diff --git a/README.md b/README.md
index 6591805..faeaaa1 100644
--- a/README.md
+++ b/README.md
@@ -165,7 +165,15 @@ The number of commit messages to generate to pick from.
 
 Note, this will use more tokens as it generates more results.
 
-This can also be configured with the CLI flag `--generate`.
+#### proxy
+
+Set a HTTP/HTTPS proxy to use for requests.
+
+To clear the proxy option, you can use the command (note the empty value after the equals sign):
+
+```sh
+aicommits config set proxy=
+```
 
 ## How it works
 
diff --git a/package.json b/package.json
index e1fd30b..370948a 100644
--- a/package.json
+++ b/package.json
@@ -46,6 +46,7 @@
 		"eslint": "^8.35.0",
 		"execa": "^7.0.0",
 		"fs-fixture": "^1.2.0",
+		"https-proxy-agent": "^5.0.1",
 		"ini": "^3.0.1",
 		"kolorist": "^1.7.0",
 		"lint-staged": "^13.1.2",
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 16aec88..cf51dd5 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -17,6 +17,7 @@ specifiers:
   eslint: ^8.35.0
   execa: ^7.0.0
   fs-fixture: ^1.2.0
+  https-proxy-agent: ^5.0.1
   ini: ^3.0.1
   kolorist: ^1.7.0
   lint-staged: ^13.1.2
@@ -41,6 +42,7 @@ devDependencies:
   eslint: 8.35.0
   execa: 7.0.0
   fs-fixture: 1.2.0
+  https-proxy-agent: 5.0.1
   ini: 3.0.1
   kolorist: 1.7.0
   lint-staged: 13.1.2
@@ -787,6 +789,15 @@ packages:
     hasBin: true
     dev: true
 
+  /agent-base/6.0.2:
+    resolution: {integrity: sha512-RZNwNclF7+MS/8bDg70amg32dyeZGZxiDuQmZxKLAlQjr3jGyLx+4Kkk58UO7D2QdgFIQCovuSuZESne6RG6XQ==}
+    engines: {node: '>= 6.0.0'}
+    dependencies:
+      debug: 4.3.4
+    transitivePeerDependencies:
+      - supports-color
+    dev: true
+
   /aggregate-error/3.1.0:
     resolution: {integrity: sha512-4I7Td01quW/RpocfNayFdFVk1qSuoh0E7JrbRJ16nH01HhKFQ88INq9Sd+nd72zqRySlr9BmDA8xlEJ6vJMrYA==}
     engines: {node: '>=8'}
@@ -2074,6 +2085,16 @@ packages:
     resolution: {integrity: sha512-mxIDAb9Lsm6DoOJ7xH+5+X4y1LU/4Hi50L9C5sIswK3JzULS4bwk1FvjdBgvYR4bzT4tuUQiC15FE2f5HbLvYw==}
     dev: true
 
+  /https-proxy-agent/5.0.1:
+    resolution: {integrity: sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==}
+    engines: {node: '>= 6'}
+    dependencies:
+      agent-base: 6.0.2
+      debug: 4.3.4
+    transitivePeerDependencies:
+      - supports-color
+    dev: true
+
   /human-signals/3.0.1:
     resolution: {integrity: sha512-rQLskxnM/5OCldHo+wNXbpVgDn5A17CUoKX+7Sokwaknlq7CdSnphy0W39GU8dw59XiCXmFXDg4fRuckQRKewQ==}
     engines: {node: '>=12.20.0'}
diff --git a/src/commands/aicommits.ts b/src/commands/aicommits.ts
index 2ca21b7..bb51adf 100644
--- a/src/commands/aicommits.ts
+++ b/src/commands/aicommits.ts
@@ -35,8 +35,10 @@ export default async (
 		staged.files.map(file => `     ${file}`).join('\n')
 	}`);
 
+	const { env } = process;
 	const config = await getConfig({
-		OPENAI_KEY: process.env.OPENAI_KEY ?? process.env.OPENAI_API_KEY,
+		OPENAI_KEY: env.OPENAI_KEY || env.OPENAI_API_KEY,
+		proxy: env.https_proxy || env.HTTPS_PROXY || env.http_proxy || env.HTTP_PROXY,
 		generate: generate?.toString(),
 	});
 
