# remove_question (/reference/remove-question)



A question the calibrated score uses is removed with `remove_questions` when you [calibrate](/reference/calibrate) instead. See [Changing questions](/concepts/scoring-models#changing-questions). Free.

## DELETE https://api.finic.ai/v1/scoring_models/{model_id}/questions/{question_id}

Removes a question from a scoring model, without calibrating it. A removed question isn't asked or tried again.

- **If it isn't calibrated yet,** you can remove any question, as long as one is left.
- **If it's calibrated,** you can remove your own questions it doesn't use. A question the score uses is removed with `remove_questions` when you [calibrate](/reference/calibrate), so the score is refit without it.

Authorization: `Bearer <API key>` (see [Authentication](/authentication)).
- Path parameter `model_id`: The scoring model's `model_id`.
- Path parameter `question_id`: The question's `id`, from [get_scoring_model](/reference/get-scoring-model).

### Responses

- **200**: The scoring model, as [get_scoring_model](/reference/get-scoring-model) returns it.

| Field | Type | Always | Description |
| --- | --- | --- | --- |
| `model_id` | string | yes | The scoring model's id, `scm_…`. |
| `name` | string | yes | A few words saying what it predicts: the `name` it was created with, or the one it was given in the Finic Portal. Empty for scoring models created before names, until someone names it there. |
| `status` | `training`, `ready`, `failed` | yes | `training` while it's being created, `ready` to score records, `failed` if creating it failed (create it again). |
| `criteria` | string | yes | The `criteria` it was created with. Empty if none was given. |
| `created_at` | string | yes | When the scoring model was created. |
| `calibrated_at` | string or null | yes | When it was last [calibrated](/reference/calibrate), or `null` if it isn't calibrated. One created from examples is calibrated from the start; one created from its criteria alone scores with Finic's estimated weights until you calibrate it. |
| `archived_at` | string or null | yes | When it was archived in the Finic Portal, or `null`. Calls to score with or calibrate an archived scoring model fail with `scoring_model_archived` until it's unarchived. |
| `examples` | integer | yes | The number of examples it was created from, or first calibrated with; 0 until then. |
| `bad_rate` | number | yes | The share of those examples with `is_bad` true, 0 to 1; 0 until then. |
| `scored` | integer | yes | The number of records [scored](/reference/score) with it. |
| `outcomes` | integer | yes | The number of those records with an outcome sent to calibrate. |
| `questions` | array of object | yes | The questions it uses, the strongest first. Your own questions it doesn't use are listed on its page in the Finic Portal. |
| `questions[].id` | string | yes | The question's id, such as `q007`, for [remove_question](/reference/remove-question) or `remove_questions`. |
| `questions[].text` | string | yes | The question |
| `questions[].source` | `finic`, `user` | yes | `finic` for a question Finic wrote, `user` for one you added. |
| `questions[].weight` | number | yes | How much it moves the score, from the latest calibration, or Finic's estimate if the scoring model isn't calibrated yet. Positive when a likely yes raises the score, negative when it lowers it; the larger, the more it counts. |

```json
{
  "model_id": "scm_01M4XRC000RT2GZSKYPD8J86G9",
  "name": "Card-not-present payment fraud",
  "status": "ready",
  "criteria": "Card-not-present payments at an online store. Bad: the payment was charged back as fraud within 90 days.",
  "created_at": "2026-10-20T17:04:11Z",
  "calibrated_at": null,
  "archived_at": null,
  "examples": 0,
  "bad_rate": 0,
  "scored": 12,
  "outcomes": 0,
  "questions": [
    {
      "id": "q003",
      "text": "This record is a card payment. Is the IP address in a different country from the billing address?",
      "source": "finic",
      "weight": 1.24
    },
    {
      "id": "q009",
      "text": "Was the account opened less than a week before the payment?",
      "source": "user",
      "weight": 0.93
    },
    {
      "id": "q006",
      "text": "This record is a card payment. Has this card paid this merchant before without a dispute?",
      "source": "finic",
      "weight": -0.71
    }
  ]
}
```

- **400**: `invalid_request`: it's the scoring model's last question. Add another before removing it.

- **401**: `authentication_error`: the API key is missing, unknown, revoked or expired.

- **404**: - `scoring_model_not_found`: no scoring model with this `model_id` in your organization.
  - `question_not_found`: the scoring model has no question with this id that you can see.

- **409**: - `question_in_use`: the calibrated score uses this question. Remove it with `remove_questions` when you calibrate.
  - `scoring_model_not_ready`: the scoring model is still being created, or creating it failed.
  - `scoring_model_archived`: the scoring model is archived.
  - `calibration_in_progress`: it's being calibrated. Remove the question when its job completes.
  - `conflict`: it changed at the same moment. Try again.

- **429**: `rate_limited`: 50 changes to this scoring model in the last 24 hours, or over the [request rate](/reference#rate-limits).