IONOS Cloud (AI Model Hub) icon

IONOS Cloud (AI Model Hub)

Interact with IONOS Cloud AI Model Hub API

Actions6

OpenAI Compatible → Chat Completion

AI-generated

Summary

Send a chat-completion request to IONOS Cloud’s OpenAI-compatible API using a selected model and a sequence of system, user, or assistant messages. The request returns the API response; optionally include its HTTP headers and status code in the output.

Inputs

  • Model (required) — Select the model ID from the list fetched live from IONOS.
  • Messages (required) — Add one or more messages, each with a role (system, user, or assistant) and text content.
  • Additional Fields — Optionally set frequency or presence penalties, logit bias, maximum completion tokens (or deprecated max tokens), number of choices, response format, comma-separated stop sequences, streaming, temperature, tool choice, tools, top_p, and an end-user identifier. These values are sent as fields in the request body.
  • Include Response Headers — When enabled, output the response body under body alongside headers and statusCode.
  • Request Options — Configure request batching, SSL certificate validation, an HTTP proxy, or a timeout.

Output shape

A single item containing the chat-completion API response.

The response body follows the API response shape. With Include Response Headers enabled, the item contains body, headers, and statusCode instead.

Links

Discussion