trustedrouter

Use hundreds of AI models through TrustedRouter in n8n workflows

Package Information

Released: 2 mo ago
Downloads: 0 weekly / 0 monthly
Latest Version: 0.1.3

Available Nodes

Documentation generating…

TrustedRouter icon
TrustedRouter
Use hundreds of AI models through a private, OpenAI-compatible router

Documentation

n8n nodes for TrustedRouter

CI
npm
license

Use hundreds of AI models through TrustedRouter in n8n. The node supports OpenAI-compatible Chat Completions and Responses, automatic model routing, fallbacks, tags, tools, workspace selection, and idempotent retries.

TrustedRouter never stores prompt or output logs. Prompts still pass through n8n while a workflow runs, and n8n may retain execution data according to the settings of your n8n instance.

Installation

n8n Cloud and verified community nodes

After n8n completes verification, an instance owner or admin can:

  1. Open the nodes panel.
  2. Search for TrustedRouter.
  3. Select Install under More from the community.

Verified community nodes must be enabled by the n8n instance owner.

Self-hosted n8n

Open Settings > Community Nodes, select Install, and enter:

n8n-nodes-trustedrouter

Restart n8n if the node does not appear immediately.

Credentials

  1. Create a TrustedRouter API key.
  2. Add a TrustedRouter API credential in n8n.
  3. Paste the API key. n8n stores it as a secret credential.
  4. Select Save to verify the credential against the live model catalog.

Operations

Text

  • Create Chat Completion calls POST /v1/chat/completions.
  • Create Response calls the stateless POST /v1/responses API with store=false.
  • Choose a model from the live catalog or enter any TrustedRouter model ID.
  • Configure fallback models, provider routing, tools, tags, trace metadata, structured JSON output, workspace selection, and an idempotency key.

Model

  • Get Many returns the current TrustedRouter model catalog.

Account

  • Get Current Key returns usage and limits for the authenticated API key.

The node is also marked Usable as an AI Tool, so an n8n AI Agent can call it as a workflow tool.

Use TrustedRouter as an n8n AI Agent chat model

n8n does not yet accept third-party AI language-model nodes for verified community-node review. You can still use TrustedRouter as the model behind an AI Agent with n8n's built-in OpenAI Chat Model node:

  1. Add an OpenAI Chat Model node to the AI Agent.
  2. Create an OpenAI credential with your TrustedRouter API key.
  3. Set Base URL to https://api.trustedrouter.com/v1.
  4. Enter a model such as trustedrouter/auto, trustedrouter/zdr, or trustedrouter/e2e.

This uses the same attested TrustedRouter API. No OpenAI account is required.

Example

Create a Text operation with these values:

Operation: Create Chat Completion
Model: trustedrouter/auto
Instructions: Answer briefly and return valid JSON.
Input: Classify {{$json.customerMessage}} as billing, technical, or sales.
Response Format: JSON Object
Idempotency Key: {{$execution.id}}:{{$itemIndex}}

The simplified output contains the response text, finish reason, model, and token usage. Disable Simplify to receive the full OpenAI-compatible response.

Security

  • The published package has no runtime dependencies.
  • It does not read environment variables or files.
  • API keys remain in n8n's credential store and are sent only in the authorization header.
  • The package is published from GitHub Actions with npm provenance.
  • TrustedRouter's running gateway can be verified at trust.trustedrouter.com.

Review the TrustedRouter trust center and source code for the full security boundary.

Development

npm ci
npm run check

Run the node locally in n8n with:

npm run dev

Support

License

MIT, maintained by Lore Hex Corp.

Discussion