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

# Models

> Tazo Large and Tazo Small, and what each one supports.

| Model | ID | Supports |
| - | - | - |
| Tazo Large | `tazo-large` | One `choice` or `noul` question. A `choice` has 2 to 32 options. |
| Tazo Small | `tazo-small` | One `choice` question with 2 to 32 options, including a `NO_TOOL` option. |

`tazo-large` is the default when `model` is omitted.

## Check capabilities at runtime

Call [`GET /v1/models`](/api-reference/models/list-models) to see each model's
`capabilities` and whether it is `ready`. Use this instead of hard-coding limits.

```bash theme={null}
curl https://api.tazolabs.com/v1/models \
  -H "Authorization: Bearer $TAZO_API_KEY"
```

| Capability | Meaning |
| - | - |
| `question_types` | Question types the model accepts. |
| `max_questions` | Most questions allowed in one request. |
| `max_choice_options` | Most options in a `choice` question. |
| `requires_no_tool_choice` | Whether the request must include a `NO_TOOL` choice. |
| `max_audio_seconds` | Longest audio accepted, if limited. |
| `required_sample_rate_hz` | Required sample rate, if any. |

## Legacy model names

Older internal model IDs and the previous `general` and `specialised` aliases
are still accepted as input during migration. Responses and `/v1/models` always
use `tazo-large` and `tazo-small`.

If you compare the request `model` with the response `model`, switch your
requests to the new names. Aliases are resolved before idempotency checks, so a
retry that uses an alias or its legacy ID reuses the same job.


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