v32

latestOpenAPI 3.1.0raw.githubusercontent.com2026-05-151,1412,2144.5 MB

Everywhere Inference

Get model from catalog

get/cloud/v3/inference/models/{model_id}

Path parameters

model_idstring required

Model ID

Response

categorystring nullable required

Category of the model.

default_flavor_namestring nullable required

Default flavor for the model.

descriptionstring required

Description of the model.

developerstring nullable required

Developer of the model.

documentation_pagestring nullable required

Path to the documentation page.

eula_urlstring nullable required

URL to the EULA text.

example_curl_requeststring nullable required

Example curl request to the model.

has_eulaboolean required

Whether the model has an EULA.

idstring uuid required

Model ID.

image_registry_idstring nullable required

Image registry of the model.

image_urlstring required

Image URL of the model.

inference_backendstring nullable required

Describing underlying inference engine.

inference_frontendstring nullable required

Describing model frontend type.

model_idstring nullable required

Model name to perform inference call.

namestring required

Name of the model.

openai_compatibilitystring nullable required

OpenAI compatibility level.

portinteger required

Port on which the model runs.

versionstring nullable required

Version of the model.

Example response

{
  "category": "Text Classification",
  "default_flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
  "description": "My first model",
  "developer": "Stability AI",
  "documentation_page": "/docs",
  "eula_url": "https://example.com/eula",
  "example_curl_request": "curl -X POST http://localhost:8080/predict -d '{\"data\": \"sample\"}'",
  "has_eula": true,
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "image_registry_id": "123e4567-e89b-12d3-a456-426614174999",
  "image_url": "registry.hub.docker.com/my_model:latest",
  "inference_backend": "torch",
  "inference_frontend": "gradio",
  "model_id": "mistralai/Pixtral-12B-2409",
  "name": "model1",
  "openai_compatibility": "full",
  "port": 8080,
  "version": "v0.1"
}