API

circle-info

Fair-use limits: To ensure a reliable experience for all users, the AI Model Studio is subject to the following fair-use limits:

  • Parallel training: Usage is limited to one active training process per user.

  • Inference capacity: Limited to a maximum of three parallel queries per user.

  • Synthetic data generation: Generation is limited to a maximum of 100 units per operation, with one parallel generation process allowed.

To increase the limits, contact IONOS Cloud Supportarrow-up-right.

The AI Model Studio can be used for inference tasks through API to be integrated into AI applications or for running more sophisticated evaluations. The following paragraphs explain how and which specifications the API can access.

Create an access token

Authentication to access your personal fine-tuned models in handled via bearer token. To create a token, click on your user name in the top right corner of the AI Model Studio web UI and navigate to Organizational Settings. API tokens will be created in the API Keys tab.

circle-exclamation

Endpoints

Best Practice: You can generate ready to use code for API calls to your model within the AI Model Studio. Go to the Models section inside the web UI, select the model you want to use, and click on <>.

Create a Generation Job

POST https://studio.ionos.de/api/v1/organizations/<YOUR_ORGANIZATION_ID>/generate

Request Body:

{
  "model_id": MODEL_ID,
  "messages": [
    [
      {
        "role": "user",
        "content": "The capital of France is"
      }
    ]
  ],
  "temperature": 0.7,
  "max_tokens": 512
}

Response:

Retrieve the Generated Output

Response:

Last updated

Was this helpful?