Panda LLM icon

Panda LLM

Free-LLM chat model with provider failover. Connect to the Chat Model input of an AI Agent or any chain.

Panda LLM

AI-generated

Summary

Provides a chat language model for an n8n AI Agent or chain, sending prompts to a selected provider and optionally trying configured fallback models when a request fails.

Inputs

  • Provider (required) — Choose Groq, Cerebras, Gemini, OpenRouter, or Mistral as the first provider. The node uses that provider's API key from its required Panda Free LLM credentials.
  • Model — Select a model for the primary provider. If left blank, the node uses that provider's built-in default model.
  • Enable Failover — Defaults to enabled. When enabled, the node tries the configured fallback provider and model selections in order after a request fails. Fallbacks without a matching API key, invalid providers, and duplicate selections are skipped.
  • Fallback Models (in order) — When failover is enabled, choose fallback provider and model pairs from the available models. Fallback providers also need configured API keys.
  • Options — Configure maximum tokens (default 1024), response format (text by default, or JSON), temperature (default 0.7), and request timeout in milliseconds (default 30000). In JSON mode, the node asks for a JSON object and adds a JSON-only system instruction if the prompt messages do not mention JSON.

Output shape

An AI Language Model connection for an AI Agent or chain; it does not return regular workflow items directly.

The model sends chat completion requests and returns the first response's text and any tool calls to its consumer. If every configured provider request fails, it throws an error containing the last failure.

Links

Discussion