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

# List models

> List model IDs and availability in an OpenAI-compatible shape. No auth required.
Use the `id` value as the `model` field in inference requests.


## What's in the response

* Each entry's **`id`** is what you pass as `model` on `/chat/completions`. Use it verbatim — IDs are case-sensitive.
* **`status`** is the only mutable field worth checking:
  * `ready` — at least one healthy replica is serving. Use it.
  * `unavailable` — model is not currently serving. Don't use; retry later or fall back to another model.
* A model that's `ready` here can still return `503` on `/chat/completions` if its replica falls over between calls. Always handle `503` with a retry or a fallback to another `ready` model.

This endpoint is the **only** one that doesn't require an API key. List it before every session — don't hardcode model IDs.


## OpenAPI

````yaml GET /models
openapi: 3.0.3
info:
  title: Overshoot API
  version: 1.0.0-beta
  description: >
    Real-time video understanding API. Create a live video stream, push frames
    over

    WebRTC (LiveKit), then ask a vision-language model questions about what's
    happening

    using an OpenAI-compatible chat completions endpoint.


    Billing endpoints are mounted on the same host under `/billing`.
servers:
  - url: https://api.overshoot.ai/v1beta
security:
  - bearerAuth: []
tags:
  - name: Streams
    description: Create, inspect, keep alive, and delete live video streams.
  - name: Models
    description: List available vision-language models.
  - name: Chat
    description: Ask models questions about a stream's frames.
  - name: Billing
    description: Pricing, prepaid balance, and checkout.
paths:
  /models:
    get:
      tags:
        - Models
      summary: List models
      description: >
        List model IDs and availability in an OpenAI-compatible shape. No auth
        required.

        Use the `id` value as the `model` field in inference requests.
      operationId: listModels
      responses:
        '200':
          description: List of models.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelsResponse'
      security: []
components:
  schemas:
    ModelsResponse:
      type: object
      properties:
        object:
          type: string
          default: list
        data:
          type: array
          items:
            $ref: '#/components/schemas/ModelInfo'
      required:
        - object
        - data
    ModelInfo:
      type: object
      properties:
        id:
          type: string
          example: google/gemma-4-26B-A4B-it
          description: >-
            Model identifier. Pass this verbatim as the `model` field on
            `/chat/completions`.
        object:
          type: string
          default: model
        created:
          type: integer
          description: Unix seconds when the model entry was registered.
        owned_by:
          type: string
          example: overshoot
        status:
          type: string
          enum:
            - ready
            - unavailable
          description: >-
            `ready` = currently serving. `unavailable` = not currently
            available.
      required:
        - id
        - object
        - created
        - owned_by
        - status
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key (e.g. `ovs_...`)
      description: >
        Every public HTTP request requires `Authorization: Bearer <api_key>`,
        except

        `GET /models` and the public `/billing/pricing` endpoints.


        - `401` means the key is missing, unknown, or revoked.

        - `403` means the key is valid but cannot access the requested resource.

        - The publish token returned by `POST /streams` is only for publishing
        media to
          LiveKit. It does not replace the API key for HTTP calls.

````