Solomon This workflow corresponds to n8n.io template #5541 — we link there as the canonical source.
This workflow follows the Agent → Execute Workflow Trigger 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 →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "f78ee73d-3d5e-4162-9b40-74cc183cb59b",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-540,
-520
],
"parameters": {},
"typeVersion": 1
},
{
"id": "9fa5f512-fd5d-4e5b-9d73-f70ec0d4b13d",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-260,
-520
],
"parameters": {
"text": "Help me test something and output the text \"This is a test workflow\" after calling the think tool twice.",
"options": {},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "35e230ce-7413-4675-b2f7-cb837cccf936",
"name": "Call sub-workflow",
"type": "n8n-nodes-base.executeWorkflow",
"position": [
200,
-520
],
"parameters": {
"mode": "each",
"options": {
"waitForSubWorkflow": false
},
"workflowId": {
"__rl": true,
"mode": "id",
"value": "={{ $workflow.id }}"
},
"workflowInputs": {
"value": {
"execution_id": "={{ $execution.id }}"
},
"schema": [
{
"id": "execution_id",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "execution_id",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [
"execution_id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": true
}
},
"typeVersion": 1.2
},
{
"id": "81bf6364-cdb1-47ac-840d-8c7d940bf616",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
60,
-880
],
"parameters": {
"color": 3,
"width": 380,
"height": 540,
"content": "## Wait for the workflow to finish before calling the subworkflow\nIf the execution is still running, too much data is retrieved and it becomes messy.\n\nSo put this node at the end of the workflow and disable the option `Wait For Sub-Workflow Completion`.\n\nThat way you have to retrieve less data and it's easier to retrieve the token usage.\n\n`{{ $workflow.id }}` is an expression to get the current workflow id. Change this if your subworkflow is in a separate file.\n\n"
},
"typeVersion": 1
},
{
"id": "11b56bfb-170d-480a-a478-5022e540a5b5",
"name": "Think",
"type": "@n8n/n8n-nodes-langchain.toolThink",
"position": [
-60,
-280
],
"parameters": {},
"typeVersion": 1
},
{
"id": "2e9101bd-73cb-4fab-91c6-e884ddb51fbf",
"name": "Extract token usage data",
"type": "n8n-nodes-base.set",
"position": [
-100,
180
],
"parameters": {
"include": "selected",
"options": {},
"assignments": {
"assignments": [
{
"id": "2e6b9daf-495c-44e3-a39e-40fc8e654eae",
"name": "execution_id",
"type": "number",
"value": "={{ $('When Executed by Another Workflow').item.json.execution_id }}"
},
{
"id": "1ba39074-c67e-453c-9a64-07e0376e64bf",
"name": "tokenUsage",
"type": "array",
"value": "={{$jmespath(\n $json,\n \"data.resultData.runData.*[] | [?data.ai_languageModel] | [].{model: data.ai_languageModel[0][0].json.response.generations[0][0].generationInfo.model_name || inputOverride.ai_languageModel[0][0].json.options.model_name || inputOverride.ai_languageModel[0][0].json.options.model, tokenUsage: data.ai_languageModel[0][0].json.tokenUsage || data.ai_languageModel[0][0].json.tokenUsageEstimate}\"\n)}}"
}
]
},
"includeFields": "workflowData.id, workflowData.name",
"includeOtherFields": true
},
"typeVersion": 3.4
},
{
"id": "1bbefdea-cd7a-46e4-8b6f-02e3ba7c4569",
"name": "Get execution data",
"type": "n8n-nodes-base.n8n",
"position": [
-320,
180
],
"parameters": {
"options": {
"activeWorkflows": true
},
"resource": "execution",
"operation": "get",
"executionId": "={{ $json.execution_id }}",
"requestOptions": {}
},
"credentials": {
"n8nApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "8cfd62f0-d3a6-4259-ae3f-471b31c177e6",
"name": "When Executed by Another Workflow",
"type": "n8n-nodes-base.executeWorkflowTrigger",
"position": [
-540,
180
],
"parameters": {
"workflowInputs": {
"values": [
{
"name": "execution_id"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "6acea4e7-3fc9-4f11-8a2e-631ab187a66d",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-840,
160
],
"parameters": {
"color": 7,
"height": 180,
"content": "After the main workflow calls the subworkflow, you'll be able to see the total tokens in the Executions spreadsheet."
