# Models & voices: Get a model (https://docs.envocal.ai/api-reference/models-and-voices/get-a-model/) > Requires agents:read ## GET `/v1/tenants/{tenantId}/models/{key}` **Required permission:** `agents:read` ### Parameters | Name | In | | Type | Description | | --- | --- | --- | --- | --- | | `tenantId` | path | required | string | Tenant id, or `current` for the key's own tenant. Must be the key's tenant or one of its sub-tenants. | | `key` | path | required | string | Model key, e.g. `gpt-realtime-1.5`. | ### Responses **200** — AiModelDto: The model. | Field | Type | | Description | | --- | --- | --- | --- | | `key` | string | required | The value to put in an agent's `model`, e.g. `gpt-realtime-1.5`. | | `name` | string | required | Display name. | | `description` | string | nullable | What the model is good at. | | `provider` | AiProviderDto | required | The company behind the model. | | `kind` | `speech-to-speech` \| `text` \| `tts` \| `stt` | required | Role in an agent: `speech-to-speech` models hear and speak themselves and come with their own voices; `text` models (LLMs) need separate speech recognition and voices; `tts` and `stt` are text-to-speech and speech-to-text models. Agents can use `speech-to-speech` models today. | | `inputModalities` | string[] | required | What the model takes in: `audio`, `text`. | | `outputModalities` | string[] | required | What the model gives out: `audio`, `text`. | | `languages` | string[] | required | Every language the model speaks (BCP 47, e.g. `sv`, `en-GB`). Its multilingual voices speak these, unless a voice lists fewer. Empty when the provider doesn't state a list: then any language counts. | | `supportsTools` | boolean | | Whether the model can call tools. | | `reasoningLevels` | string[] | required | For reasoning models, the levels an agent's `reasoningLevel` can take, from fastest to most thorough. Empty for models that don't reason. | | `defaultReasoningLevel` | string | nullable | The level used when an agent doesn't set one; null for models that don't reason. | | `isDefault` | boolean | | The model new agents get when none is given. | | `defaultVoice` | string | nullable | The voice new agents get with this model when none is given. | | `status` | `preview` \| `active` \| `deprecated` | required | `preview` (can be chosen, may change), `active`, or `deprecated` (still works, will be retired). | **401**: Missing, invalid, revoked or expired API key. **403**: The key lacks the required permission, or the tenant/resource is outside its reach. **404**: No such model. **429**: Rate limit exceeded. Retry after the number of seconds in the Retry-After header. ### Example ```bash curl -X GET "https://api.envocal.ai/v1/tenants/current/models/{key}" \ -H "Authorization: Bearer evk_eu_..." ```