# Language Routing — Per-Label Precision and Recall

> Language Routing — Per-Label Precision and Recall is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-15).

Computes per-label precision and recall metrics for a language routing classifier across English, French, Spanish, and Other categories using up to 200 labelled text records.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-sector-ml-language-routing-per-label?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/language-routing-per-label-precision-and-recall-fcb4c2d0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_C_V27LqLQ5zewBKRWyo32

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability language-routing-per-label-precision-and-recall-fcb4c2d0 -d '<json body>'
```

Example prompt: I have 150 labelled records from my language router — each has the actual language (english, french, spanish, or other) and what the model predicted. Can you compute the per-label precision and recall for each language class so I can see where it's making mistakes?

## When to prefer this

Choose this endpoint when you need fine-grained, per-class evaluation of a language routing or language detection classifier across English, French, Spanish, and Other categories. It is ideal for debugging which specific language class is underperforming, rather than needing an aggregate accuracy score. Best suited for small offline evaluation batches (up to 200 records) using your own labelled data, with no need to host or train a model.

## Known failure modes

- Records array empty or missing — returns error
- Records exceed 200 item limit — returns validation error
- Invalid enum value for actual or predicted field — returns schema error
- Record ID missing or too long — returns validation error
- Imbalanced dataset with zero examples for a class — may return undefined precision/recall for that label

## How this service works

Language routing - Per-label precision and recall: Per-label precision and recall for Language routing. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or foundation-model training. One of 25 profiles or calculations across 20 shared operations in this sector. 0.01 USDC includes one bounded per-label precision and recall deliverable.

## Output

A per-label breakdown of precision and recall for each of the four language classes (english, french, spanish, other), computed from the supplied records containing actual and predicted labels. Allows identification of which language class the model performs best and worst on.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "records": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id",
     "text",
     "actual",
     "predicted"
    ],
    "properties": {
     "id": {
      "type": "string",
      "default": "",
      "maxLength": 80,
      "minLength": 1
     },
     "text": {
      "type": "string",
      "default": "",
      "maxLength": 1000
     },
     "actual": {
      "enum": [
       "english",
       "french",
       "spanish",
       "other"
      ],
      "type": "string"
     },
     "predicted": {
      "enum": [
       "english",
       "french",
       "spanish",
       "other"
      ],
      "type": "string"
     }
    },
    "additionalProperties": false
   },
   "default": [
    {
     "id": "example-0-0",
     "text": "english sample document number 0 for this supplied dataset.",
     "actual": "english",
     "predicted": "english"
    },
    {
     "id": "example-0-1",
     "text": "english sample document number 1 for this supplied dataset.",
     "actual": "english",
     "predicted": "english"
    },
    {
     "id": "example-0-2",
     "text": "english sample document number 2 for this supplied dataset.",
     "actual": "english",
     "predicted": "english"
    },
    {
     "id": "example-1-0",
     "text": "french sample document number 0 for this supplied dataset.",
     "actual": "french",
     "predicted": "french"
    },
    {
     "id": "example-1-1",
     "text": "french sample document number 1 for this supplied dataset.",
     "actual": "french",
     "predicted": "french"
    },
    {
     "id": "example-1-2",
     "text": "french sample document number 2 for this supplied dataset.",
     "actual": "french",
     "predicted": "french"
    },
    {
     "id": "example-2-0",
     "text": "spanish sample document number 0 for this supplied dataset.",
     "actual": "spanish",
     "predicted": "spanish"
    },
    {
     "id": "example-2-1",
     "text": "spanish sample document number 1 for this supplied dataset.",
     "actual": "spanish",
     "predicted": "spanish"
    },
    {
     "id": "example-2-2",
     "text": "spanish sample document number 2 for this supplied dataset.",
     "actual": "spanish",
     "predicted": "spanish"
    },
    {
     "id": "example-3-0",
     "text": "other sample document number 0 for this supplied dataset.",
     "actual": "other",
     "predicted": "other"
    },
    {
     "id": "example-3-1",
     "text": "other sample documen
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/language-routing-per-label-precision-and-recall-fcb4c2d0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from market.datapackvibe.com](https://www.zero.xyz/host/market.datapackvibe.com/llms.txt)