},
"typeVersion": 1
},
{
"id": "88253810-84bb-4640-9fb9-9da116d10f4f",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
120,
180
],
"parameters": {
"include": "allOtherFields",
"options": {},
"fieldToSplitOut": "tokenUsage"
},
"typeVersion": 1
},
{
"id": "c91c32de-6357-47ee-abaf-fbf639362b1e",
"name": "Sum Token Totals - aggregate by model",
"type": "n8n-nodes-base.summarize",
"position": [
320,
180
],
"parameters": {
"options": {},
"fieldsToSplitBy": "id, name, tokenUsage.model, execution_id",
"fieldsToSummarize": {
"values": [
{
"field": "tokenUsage.tokenUsage.promptTokens",
"aggregation": "sum"
},
{
"field": "tokenUsage.tokenUsage.completionTokens",
"aggregation": "sum"
}
]
}
},
"typeVersion": 1.1
},
{
"id": "022cd2fc-3d1c-43fd-910e-02af46eeb4fa",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
740,
-240
],
"parameters": {
"color": 7,
"width": 660,
"height": 580,
"content": "## Limitations\n### 1. This workflow doesn't account for [Prompt caching](https://platform.openai.com/docs/guides/prompt-caching)\nIf you're consecutively sending similar prompts to OpenAI it'll automatically use Cached Tokens to reduce the cost of your requests.\n\nSo our cost estimates will have a higher value than the actual cost.\n\nOther providers like Anthropic and Google have similar mechanisms.\n\n\n\n### 2. Not tested with audio or video files\nThis workflow was tested with text and images, but no tests were made with audio files or videos.\n\n\n\n### 3. The cost is an estimate\nIn the spreadsheet you can see the total cost of the requests, but that is only an estimate.\n\nIf you do batch requests, prompt caching or other techniques to reduce cost, the estimate might be higher than the actual cost."
},
"typeVersion": 1
},
{
"id": "5a687ff7-2f31-4541-8d8c-245cb345de2b",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-840,
-520
],
"parameters": {
"color": 7,
"height": 120,
"content": "This is an example AI Agent.\n\nUse this only to understand how to call the subworkflow and obtain the token amount."
},
"typeVersion": 1
},
{
"id": "6b96057d-150e-4a97-aff7-317c369af156",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1560,
-620
],
"parameters": {
"color": 4,
"width": 660,
"height": 260,
"content": "## Where to find LLM pricing?\nYou can enter each provider's website or use one of these:\n- [llm-price.com](https://llm-price.com)\n- [llm-prices.com](https://llm-prices.com)\n- [llmprices.dev](https://llmprices.dev/)\n- [LLM Price Check](https://llmpricecheck.com/)\n- [OpenRouter Models](https://openrouter.ai/models)"
},
"typeVersion": 1
},
{
"id": "18797895-4302-422c-b1a4-44a1e5e72e5c",
"name": "Record token usage",
"type": "n8n-nodes-base.googleSheets",
"position": [
540,
180
],
"parameters": {
"columns": {
"value": {
"llm_model": "={{ $json.tokenUsage_model }}",
"timestamp": "={{ $now.format('yyyy-MM-dd HH:mm:ss')}}",
"workflow_id": "={{ $json.id }}",
"execution_id": "={{ $json.execution_id }}",
"input tokens": "={{ $json.sum_tokenUsage_tokenUsage_promptTokens }}",
"workflow_name": "={{ $json.name }}",
"completion tokens": "={{ $json.sum_tokenUsage_tokenUsage_completionTokens }}"
},
"schema": [
{
"id": "execution_id",
"type": "string",
"display": true,
"required": false,
"displayName": "execution_id",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "timestamp",
"type": "string",
"display": true,
"required": false,
"displayName": "timestamp",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "workflow_id",
"type": "string",
"display": true,
"required": false,
"displayName": "workflow_id",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "workflow_name",
"type": "string",
"display": true,
"required": false,
"displayName": "workflow_name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "llm_model",
"type": "string",
"display": true,
"required": false,
"displayName": "llm_model",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "input tokens",
"type": "string",
"display": true,
"required": false,
