> ## Documentation Index
> Fetch the complete documentation index at: https://docs.omnia-voice.com/llms.txt
> Use this file to discover all available pages before exploring further.

# List model versions

> The workspace's improvement chain as immutable records — one version minted per completed training round. Each version pins what its verdict depended on (judge criterion, curriculum hash, holdout hash), and `comparable_to_parent` is true only when parent and child share a holdout hash, so round-over-round deltas are only trusted when they are actually comparable.

Requires an owner/admin key.



## OpenAPI

````yaml /openapi.json get /v1/model_versions
openapi: 3.1.0
info:
  title: Omnia Management API
  description: >-
    The management API behind the improvement loop: capture and setup, request
    logs and datasets, grades (labels), judges (criteria), evals and deploy
    gates, fine-tuning and reinforcement learning, dedicated GPU endpoints, and
    model aliases and versions. Authenticated with a workspace API key
    (sk_sovereign_...). The inference API (chat, embeddings, rerank, responses)
    is OpenAI-compatible and documented separately.


    Responses are snake_case, list endpoints on the loop products use the
    {"object": "list", "data": [...]} envelope, and refusals use the same nested
    error shape the gateway emits: {"error": {"message", "type", "code"}}.
    Request bodies on the loop products (logs, labels, criteria, evals,
    datasets, aliases) are snake_case; the training and infrastructure products
    (fine-tuning, GRPO, environment tools, dedicated, model-version adoption)
    validate camelCase bodies, and each schema below says which it is. Endpoints
    that spend money require a key minted by a workspace owner or admin and
    return 403 otherwise.
  version: 1.0.0
servers:
  - url: https://gateway.omnia-voice.com
    description: Production
  - url: https://platform.omnia-voice.com/api
    description: Production (legacy alias — same API, older base URL)
security:
  - bearerAuth: []
paths:
  /v1/model_versions:
    get:
      summary: List model versions
      description: >-
        The workspace's improvement chain as immutable records — one version
        minted per completed training round. Each version pins what its verdict
        depended on (judge criterion, curriculum hash, holdout hash), and
        `comparable_to_parent` is true only when parent and child share a
        holdout hash, so round-over-round deltas are only trusted when they are
        actually comparable.


        Requires an owner/admin key.
      operationId: listModelVersions
      parameters:
        - name: base_model
          in: query
          required: false
          schema:
            type: string
          description: Filter to one base model's lineage.
      responses:
        '200':
          description: The version chain, newest first.
          content:
            application/json:
              schema:
                type: object
                properties:
                  object:
                    type: string
                    enum:
                      - list
                  data:
                    type: array
                    items:
                      $ref: '#/components/schemas/ModelVersion'
components:
  schemas:
    ModelVersion:
      type: object
      properties:
        id:
          type: string
        parent_id:
          type: string
          nullable: true
          description: Previous version in this lineage; null for the first.
        base_model:
          type: string
        artifact_ref:
          type: string
          description: Where the trained weights live.
        served_model:
          type: string
          nullable: true
          description: The callable model name once served; null while unserved.
        source_run_id:
          type: string
        source_kind:
          type: string
          description: Which training path minted it (e.g. sft, raft, grpo).
        verdict:
          type: string
          description: >-
            The bake-off outcome this version carries (e.g. improved,
            inconclusive).
        judge_criterion_id:
          type: string
          description: The judge the verdict depended on.
        curriculum_hash:
          type: string
        holdout_hash:
          type: string
        comparable_to_parent:
          type: boolean
          description: True only when parent and child share a holdout hash.
        adopted_at:
          type: string
          format: date-time
          nullable: true
        created_at:
          type: string
          format: date-time
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Your workspace API key, e.g. `sk_sovereign_...`, sent as `Authorization:
        Bearer <key>`.

````