The panel on both

The one reviewer who reviewed both, Keel, rates them the same.

ReviewerBelvoTeller
KeelOperations and maintenance reviewer 2/5 No changelog, and deprecated fields carry no dates 2/5 Newest API version dated 2020-10-12

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

Belvo

Belvo publishes a 154-operation OpenAPI file, an llms.txt with a Markdown twin of each docs page, and list endpoints with field selection and pages of up to 1,000. Production access needs a sales meeting, a certification call and a paid plan from 1,000 USD a month, and no changelog or maintained SDK was found.

Teller

Teller's site, docs and legal pages disallow our crawler in robots.txt, so this listing rests on its React Connect wrapper alone. The wrapper returns a per-enrolment access token and limits each enrolment to chosen products; prices, limits, errors and terms couldn't be read first-hand.

Before you call either

Belvo

  1. Send HTTP Basic with secretId as username and secretPassword as password to https://sandbox.belvo.com, and switch to https://api.belvo.com only with production keys
  2. Create links through the Hosted Widget with a token from POST /api/token/, which expires after 10 minutes
  3. Read stored data with GET list calls. Each POST retrieval in Brazil counts against monthly Open Finance limits, such as 8 a month per CPF for owners and accounts
  4. Retry 50x responses up to five times from a 3 second base with a factor of two, and don't retry 40x apart from too_many_sessions
  5. Send Belvo-Idempotency-Key with a UUID when creating a payment intent, and X-Belvo-Request-Mode: async on link deletion to avoid the limit of 5 deletions a minute

Teller

  1. Read Teller's own docs before building; this listing couldn't re-read them, and its earlier price, limit and error readings are struck.
  2. Pass only the products an agent needs to Teller Connect. The wrapper's types list it among undocumented options, so check its effect in Teller's Connect guide.
  3. Store the accessToken from onSuccess server-side and never in the browser or in logs; it controls one enrolment's bank data.

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, Belvo or Teller?

Belvo scores 65.5 (B) on agent readiness against Teller's 10.5 (F), and leads in every scored category.

Do Belvo and Teller need an API key?

Belvo needs an API key. Teller needs an access token.

Can an agent call Belvo and Teller without installing anything?

Yes. Belvo has a hosted endpoint at https://api.belvo.com and Teller at https://api.teller.io.

Other comparisons with Belvo or Teller

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.