TokenSense node reference

Complete parameter and operation reference for all TokenSense n8n nodes.

TokenSense Chat Model

Sub-node for AI Agent workflows. Attach as the language model.

ParameterTypeDefaultDescription
Modeloptionsgpt-4oModel identifier (loaded dynamically from TokenSense)
Temperaturenumber0.7Sampling temperature (0–2)
Max Tokensnumber0Maximum tokens (0 = model default)
StreamingbooleantrueWhether to stream the response
ProjectstringProject name for cost tracking
Workflow TagstringTag for dashboard attribution (auto-detected if empty)
Provider OverrideoptionsautoForce a specific provider (auto, openai, anthropic, google, mistral, xai)

TokenSense AI

General-purpose node with five resource types and eight operations.

Chat — Chat Completion

ParameterTypeDefaultDescription
Modeloptionsgpt-4oModel identifier (loaded from TokenSense)
System PromptstringOptional system message
User MessagestringThe message to send (required)
Temperaturenumber0.7Sampling temperature (0–2)
Max Tokensnumber0Maximum tokens (0 = model default)
JSON ModebooleanfalseForce model to respond with valid JSON
ProjectstringProject tag for attribution
Workflow TagstringDashboard attribution (auto-detected if empty)
Provider OverrideoptionsautoForce a specific provider

Chat — Native Anthropic

ParameterTypeDefaultDescription
Modeloptionsclaude-sonnet-4-5-20250929Anthropic model — options: claude-3-5-haiku-20241022, claude-opus-4-20250514, claude-sonnet-4-5-20250929
System PromptstringOptional system prompt
User MessagestringThe message to send (required)
Max Tokensnumber1024Maximum response tokens (required by Anthropic)
Temperaturenumber1.0Sampling temperature (0–1)
ProjectstringProject tag
Workflow TagstringDashboard attribution (auto-detected if empty)

Chat — Native Gemini

ParameterTypeDefaultDescription
Modeloptionsgemini-2.0-flashGemini model — options: gemini-1.5-pro, gemini-2.0-flash, gemini-2.0-flash-lite
User MessagestringThe message to send (required)
System InstructionstringOptional system instruction
Temperaturenumber1.0Sampling temperature (0–2)
Max Output Tokensnumber0Maximum response tokens (0 = model default)
ProjectstringProject tag
Workflow TagstringDashboard attribution (auto-detected if empty)

Image — Image Generation

ParameterTypeDefaultDescription
PromptstringImage description
Modelstringgpt-image-1Image model
Sizestring1024x1024Output dimensions
Qualitystringstandardstandard or hd
Number of Imagesnumber1Images to generate (1–10)
ProjectstringProject tag

Embedding — Text Embedding

ParameterTypeDefaultDescription
Inputstring | string[]Text to embed
Modelstringtext-embedding-3-smallEmbedding model
DimensionsnumberOutput dimensions (if supported)
ProjectstringProject tag

Audio — Text-to-Speech

ParameterTypeDefaultDescription
InputstringText to speak
Modelstringtts-1TTS model
VoicestringalloyVoice preset
Response Formatstringmp3Audio format
Speednumber1.0Playback speed (0.25–4.0)
ProjectstringProject tag

Audio — Speech-to-Text

ParameterTypeDefaultDescription
Binary PropertystringdataName of the binary property containing the audio file
Modelstringwhisper-1STT model
LanguagestringISO language code (optional)
Response FormatoptionsjsonOutput format (json/text/srt/verbose_json/vtt)
ProjectstringProject tag

Model — List Models

ParameterTypeDefaultDescription
ProviderstringFilter by provider (optional)

TokenSense AI Tool

Auto-generated from the TokenSense AI node. Shares the same parameters for each resource/operation. Attach as a Tool sub-node on an AI Agent when you need an agent to invoke another model.

Metadata fields

TokenSense adds these fields to every request and response:

FieldSourceDescription
workflow_tagWorkflow Tag field (falls back to workflow name)Identifies the workflow
stepAutomatic (from node name)Identifies the step within the workflow
execution_idAutomatic (from n8n execution ID)Identifies the specific run
sourceAutomaticAlways "n8n-community-node"

Related