Assign text to exactly one label from a closed set you provide — support triage,
Assign text to exactly one label from a closed set you provide — support triage, intent routing, spam/not-spam, sentiment buckets. The answer is always one of your labels, copied verbatim, with a 0-1 confidence; if th...
Answeringour last check, 2026-10-10
1 of 1checks answered this week
1223 msmedian answer time
$0.008listed price per call
$0.008price it asked us
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://api.losbeto.xyz/classify
| Category | Everything else |
|---|---|
| Provider host | api.losbeto.xyz |
| Networks | algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=, eip155:137, eip155:8453, solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp |
| Payment schemes | exact |
| Self-reported calls, 30 days | 14 from 4 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-10 | valid payment request | 402 | $0.008 | 1223 ms |
Example input (from the provider)
{
"bodyParams": {
"labels": [
"billing",
"shipping",
"technical",
"other"
],
"text": "My card was charged twice"
},
"contentType": "application/json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"properties": {
"bodyParams": {
"properties": {
"labels": {
"description": "2-30 candidate labels; the answer is always one of them.",
"items": {
"type": "string"
},
"type": "array"
},
"text": {
"description": "Text to classify (max 6000 chars).",
"type": "string"
}
},
"required": [
"text",
"labels"
],
"type": "object"
},
"method": {
"description": "POST",
"type": "string"
}
},
"type": "object"
},
"output": {
"properties": {
"example": {
"description": "Assign text to exactly one label from a closed set you provide \u2014 support triage, intent routing, spam/not-spam, sentiment buckets. The answer is always one of your labels, copied verbatim, with a 0-1 confidence; if the model returns anything else the payment is returned as call credit. Do NOT use for open-ended tagging \u2014 that is /extract.",
"type": "object"
}
},
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}