IONOS Cloud (AI Model Hub) icon

IONOS Cloud (AI Model Hub)

Interact with IONOS Cloud AI Model Hub API

Actions6

OpenAI Compatible → Completion

AI-generated

Summary

Sends the required model ID and prompt to IONOS Cloud’s OpenAI-compatible text completions endpoint. Optionally configures generation behavior and includes response headers and status code in the output.

Inputs

  • Model (required) — Select a model; the list is fetched live from the IONOS API.
  • Prompt (required) — Text to generate a completion from.
  • Additional Fields — Optional frequency and presence penalties, logit bias, maximum tokens, number of completions, stop sequences, streaming, temperature, top P, and end-user identifier. Stop sequences are entered comma-separated and sent as an array.
  • Include Response Headers — When enabled, nests the response body under body and adds headers and statusCode to the output.
  • Request Options — Configure batching, SSL certificate validation, an HTTP proxy, and request timeout.

Output shape

A list of items containing the API response.

With Include Response Headers enabled, each response item includes body, headers, and statusCode; otherwise the response body is returned without that wrapper. Streaming is a request option, but the source does not specify a distinct output shape for streamed responses.

Examples

Example 1: Generate a continuation from a prompt

Choose a model and provide the required prompt, then optionally set generation parameters such as max tokens or stop sequences.

Links

Discussion