@@ -49,6 +51,7 @@ export default async (
 			config.locale,
 			staged.diff,
 			config.generate,
+			config.proxy,
 		);
 	} finally {
 		s.stop('Changes analyzed');
diff --git a/src/commands/prepare-commit-msg-hook.ts b/src/commands/prepare-commit-msg-hook.ts
index 57d3ae8..5179902 100644
--- a/src/commands/prepare-commit-msg-hook.ts
+++ b/src/commands/prepare-commit-msg-hook.ts
@@ -30,7 +30,10 @@ export default () => (async () => {
 
 	intro(bgCyan(black(' aicommits ')));
 
-	const config = await getConfig();
+	const { env } = process;
+	const config = await getConfig({
+		proxy: env.https_proxy || env.HTTPS_PROXY || env.http_proxy || env.HTTP_PROXY,
+	});
 
 	const s = spinner();
 	s.start('The AI is analyzing your changes');
@@ -41,6 +44,7 @@ export default () => (async () => {
 			config.locale,
 			staged!.diff,
 			config.generate,
+			config.proxy,
 		);
 	} finally {
 		s.stop('Changes analyzed');
diff --git a/src/utils/config.ts b/src/utils/config.ts
index d029e9a..d3e0bef 100644
--- a/src/utils/config.ts
+++ b/src/utils/config.ts
@@ -51,6 +51,15 @@ const configParsers = {
 
 		return parsed;
 	},
+	proxy(url?: string) {
+		if (!url || url.length === 0) {
+			return undefined;
+		}
+
+		parseAssert('proxy', /^https?:\/\//.test(url), 'Must be a valid URL');
+
+		return url;
+	},
 } as const;
 
 type ConfigKeys = keyof typeof configParsers;
diff --git a/src/utils/openai.ts b/src/utils/openai.ts
index 17cff90..59682c0 100644
--- a/src/utils/openai.ts
+++ b/src/utils/openai.ts
@@ -2,6 +2,7 @@ import https from 'https';
 import type { ClientRequest, IncomingMessage } from 'http';
 import type { CreateChatCompletionRequest, CreateChatCompletionResponse } from 'openai';
 import { encoding_for_model as encodingForModel } from '@dqbd/tiktoken';
+import createHttpsProxyAgent from 'https-proxy-agent';
 import { KnownError } from './error.js';
 
 const httpsPost = async (
@@ -9,6 +10,7 @@ const httpsPost = async (
 	path: string,
 	headers: Record<string, string>,
 	json: unknown,
+	proxy?: string,
 ) => new Promise<{
 	request: ClientRequest;
 	response: IncomingMessage;
@@ -27,6 +29,11 @@ const httpsPost = async (
 				'Content-Length': Buffer.byteLength(postContent),
 			},
 			timeout: 10_000, // 10s
+			agent: (
+				proxy
+					? createHttpsProxyAgent(proxy)
+					: undefined
+			),
 		},
 		(response) => {
 			const body: Buffer[] = [];
@@ -53,6 +60,7 @@ const httpsPost = async (
 const createChatCompletion = async (
 	apiKey: string,
 	json: CreateChatCompletionRequest,
+	proxy?: string,
 ) => {
 	const { response, data } = await httpsPost(
 		'api.openai.com',
@@ -61,6 +69,7 @@ const createChatCompletion = async (
 			Authorization: `Bearer ${apiKey}`,
 		},
 		json,
+		proxy,
 	);
 
 	if (
@@ -97,6 +106,7 @@ export const generateCommitMessage = async (
 	locale: string,
 	diff: string,
 	completions: number,
+	proxy?: string,
 ) => {
 	const prompt = getPrompt(locale, diff);
 
@@ -109,20 +119,24 @@ export const generateCommitMessage = async (
 	}
 
 	try {
-		const completion = await createChatCompletion(apiKey, {
-			model,
-			messages: [{
-				role: 'user',
-				content: prompt,
-			}],
-			temperature: 0.7,
-			top_p: 1,
-			frequency_penalty: 0,
-			presence_penalty: 0,
-			max_tokens: 200,
-			stream: false,
-			n: completions,
-		});
+		const completion = await createChatCompletion(
+			apiKey,
+			{
+				model,
+				messages: [{
+					role: 'user',
+					content: prompt,
+				}],
+				temperature: 0.7,
+				top_p: 1,
+				frequency_penalty: 0,
+				presence_penalty: 0,
+				max_tokens: 200,
+				stream: false,
+				n: completions,
+			},
+			proxy,
+		);
 
 		return deduplicateMessages(
 			completion.choices