---
title: "List deployed prediction models"
method: GET
path: "/v1/models"
tags: ["catalog"]
---

# List deployed prediction models

`GET /v1/models`

## Request

- Base URL: `https://api.predixsport.com` (the document declares no server; this is the origin it was published from)
- URL: `https://api.predixsport.com/v1/models`
- Auth: none declared

Returns metadata (sport, task, target, classes if multiclass) for every deployed model. Use the model `id` to query its calibration via `/v1/calibration/{sport}/{model}`.

## Query parameters

- `sport` 'nba' | 'euroleague' | 'football' | 'tennis' | 'wta' | 'champions'

## Headers

- `authorization` string, nullable

## Response `200`

Successful Response

- ModelsResponse
  - `models` ModelInfo[], required
    - `id` string, required: Stable identifier, e.g. "nba_winner".
    - `sport` 'nba' | 'euroleague' | 'football' | 'tennis' | 'wta' | 'champions', required
    - `task` string, required: One of: "binary_classifier", "multiclass_classifier", "poisson_regressor", "negbin_regressor".
    - `target` string, required: Human-readable target description.
    - `classes` string[], nullable: Class labels (multiclass models only).
    - `deployed_since` string, nullable: ISO date the model was first deployed to production.
    - `notes` string, nullable
    - `calibration_basename` string, nullable: Internal short name used to locate this model's calibration file on disk (``*_calibration_data_<basename>_deploy.json``). Customers normally don't need this — pass ``id`` to ``/v1/calibration/{sport}/{id}`` and the service resolves it. Exposed for transparency.
  - `count` integer, required

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/predixsport/apis/predixsport-api.md) · [All operations](https://skmtc.dev/predixsport/apis/predixsport-api/llms.txt) · [OpenAPI document](https://skmtc.dev/predixsport/apis/predixsport-api/revisions/026afdfa7802?raw)