Md Sabirul Islam This workflow corresponds to n8n.io template #8221 — we link there as the canonical source.
This workflow follows the Agent → HTTP Request recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "Qhd5ZE0WdsOiFQqj",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "AI Chef",
"tags": [],
"nodes": [
{
"id": "525c226c-d024-4e37-8052-a2b3a0996bf1",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
48,
240
],
"parameters": {
"model": "openai/gpt-4o-mini",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "1bd83992-eb8c-4aea-8888-878cd67f8a50",
"name": "Window Buffer Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
208,
240
],
"parameters": {
"sessionKey": "={{ $json.message.chat.id }}",
"sessionIdType": "customKey",
"contextWindowLength": 200
},
"typeVersion": 1.3
},
{
"id": "77562a10-731c-4c6a-a938-5f61c8e74266",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
0,
0
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "dfc79eec-88ac-4c6f-b189-4c07f782c0fa",
"name": "Send a text message",
"type": "n8n-nodes-base.telegram",
"position": [
512,
0
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "a09f687d-3943-4787-a19e-5163be6bdf75",
"name": "Nano \ud83c\udf4c",
"type": "n8n-nodes-base.httpRequest",
"position": [
1056,
0
],
"parameters": {
"url": "https://openrouter.ai/api/v1/chat/completions",
"method": "POST",
"options": {},
"jsonBody": "={\n \"model\": \"google/gemini-2.5-flash-image-preview:free\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"Generate a photorealistic image of {{ $json.output }}\"\n }\n ]\n }\n ]\n}\n",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "predefinedCredentialType",
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer $OPENROUTER_API_KEY"
}
]
},
"nodeCredentialType": "openRouterApi"
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "a51cdb6b-d997-4f6a-a75a-12f6e249a680",
"name": "Edit Fields",
"type": "n8n-nodes-base.set",
"position": [
1248,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "6355ac9e-1f4c-42a3-8167-8bb8298cd369",
"name": "data",
"type": "string",
"value": "={{ $json.choices[0].message.images[0].image_url.url }}"
},
{
"id": "dc98bc1c-4048-4fcb-80c5-73dc99b78ddd",
"name": "base",
"type": "string",
"value": "={{ $json.choices[0].message.images[0].image_url.url.split(',')[1] }}"
},
{
"id": "8033a47e-f50c-43ae-b404-99d0fb5cf4eb",
"name": "mime",
"type": "string",
"value": "={{ $json.choices[0].message.images[0].image_url.url.split(';')[0].split(':')[1] }}"
},
{
"id": "0e516163-02cc-4242-ba70-ac2bce94d2dd",
"name": "fileName",
"type": "string",
"value": ".png"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "bf15ba16-f228-4df1-a5f2-48dd3eceb2af",
"name": "Convert to File",
"type": "n8n-nodes-base.convertToFile",
"position": [
1152,
240
],
"parameters": {
"options": {},
"operation": "toBinary",
"sourceProperty": "base"
},
"typeVersion": 1.1
},
{
"id": "0b449fab-316d-4379-88cc-5ff4136149e0",
"name": "OpenRouter Chat Model1",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
592,
272
],
"parameters": {
"model": "openai/gpt-4o-mini",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "d02178f2-962f-4dcd-978a-fffa8564ae1c",
"name": "Send a photo message",
"type": "n8n-nodes-base.telegram",
"position": [
1360,
240
],
"parameters": {
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"operation": "sendPhoto",
"binaryData": true,
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "24ceeec0-77af-441b-b479-62a3608effd8",
"name": "AI Recipe",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
208,
0
],
"parameters": {
"text": "={{ $json.message.text }}",
"options": {
"systemMessage": "You are a friendly and professional Virtual Chef Assistant. \nYour role is to help users with cooking, recipes, meal planning, food substitutions, nutrition tips, and step-by-step cooking guidance. \n\nGuidelines:\n- Always reply in a clear, simple, and conversational tone. \n- Suggest recipes based on available ingredients, dietary preferences, or cuisine styles. \n- Provide step-by-step cooking instructions when asked. \n- Offer ingredient substitutions if something is missing. \n- Give nutrition advice when relevant, but do not provide medical advice. \n- Be creative, encouraging, and make cooking feel fun and easy. \n- If the user asks for meal plans, suggest balanced options (breakfast, lunch, dinner, snacks). \n- If the user asks general questions about food or cooking techniques, explain in an easy-to-understand way. \n- Do not provide unsafe cooking practices or harmful instructions. \n\nYour personality:\n- Warm, supportive, and encouraging like a personal chef. \n- Use a mix of professional cooking knowledge and friendly conversation. \n- Adapt tone depending on user: beginner = simple steps, experienced = more advanced techniques."
