Viam ML Inference API

openapi: 3.1.0
info:
  title: Viam ML Inference API
  description: |
    REST/JSON transcoding of the Viam MLInferenceService gRPC API. Run cloud-hosted
    inference against models registered in the Viam ML registry.

    Canonical contract: https://github.com/viamrobotics/api/blob/main/proto/viam/app/mlinference/v1/ml_inference.proto
  version: '2026.05'
  contact:
    name: Viam Support
    url: https://www.viam.com/contact
servers:
  - url: https://app.viam.com
    description: Viam production cloud.
security:
  - ApiKeyAuth: []
tags:
  - name: Inference
    description: Cloud-hosted inference against registry-deployed models.
paths:
  /viam.app.mlinference.v1.MLInferenceService/GetInference:
    post:
      summary: Viam Get Inference
      description: Run inference against a registry-deployed model with binary input data.
      operationId: getInference
      tags: [Inference]
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required: [registry_item_id, registry_item_version, binary_id]
              properties:
                registry_item_id: { type: string }
                registry_item_version: { type: string }
                binary_id: { type: object }
                organization_id: { type: string }
      responses:
        '200':
          description: Successful response.
components:
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: key
      description: Viam API key.