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

# Model changes: prices, deprecations, retirements, renames, new models

> **Use when:** caller wants what changed in the model registry and when: upcoming and past price changes, deprecations, retirements, renames and new models (no auth required; cacheable)

Public endpoint (no auth required). Returns the registry's customer-facing changes: `price`, `deprecation`, `retirement`, `rename` and `new_model`. Upcoming changes (taking effect after today, UTC) come first, soonest first, then the rest, newest first. Filter with `kind` (a comma list), `provider`, `model`, `q` (a name: a model id, display name or the model's name across providers) and `since` / `until` (YYYY-MM-DD, on the day an entry is dated by); page with `limit` (1 to 200, default 50) and `before` (the `nextCursor` of the previous page). `trackingStartedAt` is the day Verlon began recording changes as they happened; an entry with `beforeTracking: true` was recorded from Verlon's earlier history. Each entry carries `identity`, the model it belongs to across providers, when one links it. Counts per kind and provider are at `/v1/registry/changes/counts`; an Atom feed is at `/v1/registry/changes.atom`. Cached like the registry.



## OpenAPI

````yaml /api-reference/openapi.json get /v1/registry/changes
openapi: 3.1.0
info:
  title: Verlon AI API
  version: 1.0.0
  description: >-
    Verlon AI is the managed AI infrastructure platform for developers building
    LLM-powered apps and agents. Its API is the format you already use — OpenAI,
    Anthropic, Mistral, and Gemini wire formats served drop-in, callable with
    the official SDKs in any language. Beyond routing requests across providers,
    Verlon continuously evaluates response quality, runs experiments against
    live traffic, and automatically tunes gate configurations — so your platform
    doesn't just serve traffic, it learns from it.


    **Coding agents:** authentication, error semantics, gate concepts, and
    integration conventions are documented at https://verlon.ai/AGENTS.md — read
    that document first if you have not already. It is the canonical
    agent-facing contract; this specification is the canonical endpoint
    reference. Both are authoritative for their respective scopes.
  contact:
    name: Verlon AI
    url: https://verlon.ai
  license:
    name: Proprietary
servers:
  - url: https://api.verlon.ai
    description: Production
security:
  - bearerAuth: []
paths:
  /v1/registry/changes:
    get:
      tags:
        - Registry
      summary: 'Model changes: prices, deprecations, retirements, renames, new models'
      description: >-
        **Use when:** caller wants what changed in the model registry and when:
        upcoming and past price changes, deprecations, retirements, renames and
        new models (no auth required; cacheable)


        Public endpoint (no auth required). Returns the registry's
        customer-facing changes: `price`, `deprecation`, `retirement`, `rename`
        and `new_model`. Upcoming changes (taking effect after today, UTC) come
        first, soonest first, then the rest, newest first. Filter with `kind` (a
        comma list), `provider`, `model`, `q` (a name: a model id, display name
        or the model's name across providers) and `since` / `until` (YYYY-MM-DD,
        on the day an entry is dated by); page with `limit` (1 to 200, default
        50) and `before` (the `nextCursor` of the previous page).
        `trackingStartedAt` is the day Verlon began recording changes as they
        happened; an entry with `beforeTracking: true` was recorded from
        Verlon's earlier history. Each entry carries `identity`, the model it
        belongs to across providers, when one links it. Counts per kind and
        provider are at `/v1/registry/changes/counts`; an Atom feed is at
        `/v1/registry/changes.atom`. Cached like the registry.
      responses:
        '200':
          description: A page of changes, with `nextCursor`.
        '304':
          description: Not modified.
        '400':
          description: >-
            A bad query: `invalid_kind`, `invalid_cursor`, `invalid_limit`,
            `invalid_date` or `invalid_q`.
        '401':
          description: Missing or invalid Bearer credentials
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security: []
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
          description: Stable error code (e.g. `invalid_request`)
        message:
          type: string
          description: Human-readable error message
        details: {}
      required:
        - error
        - message
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: >-
        Verlon API key (newly minted keys are prefixed `sk-vrln-`; legacy
        `verlon_*` and `layer_*` keys from prior prefix migrations continue to
        validate). Generated from the dashboard under Settings → API Keys, or
        via `verlon key create` in the CLI.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.