},
"promptType": "define"
},
"typeVersion": 2.2
},
{
"id": "9d5b6784-261d-41a7-8f51-87298625ec2e",
"name": "Restaurant-Style Plating prompt",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
688,
0
],
"parameters": {
"text": "={{ $('AI Recipe').item.json.output }}",
"options": {
"systemMessage": "You are an expert AI prompt generator for text-to-image models. \nYour task is to read the recipe text provided and generate a single, clear, and detailed prompt suitable for a photorealistic image generation AI. \nDo not explain the recipe, do not add extra commentary, and do not output anything else except the image prompt. \n\nFocus only on visual details:\n- How the dish looks on a plate\n- Plating style and arrangement\n- Colors, textures, garnishes\n- Lighting and perspective\n- Use only plates and dishware typically found in professional restaurants (white ceramic, slate, glass, or elegant serving dishes)\n- Make it look like a high-end restaurant presentation\n\nThe output should be concise, a single paragraph of text, fully descriptive, ready to feed directly into an image generation model and output should be in English."
},
"promptType": "define"
},
"typeVersion": 2.2
},
{
"id": "3a28861d-d7cb-490a-b8a5-aa48c0846a43",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-592,
-272
],
"parameters": {
"width": 496,
"height": 464,
"content": "## AI Chef Bot \u2013 Recipe + Food Image Generator \nImport this workflow into your n8n instance.\n\nConfigure your Telegram Bot Token (from BotFather).\n\nConfigure your OpenRouter API Key for AI text + image generation.\n\nSave and activate the workflow.\n\nGo to Telegram and send any dish name (e.g., Polpette di pesce).\n\nThe bot replies with:\n\n\ud83d\udcd6 A full recipe.\n\n\ud83d\udcf8 A restaurant-plated realistic food image."
},
"typeVersion": 1
}
],
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "4c3ecc19-e40d-4dfd-ba47-4c66aaade24e",
"connections": {
"AI Recipe": {
"main": [
[
{
"node": "Send a text message",
"type": "main",
"index": 0
}
]
]
},
"Nano \ud83c\udf4c": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Convert to File",
"type": "main",
"index": 0
}
]
]
},
"Convert to File": {
"main": [
[
{
"node": "Send a photo message",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "AI Recipe",
"type": "main",
"index": 0
}
]
]
},
"Send a text message": {
"main": [
[
{
"node": "Restaurant-Style Plating prompt",
"type": "main",
"index": 0
}
]
]
},
"Window Buffer Memory": {
"ai_memory": [
[
{
"node": "AI Recipe",
"type": "ai_memory",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Recipe",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenRouter Chat Model1": {
"ai_languageModel": [
[
{
"node": "Restaurant-Style Plating prompt",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Restaurant-Style Plating prompt": {
"main": [
[
{
"node": "Nano \ud83c\udf4c",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
openRouterApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI Chef Bot is a smart virtual chef built with n8n and Telegram. Users can ask for any dish, and the bot:
Source: https://n8n.io/workflows/8221/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Arvifund - Supabase (Fixed v6). Uses httpRequest, telegram, supabase, telegramTrigger. Event-driven trigger; 92 nodes.
HTTP Request, Telegram, Supabase +8
Arvifund - Supabase (Fixed v5). Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 91 nodes.
HTTP Request, Telegram, Google Sheets +9
Arvifund - Supabase. Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 90 nodes.
HTTP Request, Telegram, Google Sheets +8
Arvifund - Supabase (Fixed v2). Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 90 nodes.
HTTP Request, Telegram, Google Sheets +9
Arvifund - Supabase (Fixed v4). Uses httpRequest, telegram, googleSheets, telegramTrigger. Event-driven trigger; 90 nodes.
HTTP Request, Telegram, Google Sheets +9