# Get chat model

`GET https://api.endless.app/chat-models/{chat_model_id}`

Source: https://endless.app/docs/api/chat-models/get

Returns a single chat model. Scoped to the chat model named by `chat_model_id`.

## Authentication

- `bearerAuth`: HTTP bearer (JWT)

## Parameters

| Name | In | Type | Required | Description |
| --- | --- | --- | --- | --- |
| `chat_model_id` | path | string (uuid) | yes |  |
| `Endless-Api-Version` | header | string | no | Pin the caller to an API major (`1`). Omit to accept the current version. A major this deployment cannot serve is refused with 400 `unsupported_api_version`. |

## Responses

### 200 OK

Content type: `application/json` — object

- `model` (object, required)
  - `id` (string (uuid), required)
  - `codename` (string, required)
  - `name` (string, required)
  - `owner` (string | null, required)
  - `description` (string | null, required)
  - `thinking_options` (string | number | boolean | null | object | array<any | null> | null, required)
  - `cost_input` (string, required)
  - `cost_output` (string, required)
  - `cost_cache_read` (string, required)
  - `cost_cache_write` (string, required)
  - `minimum_required_plan` ("hobby" | "basic" | "pro" | "business" | null, required)
  - `position` (number, required)
  - `staff` (boolean, required)
  - `deleted_at` (string (date-time) | null, required)
  - `deleted_by_id` (string | null, required)
  - `created_at` (string (date-time), required)
  - `updated_at` (string (date-time), required)
- `variants` (array<object>, required)
  - `id` (string (uuid), required)
  - `chat_model_id` (string (uuid), required)
  - `gateway_model_id` (string | null, required)
  - `vertex_model_id` (string | null, required)
  - `enabled` (boolean, required)
  - `priority` (integer, required)
  - `deleted_at` (string (date-time) | null, required)
  - `created_at` (string (date-time), required)
  - `updated_at` (string (date-time), required)
  - `provider` ("gateway" | "vertex" | null, required)
  - `provider_model_id` (string | null, required)
  - `mirror_name` (string | null, required)
  - `mirror_missing` (boolean, required)
  - `mirror_deprecated` (boolean, required)
  - `vision` (boolean, required)
  - `knowledge_cutoff` (string | null, required)
  - `runnable` (boolean, required)
  - `serving` (boolean, required)
- `usage` (object, required)
  - `schedules` (number, required)

### Errors

- `400` (Error): The request is malformed, or failed input validation. `message` names the field and the rule it broke; `data.issues` carries them individually.
- `401` (Error): No bearer token, or a token that failed verification.
- `402` (Error): The workspace has no credits left, or the caller is over a spending limit.
- `403` (Error): Authenticated, but the caller's role in this workspace does not carry the permission this operation needs.
- `404` (Error): No resource with that id, or the caller cannot read it. The two are deliberately one answer, so an id cannot be probed for existence.
- `409` (Error): The request is well-formed, but the resource's current state forbids it — a taken name, a last admin, a limit already reached.
- `429` (Error): The caller has spent its rate-limit window. `Retry-After` says when to come back.
- `500` (Error): The request failed on our side. Safe to retry an idempotent operation with backoff.