agentutility$ man classify-text
/classify-text
NAME
classify-text — text classifier / zero-shot classifier / category sorter
SYNOPSIS
POST https://x402.agentutility.ai/classify-text
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Text classifier / zero-shot classifier / category sorter. Caller supplies labels (2-25). Multi-label mode. Calibrated confidences + reasoning. Mistral powered.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| text | string | Source text. Max 15,000 chars. | required |
| labels | array | Array of 2-25 candidate labels (strings, ≤80 chars each). | required |
| multi_label | boolean | If true, returns all labels that meaningfully apply. Default false (single best). | optional |
| label_descriptions | object | Optional { label: description } mapping for finer control. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| results | array | Array of {label, confidence}. |
| top_label | string | Highest-confidence label chosen from the caller's supplied label set. |
| reasoning | string | Short explanation of why the classifier picked the top label. |
| multi_label | boolean | True if multi-label mode was used (text can match more than one label). |
| labels | array | Array of label objects with name and calibrated confidence score, sorted by score descending. |
| input_chars | number | Character count of the input text submitted for classification. |
| model | string | Mistral model identifier used to produce the classification. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/classify-text \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# MCP packages on npm under # @agentutility/mcp-* (one per cluster) # # Catalog + install: # https://mcp.agentutility.ai # # Or call classify-text directly over HTTP — see above.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- classifycategorizemoderationroutingaillm
- env
- VENICE_API_KEY
- methods
- POST
- cluster
- wordmint
- price
- $0.02 USDC per call
ADJACENT — other endpoints in wordmint
| endpoint | description | price |
|---|---|---|
| classify | Zero-shot text classifier. | $0.02 |
| describe-image | AI image descriptor / vision LLM. | $0.02 |
| detect-pii | PII detector / data leak scanner. | $0.02 |
| email-draft | AI email writer / cold outreach / follow-up generator. | $0.02 |
| extract | Named entity extractor / NER. | $0.02 |
| moderate-content | Content moderation / safety classifier / OpenAI-style toxicity API. | $0.02 |
| resume-scorer | AI resume scorer / ATS keyword analyzer. | $0.02 |
| rewrite-tone | Tone rewriter / paraphraser / writing style changer. | $0.02 |
SEE ALSO