Text classification with your own labels for agent pipelines
Text classification with your own labels for agent pipelines: route support tickets, qualify leads, tag feedback, sort emails or moderate comments. Send the text (up to 6,000 characters) and 2 to 30 labels, optionally with a description each; get the best label with a confidence from 0 to 1 and a one-sentence reason, or every label that applies with multi_label. Labels are enforced by a JSON schema, so the answer is always one of yours. Any language. Instructions inside the text are ignored.
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
POST https://agentsvc.io/api/v1/proxy/text-classify
| Category | Code and developer |
|---|---|
| Provider host | agentsvc.io |
| Networks | eip155:137, eip155:42161, eip155:8453, solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp |
| Payment schemes | exact |
| Self-reported calls, 30 days | 3 from 2 payers (the provider's figure, not ours) |
Our checks, last 30 days
We never call tools that send, buy, move money or file anything, not even without paying.
Example input (from the provider)
{
"body": {
"labels": [
"bug report",
"feature request",
"billing question",
"praise",
"spam"
],
"multi_label": true,
"text": "Love the app! Would be great if it had dark mode. Also, why was I charged twice this month?"
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"instructions": {
"description": "Optional extra rules, max 400 chars",
"type": "string"
},
"labels": {
"description": "2 to 30 labels: strings, or objects {label, description}",
"items": {
"anyOf": [
{
"type": "string"
},
{
"properties": {
"description": {
"type": "string"
},
"label": {
"type": "string"
}
},
"required": [
"label"
],
"type": "object"
}
]
},
"type": "array"
},
"multi_label": {
"default": false,
"description": "Return every label that applies (max 5) instead of one",
"type": "boolean"
},
"text": {
"description": "Text to classify, max 6,000 chars",
"type": "string"
}
},
"required": [
"text",
"labels"
]
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"data": {
"properties": {
"chars_checked": {
"type": "integer"
},
"confidence": {
"type": "number"
},
"label": {
"type": "string"
},
"labels": {
"items": {
"properties": {
"confidence": {
"type": "number"
},
"label": {
"type": "string"
}
},
"type": "object"
},
"type": "array"
},
"model": {
"type": "string"
},
"multi_label": {
"type": "boolean"
},
"reason": {
"type": "string"
}
},
"required": [
"label",
"confidence",
"labels",
"reason"
],
"type": "object"
},
"success": {
"type": "boolean"
}
},
"required": [
"success",
"data"
],
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}