slug: scalable-inference-serving
provider: Scalable Inference Serving
generated_by: planning/capability-mapping/scripts/classify_capabilities.py
model: claude-opus-5
frame:
- Software & Technology
min_confidence: 0.7
capability_model:
  source: https://github.com/vincentmakes/turbo-ea-capabilities
  license: CC-BY-4.0
  attribution: Turbo EA Capabilities by Vincent Verdet — Turbo EA, https://github.com/vincentmakes/turbo-ea-capabilities,
    CC BY 4.0
  notice: NOTICE
edge_count: 2
edges:
- tag: Inference
  spec_file: scalable-inference-serving-inference-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.78
  evidence: POST /v2/models/{model_name}/infer RunInference Run Model Inference
  reason: The operations execute ML model inference against served model versions (InferenceRequest/InferenceResponse,
    TensorDatatype), which is the serving leg of the AI/ML model lifecycle under Artificial Intelligence
    Management. Some ambiguity remains as runtime inference could also be read as application operations.
- tag: Models
  spec_file: scalable-inference-serving-models-api-openapi.yml
  capability_id: BC-610.60
  capability_id_l1: BC-610
  capability_name: Artificial Intelligence Management
  confidence: 0.72
  evidence: GET /v2/models/{model_name}/versions/{model_version} GetModelVersionMetadata Get Model Version
    Metadata
  reason: Operations expose served ML models and their versions, including readiness and metadata, which
    is model lifecycle/MLOps territory under Artificial Intelligence Management.