diff --git a/src/renderer/src/hooks/useQuickCompletion.ts b/src/renderer/src/hooks/useQuickCompletion.ts
new file mode 100644
index 0000000000..1b049162d6
--- /dev/null
+++ b/src/renderer/src/hooks/useQuickCompletion.ts
@@ -0,0 +1,48 @@
+import { fetchChatCompletion } from '@renderer/services/ApiService'
+import { getDefaultAssistant } from '@renderer/services/AssistantService'
+import type { Assistant, FetchChatCompletionParams } from '@renderer/types'
+import type { Chunk } from '@renderer/types/chunk'
+import { useCallback } from 'react'
+
+import { useDefaultModel } from './useAssistant'
+
+/**
+ * Parameters for performing a quick completion using the quick model.
+ */
+export type QuickCompletionParams = {
+  /**
+   * The prompt text to send to the model.
+   */
+  prompt: string
+  /**
+   * Callback invoked whenever a new chunk of the streaming response arrives.
+   */
+  onChunk: (chunk: Chunk) => void
+  /**
+   * Optional partial assistant settings to override the default quick assistant.
+   */
+  assistantUpdate?: Partial<Assistant>
+  /**
+   * Optional additional parameters to pass to the underlying fetchChatCompletion call.
+   * Excludes prompt, messages, assistant, and onChunkReceived which are handled internally.
+   */
+  params?: Partial<Omit<FetchChatCompletionParams, 'prompt' | 'messages' | 'assistant' | 'onChunkReceived'>>
+}
+
+export const useQuickCompletion = () => {
+  const { quickModel } = useDefaultModel()
+
+  const completion = useCallback(
+    async ({ prompt, onChunk, assistantUpdate, params }: QuickCompletionParams) => {
+      const assistant = {
+        ...getDefaultAssistant(),
+        model: quickModel,
+        ...assistantUpdate
+      } satisfies Assistant
+      return fetchChatCompletion({ prompt, assistant, onChunkReceived: onChunk, ...params })
+    },
+    [quickModel]
+  )
+
+  return completion
+}