ExadoInstall

Summary

Generate a text completion using the OpenAI-compatible legacy completions endpoint of the Exado API.

Inputs

• Model Name or ID (required) — Select the OpenAI-compatible model to use for completion, either from a provided list or by specifying an ID with an expression.
• Prompt (required) — Input text prompt that the model will complete.
• Stream Response — Enable to receive the completion as a stream of Server-Sent Events (SSE) chunks.
• Emit Each Chunk — When streaming is enabled, toggle whether to output each streamed chunk as a separate item or to combine into a single item.
• Additional Options — Optional parameters to tweak completion behavior, including temperature, max tokens, top_p, frequency and presence penalties, stop sequences, deterministic seed, and whether to include usage statistics in the stream.

Output shape

a single JSON object per input item or multiple items per input if streaming with emitEachChunk enabled

By default, returns a single JSON response with the completion text and metadata. If streaming is enabled, it consumes SSE chat completion chunk frames; if 'Emit Each Chunk' is true, the node emits one item per streamed chunk, otherwise emits a single merged completion result. Errors during streaming raise a node error with partial content included.

Examples

Example 1: Generate a completion

Select a model, provide a text prompt, optionally enable streaming and set additional parameters to control generation output.

Links

• n8n community nodes installation guide