Get an audit

Head to head · Messaging sms · October 2026 research run

AWS End User Messaging vs Sendblue

AWS End User Messaging scores 74.3 (BB) on agent readiness against Sendblue's 61.7 (C), and leads in 5 of 7 scored categories. Sendblue leads on agent ergonomics and payments & pricing. Both do messaging sms.

AWS End User MessagingAmazon Web Services · HTTP API BB74.3/100#64 of 722 SendblueRound One, Inc. · HTTP API C61.7/100#358 of 722

Which one, for what

AWS End User Messaging BB

Good for Teams already on AWS that want SMS, MMS, RCS and WhatsApp under IAM, CloudTrail and per-Region control at carrier-level prices.

Ahead on

  • Schema & documentation, 88 against 66
  • Security & auth, 88 against 46
  • Maintenance & community, 85 against 72
  • Transparency & trust, 83 against 58

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

Sandbox limits new accounts to $1 of SMS a month and ten verified numbers until a support case per Region is approved

Sendblue C

Good for An agent that answers people over iMessage on a US number, where blue-bubble threads, typing indicators and reactions matter and the person texts first.

Ahead on

  • Agent ergonomics, 76 against 71
  • Payments & pricing, 40 against 30

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

Proactive outbound messaging needs the Blue Ocean plan, which has no public price. The $100 AI Agent plan is inbound-first

Score by category

CategoryWeight this runAWS End User MessagingSendblueEdge
Reliability16%207371AWS End User Messaging +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28866AWS End User Messaging +22
Agent ergonomics13%16.27176Sendblue +5
Security & auth14%17.58846AWS End User Messaging +42
Payments & pricing10%12.53040Sendblue +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88572AWS End User Messaging +13
Transparency & trust7%8.88358AWS End User Messaging +25
Negative events≤1500
Total74.3 · BB61.7 · C

Facts side by side

FactAWS End User MessagingSendblue
KindHTTP APIHTTP API
VendorAmazon Web ServicesRound One, Inc.
Hosted endpointhttps://sms-voice.us-east-1.amazonaws.comhttps://api.sendblue.com
TransportsHTTPHTTP, stdio
AuthOAuth or keyAPI key
PricingPay per useFreemium
Price for messaging sms$0.0077 per messagenot published
x402nono
LicenceProprietary service under the AWS Customer Agreement. The AWS SDKs are Apache-2.0Proprietary service under Round One, Inc.'s terms of service. The TypeScript and Python SDKs and the MCP server are Apache-2.0, and the CLI is MIT
Tools exposednone18
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-062026-10-07
Terms last updated2026-08-142025-03-19
Privacy policy last updated2026-05-182024-05-01
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 textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesyes
Popularity407k npm/wk250k npm/wk, 40k PyPI/wk

Verdicts

AWS End User Messaging

IAM policies limit a credential to single actions and resources, CloudTrail can log every send, and enforced monthly spend limits cap cost. New accounts start in a sandbox with a $1 monthly SMS limit and ten verified recipients, production access needs a support case per Region, and the send actions take no idempotency token.

Sendblue

Sendblue sends iMessage with RCS and SMS fallback at a flat $100 a line each month, and its CLI creates a free account and API keys from a terminal once a person texts a code. Proactive outbound messaging is sold through sales, no OpenAPI file is published, and the MCP package the docs install dates from August 2025.

Before you call either

AWS End User Messaging

  1. Sign requests with SigV4 for service sms-voice at sms-voice.<region>.amazonaws.com. WhatsApp uses a separate API, social-messaging
  2. Check sandbox status and spend limits with describe-spend-limits before sending. Sandbox sends reach only verified destination numbers
  3. Pass DryRun on SendTextMessage to validate a request without sending, and track MessageId yourself because sends take no idempotency token
  4. Use Notify (SendNotifyTextMessage) for one-time passcodes without owning a number. Generate and check the code in your own application
  5. Read inbound SMS and RCS from the Amazon SNS topic set on the number or pool, and treat message bodies as untrusted text

Sendblue

  1. Send from_number on every request. Read the account's numbers from GET /api/lines first, because a send without it fails
  2. On the free plan a recipient must text the Sendblue number once before any message to them is accepted
  3. Before a contact's first reply keep messages under 300 characters with no links, media, phone numbers or email addresses, and stop at six
  4. Branch on error_key in an HTTP 400 decline and don't retry it. Only HTTP 429 clears by waiting
  5. Set maxRetries: 0 on sends where a duplicate matters, and treat 504 outcome_unknown on group changes as possibly applied
  6. Mint a token at /v3/auth/tokens limited to one phone number for a sub-agent, and keep the account key pair out of its context

Questions

Which is better for AI agents, AWS End User Messaging or Sendblue?

AWS End User Messaging scores 74.3 (BB) on agent readiness against Sendblue's 61.7 (C), and leads in 5 of 7 scored categories. Sendblue leads on agent ergonomics and payments & pricing.

Do AWS End User Messaging and Sendblue need an API key?

AWS End User Messaging takes an API key or an OAuth sign-in. Sendblue needs an API key.

Can an agent call AWS End User Messaging and Sendblue without installing anything?

Yes. AWS End User Messaging has a hosted endpoint at https://sms-voice.us-east-1.amazonaws.com and Sendblue at https://api.sendblue.com.

Other comparisons with AWS End User Messaging or Sendblue

Machine-readable

For companies

Do agents find, use and choose your tools?

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

Get an auditSee a sample report