LLM7 Chat icon

LLM7 Chat

Send chat completions to llm7.io or any OpenAI-compatible API. Direct HTTP, no LangChain.

LLM7 Chat

AI-generated

Summary

Send chat completion requests to an OpenAI-compatible API endpoint and receive generated assistant messages based on provided conversational messages.

Inputs

  • Base URL (required) — The OpenAI-compatible API endpoint URL (default: https://api.llm7.io/v1).
  • API Key — API key for authentication; leave empty or set to "unused" to use the llm7.io free tier.
  • Model (required) — Model identifier to use for chat completion, e.g., default, fast, pro, gpt-4o-mini.
  • Messages (required) — A list of messages forming the conversation history; each message includes a role (system, user, assistant) and content. At least one message is required.
  • Options — Optional parameters to control generation: Temperature (randomness), Max Tokens (response length limit), Top P (nucleus sampling), Frequency Penalty, Presence Penalty, Timeout (request timeout in seconds), and Response Format (text or JSON object).

Output shape

A list of JSON objects, each corresponding to an input item, containing the generated content text, role, finish reason, model used, usage statistics if available, and the raw API response.

Each output item is paired with the corresponding input item. If the API response is empty or an error occurs, the node throws an error unless "Continue on Fail" is enabled, in which case the error message is included in the output JSON.

Links

Discussion