Package Information
Available Nodes
Documentation generating…
Documentation
n8n-nodes-obscurify
This is an n8n community node. It lets you use Obscurify.ai in your n8n workflows.
Obscurify.ai is a privacy-focused AI service with an OpenAI-compatible API to 200+ models (GPT, Claude, Gemini, DeepSeek, Qwen, Llama, Mistral and more). Text requests only use zero-data-retention routes, prompts and responses aren't stored on Obscurify.ai's servers, and accounts are a random account number with no email.
n8n is a fair-code licensed workflow automation platform.
Installation ·
Operations ·
Credentials ·
Compatibility ·
Usage ·
Resources
Installation
Follow the installation guide in the n8n community nodes documentation. The package name is n8n-nodes-obscurify. It has no runtime dependencies.
Operations
Chat
- Message a Model: send a list of messages (system, user, assistant) to any Obscurify.ai model and get its reply. Options: maximum tokens, temperature, top P, reasoning effort (none to max; models that don't reason ignore it) and JSON output. With Simplify Output on (the default), the node returns
content,reasoning(when the model reasons),finish_reason,modelandusage.
Model
- Get Many: list the available models with their context windows, tool support and per-token prices. Decision models are left out unless you turn off Chat Models Only.
Account
- Get Balance: the balance of the account the API key belongs to, in USD.
The node can also be used as a tool by n8n's AI Agent.
Credentials
- Create an account at obscurify.ai. You get a random account number: no email, no password.
- Add a balance on the account page. The API works on every plan with a positive balance. Frontier models need the Casual plan or higher, and uncensored models need Pro.
- On obscurify.ai/account, click Show API Key.
- In n8n, create an Obscurify.ai API credential and paste the
sk-obs1_...key. Leave Base URL athttps://obscurify.ai/v1unless you reach Obscurify.ai through a proxy.
The credential test checks the key against the account balance endpoint.
Compatibility
Tested with n8n 2.45.5 (docker n8nio/n8n:latest, 2026-10-28). Built with @n8n/node-cli 0.54.
Usage
A minimal workflow: Manual Trigger → Obscurify.ai (Chat: Message a Model). Pick a model such as deepseek/deepseek-v4-flash, add a user message like Summarize this: {{ $json.text }}, and read the reply from {{ $json.content }}.
To get structured data back, turn on Options → JSON Output and ask for JSON in the prompt. Then parse {{ JSON.parse($json.content) }}.
Prices per model: obscurify.ai/model_cards. Each request is charged to your Obscurify.ai balance at that model's price.
Development
npm install
npm run lint
npm run build
npm run dev # n8n with this node loaded
OBSCURIFY_API_KEY=sk-obs1_... e2e/run.sh # real n8n in docker: chat, reasoning + JSON, balance, models
Releases are published to npm from GitHub Actions with provenance (.github/workflows/publish.yml, on a version tag).