---
title: "Quantized Credit Model Scorer"
method: POST
path: "/v1/tools/score_credit_model_quantized"
tags: ["TODO_TAGS_REVIEW"]
---

# Quantized Credit Model Scorer

`POST /v1/tools/score_credit_model_quantized`

## Request

- Base URL: `https://ainumbers.co`
- URL: `https://ainumbers.co/v1/tools/score_credit_model_quantized`
- Auth: none declared

Runs a fixed, int8-quantized logistic-regression-class credit-decisioning model as a pure integer inference kernel and returns the score it produced from the supplied normalized inputs. Proves that THIS fixed quantized model produced THIS score from THESE inputs. It is not a fairness attestation and not a model-quality certification, and the underlying model is a synthetic offline demand-test artifact, not fit for real regulatory credit decisioning. The quantization_parity block on the artifact records the float-vs-quantized agreement rate measured over 1000 held-out vectors.

**Tool URL:** https://ainumbers.co/chaingraph/art-348-score-credit-model-quantized.html
**AP2/Policy Mandate export:** yes

## Request body

- object
  - `normalized_fixp16` unknown[], required
    - unknown

## Response `200`

Successful tool execution result

- object
  - `accumulator_fixp` integer
  - `bits` integer
  - `decision` integer
  - `n_features` integer
  - `quant_method` string
  - `threshold_fixp` integer

---

[API](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite.md) · [All operations](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite/llms.txt) · [OpenAPI document](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite/revisions/b462e4f5bb28?raw)