Email: Most devs don't know how LLM tokens work

Subject:
Most devs don't know how LLM tokens work
Received:
4/23/2026, 6:24:27 PM
From:
"Matt Pocock (AI Hero)" <matt@aihero.dev>
To:
porch.hat.81@rss.andrealin.it
&lt;!DOCTYPE html&gt;
&lt;html&gt;
&lt;head&gt;
&lt;style&gt;.ck-link { text-decoration: underline; }&lt;/style&gt;
&lt;style&gt;.ck-link { text-decoration: underline; }&lt;/style&gt;
&lt;style&gt;@media only screen { .email * { word-break: break-word; } }
@media screen and (max-width: 384px) { .mail-message-content { width: 414px !important; } }
@media only screen { .email * { word-break: break-word; } }
@media screen and (max-width: 384px) { .mail-message-content { width: 414px !important; } }
@media only screen and (max-width:600px) { .ck-mobile-font-size { font-size:50px !important; }  }
@media only screen and (max-width:600px) { .ck-mobile-font-size { font-size:50px !important; }  }&lt;/style&gt;
&lt;meta http-equiv="Content-Type" content="text/html; charset=UTF-8"&gt;
&lt;/head&gt;
&lt;body style="margin:0;padding:0;-webkit-font-smoothing:antialiased;-ms-text-size-adjust:100%;-webkit-text-size-adjust:100%"&gt;
&lt;div class="email" style="margin-left:18px;margin-right:18px"&gt;
&lt;table cellpadding="0" cellspacing="0" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt;width:100%;margin:0 auto"&gt;&lt;tbody&gt;&lt;tr&gt;&lt;td style="vertical-align:top"&gt;
&lt;div&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Hey Andrea,&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;I've been thinking a lot more about the fundamentals of LLMs - and it dawned on me recently that most devs don't even know what tokens are.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;If that's you - no shame. Here's an email to get you up to speed.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Tokens are the fundamental building blocks that help Large Language Models (LLMs) process text. Understanding them is essential, especially since you're billed based on token usage.&lt;/p&gt;
&lt;h2 style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.5em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;What Are Tokens?&lt;/h2&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Tokens are simply numbers that represent how the LLM "thinks" about the text you provide. The process of converting text into tokens is called &lt;strong&gt;encoding&lt;/strong&gt;.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;The tokenization process works in two parts:&lt;/p&gt;
&lt;ol style="margin:1em 0;margin-left:1em;padding:0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;list-style-position:outside !important"&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;The tokenizer splits text into tokens it recognizes&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;These tokens are converted into numbers&lt;/li&gt;
&lt;/ol&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;img width="400px" src="https://res.cloudinary.com/total-typescript/image/upload/v1758555807/aihero.dev/emails/tokens/encoding.png" alt="Encoding" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Decoding is the reverse process:&lt;/p&gt;
&lt;ol style="margin:1em 0;margin-left:1em;padding:0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;list-style-position:outside !important"&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;Numbers are converted back into text tokens&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;The tokens are joined together to form the output&lt;/li&gt;
&lt;/ol&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;img width="400px" src="https://res.cloudinary.com/total-typescript/image/upload/v1758555807/aihero.dev/emails/tokens/decoding.png" alt="Decoding" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;&lt;/p&gt;
&lt;h2 style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.5em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;The LLM Process Flow&lt;/h2&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;The complete LLM process looks like this:&lt;/p&gt;
&lt;ol style="margin:1em 0;margin-left:1em;padding:0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;list-style-position:outside !important"&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;Tokenizer encodes your input text into tokens&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;LLM processes your tokens&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;LLM produces output tokens&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;Output tokens are decoded back into readable text&lt;/li&gt;
&lt;/ol&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;img width="400px" src="https://res.cloudinary.com/total-typescript/image/upload/v1758555807/aihero.dev/emails/tokens/llm-process.png" alt="LLM Process Flow" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;To clarify, input tokens include:&lt;/p&gt;
&lt;ul style="margin:1em 0;margin-left:1em;padding:0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;list-style-position:outside !important"&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;Your conversation history with the LLM&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;System prompts&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;Tool definitions&lt;/li&gt;
&lt;/ul&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Output tokens are what the LLM sends back as a response.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;You're billed for both input and output tokens, typically at different rates. One way to save money is to design your prompts to generate fewer output tokens.&lt;/p&gt;
&lt;h2 style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.5em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;How Tokens Are Created&lt;/h2&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;The tokenization process starts with a large corpus of text - similar to what's used to train the LLM itself. Let's imagine a tiny corpus consisting of just one sentence: "the cat sat on the mat."&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;img width="400px" src="https://res.cloudinary.com/total-typescript/image/upload/v1758555808/aihero.dev/emails/tokens/tokenizer-training.png" alt="Tokenization" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;First, all individual characters are extracted:&lt;/p&gt;