"displayName": "input tokens",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "completion tokens",
"type": "string",
"display": true,
"required": false,
"displayName": "completion tokens",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "input price",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "input price",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "output price",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "output price",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "input cost",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "input cost",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "output cost",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "output cost",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "total cost",
"type": "string",
"display": true,
"removed": true,
"required": false,
"displayName": "total cost",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1c9CeePI6ebNnIKogyJKHUpDWT6UEowpH9OwVtViadyE/edit#gid=0",
"cachedResultName": "Executions"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "1c9CeePI6ebNnIKogyJKHUpDWT6UEowpH9OwVtViadyE",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/1c9CeePI6ebNnIKogyJKHUpDWT6UEowpH9OwVtViadyE/edit?usp=drivesdk",
"cachedResultName": "[TEMPLATE] Calculate LLM Token Usage"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 4.6
},
{
"id": "b958bc0c-9142-4d1c-a72f-e05fb0f007c6",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1560,
-880
],
"parameters": {
"color": 4,
"width": 660,
"height": 240,
"content": "## Make a copy of this Sheets file\n\ud83d\udc49 [**[TEMPLATE] Calculate LLM Token Usage**](https://docs.google.com/spreadsheets/d/1c9CeePI6ebNnIKogyJKHUpDWT6UEowpH9OwVtViadyE/edit?usp=sharing)\n\nThere are two sheets in this file:\n1. Executions\nAvoid changing the green columns. They have formulas on the header rows.\n\n2. LLM Pricing\nUpdate this list with the LLM models you are using"
},
"typeVersion": 1
},
{
"id": "1f7fb4ae-ca87-484a-9b45-38d4a7f14c6d",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
740,
-620
],
"parameters": {
"color": 7,
"width": 400,
"height": 200,
"content": "# Need help?\nCreate a topic on the community forums here:\nhttps://community.n8n.io/c/questions/\n\n\nOr join our exclusive [Scrapes Academy](https://www.skool.com/scrapes/about?ref=21f10ad99f4d46ba9b8aaea8c9f58c34) community"
},
"typeVersion": 1
},
{
"id": "a4370528-00d7-4b04-8eb2-8aab6d5d77dc",
"name": "Sticky Note10",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1560,
-340
],
"parameters": {
"color": 7,
"width": 660,
"height": 680,
"content": "# Author\n\n### Solomon\n\ud83c\udf93 AI & Automation Educator at the [Scrapes Academy](https://www.skool.com/scrapes/about?ref=21f10ad99f4d46ba9b8aaea8c9f58c34)\n\nFor business inquiries:\n- automations.solomon@gmail.com\n- [Telegram](https://t.me/salomaoguilherme)\n- [LinkedIn](https://www.linkedin.com/in/guisalomao/)\n\n### Check out my other templates\n### \ud83d\udc49 https://n8n.io/creators/solomon/\n"
},
"typeVersion": 1
},
{
"id": "17cf9314-b6a2-4abc-9223-846c08d53237",
"name": "Sticky Note16",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1540,
240
],
"parameters": {
"color": 4,
"width": 620,
"height": 80,
"content": "### \ud83d\udca1 **Want to learn advanced n8n skills and earn money building workflows?**\n\u200e \u200e \u200e \u200e \u200e \u200e \u200e \u200eCheck out [Scrapes Academy](https://www.skool.com/scrapes/about?ref=21f10ad99f4d46ba9b8aaea8c9f58c34)"
},
"typeVersion": 1
},
{
"id": "9cd12907-4b88-4bed-a997-53b7a0d07d12",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2280,
-880
],
"parameters": {
"width": 700,
"height": 640,
