diff --git a/src/lib/Chat.svelte b/src/lib/Chat.svelte
index 8d1a468..e65c50a 100644
--- a/src/lib/Chat.svelte
+++ b/src/lib/Chat.svelte
@@ -37,6 +37,7 @@
     key: 'model',
     name: 'Model',
     default: 'gpt-3.5-turbo',
+    title: 'The model to use - GPT-3.5 is cheaper, but GPT-4 is more powerful.',
     options: supportedModels,
     type: 'select'
   }
@@ -47,6 +48,9 @@
       key: 'temperature',
       name: 'Sampling Temperature',
       default: 1,
+      title: 'What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\n' +
+              '\n' +
+              'We generally recommend altering this or top_p but not both.',
       min: 0,
       max: 2,
       step: 0.1,
@@ -56,6 +60,9 @@
       key: 'top_p',
       name: 'Nucleus Sampling',
       default: 1,
+      title: 'An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n' +
+              '\n' +
+              'We generally recommend altering this or temperature but not both',
       min: 0,
       max: 1,
       step: 0.1,
@@ -65,6 +72,7 @@
       key: 'n',
       name: 'Number of Messages',
       default: 1,
+      title: 'How many chat completion choices to generate for each input message.',
       min: 1,
       max: 10,
       step: 1,
@@ -73,6 +81,9 @@
     {
       key: 'max_tokens',
       name: 'Max Tokens',
+      title: 'The maximum number of tokens to generate in the completion.\n' +
+              '\n' +
+              'The token count of your prompt plus max_tokens cannot exceed the model\'s context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).\n',
       default: 0,
       min: 0,
       max: 32768,
@@ -83,6 +94,7 @@
       key: 'presence_penalty',
       name: 'Presence Penalty',
       default: 0,
+      title: 'Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model\'s likelihood to talk about new topics.',
       min: -2,
       max: 2,
       step: 0.2,
@@ -92,6 +104,7 @@
       key: 'frequency_penalty',
       name: 'Frequency Penalty',
       default: 0,
+      title: 'Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model\'s likelihood to repeat the same line verbatim.',
       min: -2,
       max: 2,
       step: 0.2,
@@ -538,6 +551,7 @@
                   class="input"
                   inputmode="decimal"
                   type={setting.type}
+                  title="{setting.title}"
                   id="settings-{setting.key}"
                   min={setting.min}
                   max={setting.max}
@@ -546,7 +560,7 @@
                 />
               {:else if setting.type === 'select'}
                 <div class="select">
-                  <select id="settings-{setting.key}">
+                  <select id="settings-{setting.key}" title="{setting.title}">
                     {#each setting.options as option}
                       <option value={option} selected={option === setting.default}>{option}</option>
                     {/each}
diff --git a/src/lib/Types.svelte b/src/lib/Types.svelte
index d570949..3b61517 100644
--- a/src/lib/Types.svelte
+++ b/src/lib/Types.svelte
@@ -60,6 +60,7 @@
   export type Settings = {
     key: string;
     name: string;
+    title: string;
   } & (SettingsNumber | SettingsSelect);
 
   type ResponseOK = {