CLI Proxy Web icon

CLI Proxy Web

Call CLI Proxy Web API endpoints from n8n

Actions6

Create Chat Completion

AI-generated

Summary

Send an OpenAI-compatible chat completion request to the configured CLI Proxy Web endpoint using the selected model and messages, with optional generation settings and extra request fields.

Inputs

  • Model (required) — Model identifier; defaults to gpt-5-mini.
  • Messages (required) — JSON array of OpenAI-compatible message objects; defaults to a user message asking for a summary.
  • Options — Optional settings: stream (false), reasoning effort (none, low, medium, high, or xhigh), temperature (1), maximum tokens (1024), top P (1), presence penalty (0), frequency penalty (0), and Additional Body JSON ({}), whose fields are merged into the request and can override the generated fields.

Output shape

A list of n8n items, each containing the response as JSON.

Makes an authenticated POST request to /v1/chat/completions for each input item. The response is normalized to an object: object responses remain as-is, arrays are wrapped in {"data": [...]}, and primitive responses in {"value": ...}. If Continue On Fail is enabled, failed items contain an error field.

Links

Discussion