1 min read 80 words Updated Sep 24, 2026 Created Sep 24, 2026
#AI#LLM

It is compatible with the OpenAI Specification:

from openai import OpenAI

IONOS_API_TOKEN = ""
openai = OpenAI(
    api_key=IONOS_API_TOKEN, base_url="https://openai.inference.de-txl.ionos.com/v1"
)

completion = openai.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {
            "role": "user",
            "content": "Wie ist das Wetter meistens in Deutschland?",
        }
    ],
    max_completion_tokens=400,
    temperature=0,
    top_p=0.1,
    stream=True,
)
for chunk in completion:
    print(chunk.choices[0].delta.content, end="")

Models

Chat models

See usage: Chat Models IONOS Cloud

OCR

https://docs.ionos.com/cloud/ai/ai-model-hub/models/ocr-models
LightOnOCR-2-1B

How to use the LightOnOCR model with the openai SDK: https://docs.ionos.com/cloud/ai/ai-model-hub/how-tos/pdf-to-text

Embedding models