TokenSense node reference

Parameter and operation reference for n8n-nodes-tokensense 0.1.20. Defaults below are unchanged to preserve existing workflows.

Release status checked 4 October 2026: npm 0.1.20 is published for self-hosted installations. n8n has approved 0.1.20 for Cloud; 0.1.18 remains live there until n8n publishes the update. See the release note.

TokenSense Chat Model

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

ParameterTypeDefaultDescription
Modeloptionsgpt-4.1-miniModel identifier (loaded dynamically from TokenSense)
Temperaturenumber0.7Sampling temperature (0–2)
Max Tokensnumber0Maximum tokens (0 = model default)
StreamingbooleantrueWhether to stream the response
Projectstring—Project name for cost tracking
Workflow Tagstring—Tag for dashboard attribution (auto-detected if empty)
Provider OverrideoptionsautoForce a specific provider (auto, openai, anthropic, google, mistral, xai); Moonshot models use auto routing

TokenSense AI

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

Chat — Chat Completion

ParameterTypeDefaultDescription
Modeloptionsgpt-4.1-miniModel identifier (loaded from TokenSense)
System Promptstring—Optional system message
User Messagestring—The message to send (required)
Temperaturenumber0.7Sampling temperature (0–2)
Max Tokensnumber0Maximum tokens (0 = model default)
JSON ModebooleanfalseForce model to respond with valid JSON
Projectstring—Project tag for attribution
Workflow Tagstring—Dashboard attribution (auto-detected if empty)
Provider OverrideoptionsautoForce a specific provider

Chat — Native Anthropic

ParameterTypeDefaultDescription
Modeloptionsclaude-sonnet-4-6In 0.1.20: Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 4.5, and compatible older choices. Existing selections remain unchanged.
System Promptstring—Optional system prompt
User Messagestring—The message to send (required)
Max Tokensnumber1024Maximum generated tokens including thinking; a small limit may leave no visible text
Temperaturenumber1.0Sampling temperature (0–1); omitted for Claude models that fix sampling
Projectstring—Project tag
Workflow Tagstring—Dashboard attribution (auto-detected if empty)

Chat — Native Gemini

ParameterTypeDefaultDescription
Modeloptionsgemini-3-flash-previewIn 0.1.20: Gemini 3.8 Flash, stable 3.1 Flash-Lite, 3.5 Flash-Lite, Pro Preview, and compatible older choices. Existing selections remain unchanged.
User Messagestring—The message to send (required)
System Instructionstring—Optional system instruction
Temperaturenumber1.0Sampling temperature (0–2)
Max Output Tokensnumber0Maximum response tokens (0 = model default)
Projectstring—Project tag
Workflow Tagstring—Dashboard attribution (auto-detected if empty)

Image — Image Generation

ParameterTypeDefaultDescription
Promptstring—Image description
Modeloptionsgpt-image-2Current additions: gpt-image-2.5-flare, gpt-image-2.5-sunburst, gemini-3.1-flash-image, gemini-3.1-flash-lite-image, gemini-3-pro-image, flux-3. Older GPT Image and FLUX 2 choices remain. DALL-E choices are labelled deprecated; Imagen 4 is retired.
Sizestring1024x1024Output dimensions; Gemini image compatibility requests require 1024x1024
Qualitystringstandardauto, low, medium, high; xhigh and max for Image 2.5. Saved standard maps to auto and hd to high for GPT Image. Quality is omitted for Gemini images and FLUX 3.
Number of Imagesnumber1Images to generate (1–10 in the node); Gemini images and FLUX 3 require 1
Projectstring—Project tag

Embedding — Text Embedding

ParameterTypeDefaultDescription
Inputstring | string[]—Text to embed
Modeloptionstext-embedding-3-smallEmbedding model — options: text-embedding-3-large, text-embedding-3-small, text-embedding-ada-002
Dimensionsnumber—Output dimensions (if supported)
Projectstring—Project tag

Audio — Text-to-Speech

ParameterTypeDefaultDescription
Inputstring—Text to speak
Modeloptionstts-1TTS model — options: tts-1, tts-1-hd, gpt-4o-mini-tts
VoiceoptionsalloyVoice preset — options: alloy, ash, ballad, cedar, coral, echo, fable, marin, nova, onyx, sage, shimmer, verse
Response Formatoptionsmp3Audio format — options: mp3, opus, aac, flac, wav, pcm
Speednumber1.0Playback speed (0.25–4.0)
Projectstring—Project tag

Audio — Speech-to-Text

ParameterTypeDefaultDescription
Binary PropertystringdataName of the binary property containing the audio file
Modeloptionswhisper-1STT model — options: whisper-1, gpt-transcribe, gpt-4o-transcribe, gpt-4o-mini-transcribe
Languagestring—ISO language code (optional)
Response FormatoptionsjsonOutput format (json/text/srt/verbose_json/vtt); current GPT transcription models require json through TokenSense
Projectstring—Project tag

Model — List Models

No parameters — returns all models available in your TokenSense workspace.

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.

Model compatibility

Model access depends on your provider account and key. GPT 6.1 Sol and GPT 6 Astra tool requests require the Responses API. The Chat Model node uses Chat Completions: choose a Chat-compatible model for agents, or use an HTTP Request node against /v1/responses. Text requests without tools can use GPT 6.1 Sol through Chat Completions.

Gemini 3.8 Flash accepts low, medium, or high thinking. TokenSense maps minimal to low and removes obsolete sampling controls for this model. Claude Fable 5.1, Opus 5.5, Sonnet 5.5, and Opus 4.7 fix sampling; their thinking tokens count toward the output limit. Check x-tokensense-adapted on gateway responses when diagnosing changes. Retired IDs return model_retired; saved workflows are not silently migrated.

When cost is unavailable

In 0.1.20, Image Generation and Speech-to-Text expose pricingAvailable, billingReason, and cost. Text-to-Speech exposes pricing metadata when the gateway supplies its billing headers. A false or absent availability flag and an empty cost are not a zero-dollar bill.

Mini TTS returns binary audio without the usage needed to calculate its token bill. Its reason is binary_audio_usage_unavailable. Image costs can also be unavailable when the provider omits billable text/image usage dimensions. Keep these requests separate from fully priced totals rather than substituting zero.

These output fields are operation-specific. Native Gemini retains its native usage data and cost header mapping; do not assume every node operation has the same JSON shape. See usage patterns.

Metadata fields

The nodes send these attribution fields with AI requests:

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