Token usage data is missing after "Basic LLM Chain" node

[Anshul_Namdev]

Hi @Kunwei_TAN, welcome!
Currently this is a limitation with the basic LLM Chain node.
There is a possible workaround by using the AI agent node or by retrieving data by the N8N API.

Access an agent's chat model output in subsequent nodes

The following is the json output of the chat module of a standard AI Agent node. I’d like the output of my agent to include model_name and tokenUsage so that the user gets an immediate feedback about the cost of usage per message. How do I access this data? I wasn’t able to find a suitable object in subsequent nodes or even in the system message of the agent node. [ { "response": { "generations": [ [ { "text": "TRUNCATED OUTPUT", "generati…

If you want that kind of information directly, consider using the OpenAI node or Gemini node.

If you want to get the usage by the n8n API, here is the workaround:

How to retrieve used tokens in a node?

for (const item of $input.all()) { try { // Utilisation de .first() pour forcer n8n à aller chercher les données // dans le nœud Gemini2 peu importe où il se trouve const geminiData = $(‘Gemini2’).first().json; item.json.prompt_tokens = geminiData.tokenUsage?.promptTokens || 0; item.json.completion_tokens = geminiData.tokenUsage?.completionTokens || 0; item.json.total_tokens = geminiData.tokenUsage?.totalTokens || 0; } catch (error) { item.json.prompt_tokens = 0; item.json.completion_tok…