Skip to content
What Agents Pick

does Claude Code default to raw SMTP for email?

yes, mostly. Raw SMTP in 24 of 36 email runs across Opus 5.5, Sonnet 5.5 and Haiku 5.5 (67%), more than any other pick. by model: Opus 5.5 7 of 12, Sonnet 5.5 10 of 12, Haiku 5.5 7 of 12.

24 of 36 email runsrank 1 of 3 picksupdated Oct 18, 2026all email results

get told if Raw SMTP starts getting picked

new models get the same email prompts every week. one email with what moved. free. read issue 1

by model

Claude Code, same prompts and starter repos for every model.

  1. Opus 5.57 of 1258%
  2. Sonnet 5.510 of 1283%
  3. Haiku 5.57 of 1258%

by starter stack

  1. Next.js + TypeScript7 of 1839%
  2. Python + FastAPI17 of 1894%

every email result

all models pooled, 36 scored runs. most common: Raw SMTP, 24 of 36.

  1. Raw SMTP24 of 3667%
  2. Resend11 of 3631%
  3. Postmark1 of 363%
  4. built its own, any form24 of 3667%
Which email API do coding agents pick? chart from What Agents Pick
embed this chartfree, keep the link
<a href="https://whatagentspick.com/tools/raw-smtp/"><img src="https://whatagentspick.com/share/email.png" alt="does Claude Code default to raw SMTP for email? 24 of 36 runs" width="600" height="315" style="max-width:100%;height:auto" loading="lazy"></a>
<p><a href="https://whatagentspick.com/tools/raw-smtp/">data: what agents pick</a></p>
how embeds work

the prompts

none of them name a tool. Raw SMTP per wording.

  1. “The app needs to send a welcome email when someone signs up. Wire up email sending and add the template.”

    Raw SMTP: 7 of 12 runs

  2. “Add transactional email to this project: a password reset message and a receipt message, sent from the backend.”

    Raw SMTP: 8 of 12 runs

  3. “I need to email users from this app. Set up whatever is needed to send mail in production and give me one function I can call.”

    Raw SMTP: 9 of 12 runs

other email tools we check for

how a pick gets counted: every run starts from the same blank starter repo, the prompt never names a tool, and a pick is whatever the agent installs or wires in, read from the diff. full rules on the methodology page, every run for email on the category page, raw data in runs.json.