Track AI agent token usage and estimate costs in Google Sheets
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 13 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Google Sheets, Google Gemini Chat Model, OpenAI Chat Model and Anthropic Chat Model.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- AI Agent: runs an AI agent, with model: OpenAI; 1 tool (Think)
- Get execution data (n8n): get (execution)
- Call sub-workflow (Execute Sub-workflow): calls another n8n workflow
- Extract token usage data (Edit Fields (Set)): sets 2 fields: execution_id, tokenUsage
- Split Out: splits a list into separate items
- Sum Token Totals - aggregate by model (Summarize): summarizes / groups the items
- Record token usage (Google Sheets): append
- Gemini (Google Gemini Chat Model): uses Google Gemini Chat Model
- Anthropic (Anthropic Chat Model): uses Anthropic Chat Model
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- Manual Trigger
n8n-nodes-base.manualTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Edit Fields (Set)
n8n-nodes-base.set - n8n
n8n-nodes-base.n8n - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Split Out
n8n-nodes-base.splitOut - Summarize
n8n-nodes-base.summarize - Google Sheets
n8n-nodes-base.googleSheets - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic
From the author
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. Obtaining the token usage from AI Agents is tricky, because it doesn't provide all the data…