ModelOptionSchema

display_namestringrequired

User-friendly display name of the model.

is_finetuned_modelbooleanrequired

When true, the model is a fine-tuned model; when false, it is a base model.

model_idintegerrequired

Unique identifier of the model.

model_namestringrequired

Name of the model, used as the model value in inference requests.

hf_repostring

Hugging Face repository identifier of the base model, if applicable.

Default: null

base_mode_hf_repostring

Hugging Face repository identifier of the underlying base model for a fine-tuned model, if applicable.

Default: null

providerstring

Name of the model provider, such as HuggingFace or Hyperstack.

Default: null

input_modalitiesstring[]

Input modalities the model accepts, such as text or image.

Default: null

output_modalitiesstring[]

Output modalities the model produces, such as text or image.

Default: null

parameter_schemaobject

JSON Schema describing the model's accepted generation parameters. Populated for vision (image) models with their image-generation parameters; null for text models.

Default: null

ModelOptionSchema

{
  "display_name": "string",
  "is_finetuned_model": true,
  "model_id": 0,
  "model_name": "string",
  "hf_repo": null,
  "base_mode_hf_repo": null,
  "provider": null,
  "input_modalities": [
    "string"
  ],
  "output_modalities": [
    "string"
  ],
  "parameter_schema": {}
}