judge_output $0.07 per call

Independent LLM-as-judge: scores a candidate output against a task and criteria (0-100), with pass/fail, issues and suggestions. Use it for self-verification, best-of-N, or QA gates.

For AI agents: call judge_output
POST https://toll402.dev/v1/judge
{
 "task": "Write a haiku about the sea",
 "candidate": "Waves fold into foam / salt wind combs the sleeping dunes / gulls stitch the grey sky",
 "criteria": [
  "is a haiku (5-7-5)",
  "imagery"
 ]
}
Answers 402 with x402 payment requirements; pay with any x402 client (@x402/fetch, x402 for Python, toll402-client, toll402-mcp) or send a prepaid-credits key as x-toll402-key (https://toll402.dev/credits). Paid per call via x402 (USDC on Base) or with a prepaid-credits key (x-toll402-key, card at /credits); charged only on success. Start at /llms.txt or connect the MCP server: npx -y toll402-mcp · remote https://toll402.dev/mcp.

Input schema

{
 "type": "object",
 "properties": {
  "task": {
   "type": "string",
   "description": "The task/instructions the candidate was supposed to fulfil",
   "maxLength": 20000
  },
  "candidate": {
   "type": "string",
   "description": "The output to evaluate",
   "maxLength": 100000
  },
  "reference": {
   "type": "string",
   "maxLength": 100000,
   "description": "Optional gold/reference answer"
  },
  "criteria": {
   "type": "array",
   "items": {
    "type": "string",
    "maxLength": 300
   },
   "minItems": 1,
   "maxItems": 10,
   "default": [
    "correctness",
    "completeness",
    "clarity"
   ]
  }
 },
 "required": [
  "task",
  "candidate"
 ],
 "additionalProperties": false
}

Example output

{
 "overall": 88,
 "pass": true,
 "scores": [
  {
   "criterion": "is a haiku (5-7-5)",
   "score": 90,
   "rationale": "..."
  }
 ],
 "issues": [],
 "suggestions": []
}

MCP

{"mcpServers":{"toll402":{"command":"npx","args":["-y","toll402-mcp"],"env":{"TOLL402_WALLET_KEY":"0x..."}}}}

All tools · OpenAPI