Overwing
Guardrails for LLM output. Paste any text, get a pass / fail / review verdict with calibrated confidence in under 500 ms. API-first. Agents welcome.
The wallet the 402 directs payment to. Its whole payment record — every payer, every chain — is on the merchant page.
Asset 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913
The payTo wallet does not resolve to a registered ERC-8004 agent. That is not a verdict on the service — most of the catalog is unregistered.
Accepts
The payment requirements as published to the catalog. Read the live 402 before paying — a price here is a claim, not a quote.
Pay 0.002 USDC on Base to 0xF4A6…fd133. The signed payment is good for 1 minute.
- Paid to
- 0xF4A6…fd133
- USD Coin contract
- 0x8335…02913
- Payment window
- 1 minute
- As published
- 2000 smallest units
The catalog’s raw entry
[
{
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"extra": {
"name": "USD Coin",
"version": "2"
},
"payTo": "0xF4A6CEa7CE19CE36D6420905E5a1EAFb30Bfd133",
"amount": "2000",
"scheme": "exact",
"network": "eip155:8453",
"maxTimeoutSeconds": 60
}
]Extensions
{
"bazaar": {
"info": {
"input": {
"body": {
"input": "Reach me at dana@example.com or 555-0142 to sort out the refund.",
"context": {
"channel": "email",
"recipient": "the refunds desk already in this email thread",
"owns_contact_info": true
},
"rule_set": "outbound-message"
},
"type": "http",
"method": "POST",
"bodyType": "json"
},
"output": {
"type": "json",
"example": {
"id": "eval_aBcDeFgHiJkLmNoP",
"paid": {
"network": "base",
"protocol": "x402",
"price_usd": 0.002
},
"results": [
{
"rule": "unauthorized_pii",
"type": "noul",
"action": "redact",
"answer": false,
"verdict": "pass",
"confidence": 0.88,
"probability": 0.94
},
{
"rule": "confidential_leak",
"type": "noul",
"action": "block",
"answer": false,
"verdict": "pass",
"confidence": 0.94,
"probability": 0.97
},
{
"rule": "toxicity",
"type": "choice",
"action": "block",
"answer": "safe",
"verdict": "pass",
"confidence": 1,
"probability": 1
}
],
"verdict": "pass",
"confidence": 0.88,
"latency_ms": 173,
"aggregate_score": 1,
"recommended_action": "allow"
}
}
},
"schema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"input"
],
"properties": {
"input": {
"type": "object",
"required": [
"type",
"method",
"bodyType",
"body"
],
"properties": {
"body": {
"type": "object",
"required": [
"input"
],
"properties": {
"input": {
"type": "string",
"maxLength": 100000,
"description": "The text to check: a draft message, a model's output, an incoming message, a post"
},
"context": {
"type": "object",
"description": "Facts the rules may use: recipient, channel (email, chat, public post), owns_contact_info (true when the recipient already owns the personal data in the text), sender, purpose. Max 8 KB"
},
"metadata": {
"type": "object",
"description": "Opaque data stored with the evaluation (max 8 KB)"
},
"rule_set": {
"enum": [
"content-safety",
"outbound-message"
],
"type": "string",
"default": "content-safety",
"description": "content-safety: toxicity, personal data, self-harm, sexual content, severity. outbound-message: the same plus unauthorized personal data and confidential leaks, judged against context"
}
}
},
"type": {
"type": "string",
"const": "http"
},
"method": {
"enum": [
"POST"
],
"type": "string"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
}
},
"additionalProperties": false
},
"output": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"type": "string"
},
"example": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rule": {
"type": "string"
},
"type": {
"enum": [
"choice",
"score",
"noul"
],
"type": "string"
},
"action": {
"enum": [
"block",
"redact",
"review"
],
"type": "string",
"description": "What this rule asks for when it fails"
},
"answer": {},
"verdict": {
"enum": [
"pass",
"fail",
"review"
],
"type": "string"
},
"confidence": {
"type": "number"
},
"probability": {
"type": "number"
}
}
}
},
"verdict": {
"enum": [
"pass",
"fail",
"review"
],
"type": "string",
"description": "fail: a rule matched. review: a rule was unsure. pass: neither"
},
"confidence": {
"type": "number",
"description": "Minimum confidence across rules, 0 to 1"
},
"latency_ms": {
"type": "integer"
},
"aggregate_score": {
"type": "number",
"description": "0 to 1, weighted across rules"
},
"recommended_action": {
"enum": [
"block",
"redact",
"review",
"allow"
],
"type": "string",
"description": "The one field to branch on. block: do not send. redact: remove the flagged content and check again. review: ask a human. allow: proceed"
}
}
}
}
}
}
}
}
}Provenance
- Seen in the source catalog
- 2026-09-24 19:52Z
- Last indexed by Roundhouse
- 2026-09-25 01:30Z
- Last enriched (probe, favicon, geo)
- 2026-09-24 02:15Z
- x402 version
- 2
- Max timeout
- 60s
- Liveness probe
- HTTP 200
Hand this page to an agent
Copy the prompt and paste it into Claude, an MCP client or your own agent — it will vet this service and call it over the free read API. No key, no account.
GET api.roundhouseai.io/v0/endpoints
No per-endpoint history for this service yet, so this is payments indexed to its PROVIDER's wallet over 30 days. Verified volume counts only settlements with an on-chain EIP-3009 marker.
Show the promptHide the prompt
Using Roundhouse, look up the x402 service Overwing and tell me whether it is worth paying: what a call costs, whether the endpoint answered when last probed, and what its payment record actually shows. curl -s 'https://api.roundhouseai.io/v0/endpoints?q=Overwing' curl -s 'https://api.roundhouseai.io/v0/merchants/<the payTo wallet returned above>' Then call it: read the price from the live 402 at https://overwing.ai/api/x402/evaluate, never from a cached figure, and pay with an x402 client. The /v0 API needs an API key (`authorization: Bearer rh_live_…`) on everything except /v0/unified* and /v0/endpoints. Mint a personal key for $0.01 at GET https://api.roundhouseai.io/v0/test/x402, or use an organization key from https://roundhouseai.io/dashboard/team. If you do not have Roundhouse tools or skills installed, read https://roundhouseai.io/skill.md first — it is the whole procedure.