"content": "## Description\n### This n8n template demonstrates how to obtain token usage from AI Agents and places the data into a spreadsheet that calculates the estimated cost of the execution.\n\nObtaining the token usage from AI Agents is tricky, because it doesn't provide all the data from tool calls. This workflows taps into the workflow execution metadata to extract token usage information.\n\n### How it works\n- The AI Agent executes and then calls a subworkflow to calculate the token usage.\n- The data is stored in Google Sheets\n- The spreadsheet has formulas to calculate the estimated cost of the execution.\n\n### How to use\n- The AI Agent is used as an example. Feel free to replace this with other agents you have.\n- Call the subworkflow AFTER all the other branches have finished executing.\n\n### Requirements\n- LLM account (OpenAI, Gemini...) for API usage.\n- Google Drive and Sheets credentials\n- n8n API key of your instance"
},
"typeVersion": 1
},
{
"id": "51c0beee-ca42-4d3b-a725-1922a778cfcc",
"name": "Gemini",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
-400,
-280
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.5-flash"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "2e02c00e-375e-4fdb-adc5-0b49f6217cd1",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-320,
-280
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "7dcc1116-ba80-4fad-89f9-ddae07a906e9",
"name": "Anthropic",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
-240,
-280
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-3-haiku-20240307",
"cachedResultName": "Claude Haiku 3"
},
"options": {}
},
"credentials": {
"anthropicApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "e222998d-669c-47f6-9ddc-037a2b2c3166",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
-420,
-160
],
"parameters": {
"color": 7,
"width": 280,
"height": 200,
"content": "Works well with all the providers above.\n\nIf you use another provider, you might need to adjust this node:\n\n`Extract token usage data`\n\nOn the below workflow \ud83d\udc47"
},
"typeVersion": 1
}
],
"connections": {
"Think": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Gemini": {
"ai_languageModel": [
[]
]
},
"OpenAI": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Call sub-workflow",
"type": "main",
"index": 0
}
]
]
},
"Anthropic": {
"ai_languageModel": [
[]
]
},
"Split Out": {
"main": [
[
{
"node": "Sum Token Totals - aggregate by model",
"type": "main",
"index": 0
}
]
]
},
"Get execution data": {
"main": [
[
{
"node": "Extract token usage data",
"type": "main",
"index": 0
}
]
]
},
"Extract token usage data": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "Get execution data",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Sum Token Totals - aggregate by model": {
"main": [
[
{
"node": "Record token usage",
"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.
anthropicApigooglePalmApigoogleSheetsOAuth2Apin8nApiopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Obtaining the token usage from AI Agents is tricky, because it doesn't provide all the data from tool calls. This workflow taps into the workflow execution metadata to extract token usage information.
Source: https://n8n.io/workflows/5541/ — 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.
This workflow is designed for marketers, content creators, agencies, and solo founders who want to publish long‑form posts with visuals on autopilot using n8n and AI agents.
Tool Http Request, Agent, HTTP Request +27
This workflow contains community nodes that are only compatible with the self-hosted version of n8n.
Output Parser Structured, Telegram, N8N Nodes Tesseractjs +14
Tired of scrolling through messy notes and bookmarks to find your favorite recipes? Wish you had a personal chef's assistant to help you in the kitchen?
Telegram Trigger, Google Sheets, Telegram +6
This workflow automates Facebook posting and appointment booking directly from a Telegram bot, making it especially useful for pet grooming businesses that want to keep their social media active while
Google Sheets, OpenAI Chat, Output Parser Structured +12
Automatically publish blog content to WordPress with AI-generated branded images, internal linking, and client reporting using Google Sheets, OpenAI, and Gemini
Execute Workflow Trigger, Google Sheets, Agent +6