Get API Docs

Page Outline

• Path Parameters
• Query Parameters
• Behavior
• Response

---

Returns the auto-generated OpenAPI specification for a model's inference endpoint, enabling clients to understand the expected input schema, output schema, and authentication requirements.

Base Path: /api/v1/models

Method: GET

Path: /{model_id}/api-docs

Auth: Requires a valid Bearer token (Authorization: Bearer <JWT>)

Path Parameters

Parameter	Type	Description
model_id	string	Unique identifier of the model

Query Parameters

Parameter	Type	Default	Description
version_id	string	—	Generate docs for a specific version. Defaults to the promoted version
format	string	json	Response format: json (OpenAPI 3.0 JSON) or yaml (OpenAPI 3.0 YAML)

Behavior

• Generates an OpenAPI 3.0 specification scoped to the inference endpoint (/infer) for this specific model.
• The requestBody schema is derived from the model's feature_columns and their data types, inferred from the linked dataset at training time.
• The responses schema is derived from the model's task_type and output labels.
• Returns HTTP 422 if the model has no promoted version and no schema to derive from.
• Returns HTTP 404 if the model is not found.

Response

Returns an OpenAPI 3.0 specification document.

{
  "openapi": "3.0.0",
  "info": {
    "title": "My Churn Predictor - Inference API",
    "version": "3",
    "description": "Auto-generated inference API for model mdl-7f3a19bc (version ver-001)."
  },
  "paths": {
    "/infer": {
      "post": {
        "summary": "Run inference",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "properties": {
                  "age": { "type": "integer" },
                  "tenure": { "type": "integer" },
                  "monthly_spend": { "type": "number" },
                  "support_tickets": { "type": "integer" }
                },
                "required": ["age", "tenure", "monthly_spend"]
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Prediction result",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "prediction": { "type": "string", "enum": ["not_churned", "churned"] },
                    "probabilities": { "type": "object" }
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}