&lt;pre class="hljs"&gt;&lt;code&gt;T H E space C A T space S A T space O N space T H E space M A T
&lt;/code&gt;&lt;/pre&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Each of these characters becomes its own token in the vocabulary.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Next, common groupings of characters are identified:&lt;/p&gt;
&lt;ul style="margin:1em 0;margin-left:1em;padding:0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;list-style-position:outside !important"&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;"TH" appears in "the" (twice)&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;"HE" appears in "the" (twice)&lt;/li&gt;
&lt;li style="padding:0 0 0 1em;margin:0;margin-left:1em"&gt;"AT" appears in "cat", "sat", and "mat"&lt;/li&gt;
&lt;/ul&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Each of these groupings also gets assigned its own token.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Then, groups of groups are identified - like "TH" + "HE" creating "THE" (the word "the"), which gets its own token.&lt;/p&gt;
&lt;h2 style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.5em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;Vocabulary Size Matters&lt;/h2&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;The goal is to create a large vocabulary of tokens because larger vocabularies can split words into fewer tokens, making processing more efficient.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;img width="400px" src="https://res.cloudinary.com/total-typescript/image/upload/v1758555808/aihero.dev/emails/tokens/vocabulary-size.png" alt="Vocabulary Size" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;For example, a vocabulary size of 1,000 tokens might split "understanding" into 5 tokens. A vocabulary size of 50,000 tokens might split it into 3 tokens, and a vocabulary size of 200,000 tokens might split it into 2 tokens.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Having a larger vocabulary means you can split words into fewer tokens, making processing more efficient.&lt;/p&gt;
&lt;h2 style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.5em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;Handling Unusual Words&lt;/h2&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;The tokenizer struggles with uncommon words. For example, "O Frabjous Day" from Lewis Carroll's poem gets split into many tokens because "Frabjous" is a made-up word that doesn't appear frequently in the training corpus.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;img width="400px" src="https://res.cloudinary.com/total-typescript/image/upload/v1758555807/aihero.dev/emails/tokens/unusual-words.png" alt="Unusual Words" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;We can see that it turns it into 7 tokens - more than we'd expect from only 15 characters.&lt;/p&gt;
&lt;h2 style="font-weight:bold;font-style:normal;font-size:1em;margin:0;font-size:1.5em;margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#000000;line-height:1.5"&gt;Final Thoughts&lt;/h2&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;I hope that helps demystify tokens a bit. I found the &lt;a href="https://7751c435.click.kit-mail3.com/p9u2lvnpmmtqu35z7zkfqhpqekqzehrhkk55z/reh8h9umz3me60t2/aHR0cHM6Ly90aWt0b2tlbml6ZXIudmVyY2VsLmFwcC8=" style="color:#0875c1" url-id="1848120104"&gt;tiktokenizer playground&lt;/a&gt; really useful for understanding this stuff.&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Let me know if you have any questions - and what else would you like me to cover next?&lt;/p&gt;
&lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;Matt&lt;/p&gt;
&lt;/div&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;/p&gt;
&lt;/td&gt;&lt;/tr&gt;&lt;/tbody&gt;&lt;/table&gt;
&lt;div class="email-footer"&gt;&lt;table cellpadding="0" cellspacing="0" style="border-collapse:separate;mso-table-lspace:0pt;mso-table-rspace:0pt;width:100%;margin:0 auto"&gt;&lt;tbody&gt;&lt;tr&gt;&lt;td style="vertical-align:top"&gt;
&lt;div&gt;&lt;div class="email-footer" style="color:#4b4b4b"&gt;
  &lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;color:#4b4b4b; margin:1em 0;font-family:Arial,-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;;font-size:12px;line-height:1.5;display:block;margin:13px 0;"&gt;&lt;a href="https://7751c435.click.kit-mail3.com/p9u2lvnpmmtqu35z7zkfqhpqekqzehrhkk55z/g3h72p2wcwumwlmkqmcr/aHR0cHM6Ly93d3cudG90YWx0eXBlc2NyaXB0LmNvbS91bnN1YnNjcmliZWQ_c2VxdWVuY2U9YWlfaGVybw==" trigger-id="5153768" style="color:#0875c1" url-id="1848120105"&gt;Unsubscribe from AI Hero Emails&lt;/a&gt;. You can also &lt;a href="https://7751c435.unsubscribe.kit-mail3.com/p9u2lvnpmmtqu35z7zkfqhpqekqzehrhkk55z" style="color:#0875c1"&gt;&lt;span style="font-size:12px"&gt;unsubscribe&lt;/span&gt;&lt;/a&gt;&lt;span style="font-size:12px"&gt; from all emails at any time.&lt;/span&gt;&lt;/p&gt;
  &lt;p style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5;color:#4b4b4b; margin:1em 0;font-family:Arial,-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;;line-height:1.5;display:block;margin:13px 0;"&gt;&lt;span style="font-size:10px"&gt;12333 Sowden Rd, Ste. B, PMB #97429, Houston, TX 77080&lt;/span&gt;&lt;/p&gt;
&lt;/div&gt;&lt;/div&gt;
&lt;p class="" style="margin:1em 0;font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen-Sans,Ubuntu,Cantarell,'Helvetica Neue',sans-serif;color:#2d2d2f;font-size:16px;line-height:1.5"&gt;&lt;/p&gt;
&lt;/td&gt;&lt;/tr&gt;&lt;/tbody&gt;&lt;/table&gt;&lt;/div&gt;
&lt;/div&gt;
&lt;!-- --&gt;
&lt;img src="https://7751c435.open.kit-mail3.com/p9u2lvnpmmtqu35z7zkfqhpqekqzehrhkk55z" alt="" style="border:0 none;display:block;height:auto;line-height:100%;outline:none;-webkit-text-decoration:none;text-decoration:none;max-width:100%"&gt;
&lt;/body&gt;
&lt;/html&gt;
Email Content
