Antfly · Schema

InferenceModelInstance

One loading or loaded incarnation of a model in this inference server. Backend session and composite-cache implementation details are private.

Artificial IntelligenceSearchRetrievalVectorsHybrid

Properties

Name Type Description
id string Opaque incarnation identifier; changes after eviction and reload.
model string
tasks array
state string
active_handles integer Internal owners or loading waiters preventing eviction. This is not a count of HTTP requests.
startup_managed boolean
unloadable boolean Whether an unload would be permitted at snapshot time; concurrent use can change this.
unload_blocked_reason string
backend string Selected execution backend, when known.
residency_mode string Weight residency policy; loaded does not imply full device residency.
idle_ms integer Elapsed milliseconds since last use, not a wall-clock timestamp.
View JSON Schema on GitHub

JSON Schema

antfly-inference-model-instance-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/antfly/json-schema/antfly-inference-model-instance-schema.json",
  "title": "InferenceModelInstance",
  "description": "One loading or loaded incarnation of a model in this inference server. Backend session and composite-cache implementation details are private.",
  "x-generated": "2026-11-10",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/antfly-models-api-openapi.yml#/components/schemas/InferenceModelInstance",
  "type": "object",
  "required": [
    "id",
    "model",
    "tasks",
    "state",
    "active_handles",
    "startup_managed",
    "unloadable",
    "residency_mode",
    "idle_ms"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Opaque incarnation identifier; changes after eviction and reload."
    },
    "model": {
      "type": "string"
    },
    "tasks": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/InferenceModelKind"
      }
    },
    "state": {
      "type": "string",
      "enum": [
        "loading",
        "loaded"
      ]
    },
    "active_handles": {
      "type": "integer",
      "format": "int64",
      "description": "Internal owners or loading waiters preventing eviction. This is not a count of HTTP requests."
    },
    "startup_managed": {
      "type": "boolean"
    },
    "unloadable": {
      "type": "boolean",
      "description": "Whether an unload would be permitted at snapshot time; concurrent use can change this."
    },
    "unload_blocked_reason": {
      "type": "string",
      "enum": [
        "loading",
        "in_use",
        "startup_managed"
      ]
    },
    "backend": {
      "type": "string",
      "description": "Selected execution backend, when known."
    },
    "residency_mode": {
      "type": "string",
      "enum": [
        "backend_managed",
        "streamed",
        "resident"
      ],
      "description": "Weight residency policy; loaded does not imply full device residency."
    },
    "idle_ms": {
      "type": "integer",
      "format": "int64",
      "description": "Elapsed milliseconds since last use, not a wall-clock timestamp."
    }
  },
  "$defs": {
    "InferenceModelKind": {
      "type": "string",
      "description": "Model registry kind.",
      "enum": [
        "generator",
        "embedder",
        "reranker",
        "chunker",
        "classifier",
        "rewriter",
        "reader",
        "transcriber",
        "extractor"
      ]
    }
  }
}

Work with this as data

Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/antfly-inference-model-instance"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.