Judge long documents (preview)
POST /v1/judge/longThe typed questions of /v1/judge over a document of up to 900 KB (about 262k tokens), in one call. Send POST /v1/judge/long with the required fields state and questions and pay $0.02 per call over x402 or MPP (there is no free tier). It returns the result.
Preview: built on Jev features its maker labels experimental. Answers come from a model, not deterministic code.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
state | string | object | yes | The document, up to 900000 bytes. |
questions | object | yes | Your own ids mapped to { type: noul | choice | score, instructions, criteria }, as on /v1/judge. |
model | string (one of: jev-latest, jev-preview) | no |
Example request
curl -i -X POST https://agent402.tools/v1/judge/long \
-H "Content-Type: application/json" \
-d '{"state":"Section 1. The tenant pays rent on the first of each month. Section 2. Either party may end this lease with 60 days written notice.","questions":{"has_notice":{"type":"noul","instructions":"Does the document set a notice period for ending the agreement?"}}}'
Without payment this returns HTTP 402 Payment Required with the exact price for judge-long; any x402 v2 or MPP client pays it and retries.
Example response
{}
From an MCP client
catalog.call {
"slug": "judge-long",
"params": {
"state": "Section 1. The tenant pays rent on the first of each month. Section 2. Either party may end this lease with 60 days written notice.",
"questions": {
"has_notice": {
"type": "noul",
"instructions": "Does the document set a notice period for ending the agreement?"
}
}
}
}
The hosted connector at https://agent402.tools/mcp needs a payment for judge-long; the stdio package pays it from a wallet or from an AGENT402_CREDITS_KEY issued earlier. Local install: npx -y agent402-mcp.
Errors and behavior
stateandquestionsare required. An input the tool rejects returns an HTTP 4xx whose body carrieserror,tool,expected,requiredandexample, so the caller can correct it.- A paid call that ends in any status of 400 or above is not charged over x402, MPP or a prepaid credits key: settlement is cancelled when the tool fails. The exception is a Tempo push credential, a transfer the buyer sent before the call: it settles before the tool runs, so if the tool then fails the payment is recorded as a refund owed to the paying wallet.
- Wallet-only: this tool runs a model, so it has no proof-of-work tier. A prepaid card-credits key issued earlier (
Authorization: Bearer a402_...) also pays it. - Model-backed: the answer is generated by a model, so the same input can produce a different result.
- A
GETorHEADto /v1/judge/long returns the same 402 quote, so the price can be read without a body. - An
Idempotency-Keyheader makes a retried paid call replay the first 200 instead of charging again (an answer larger than 1 MB and a streamed response are not replayed).
Paid call (JavaScript agent)
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
const client = new x402Client();
client.setSpendControls?.({ maxAmountPerPayment: "$0.02" }); // refuse any quote above this tool's price
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);
const res = await payFetch("https://agent402.tools/v1/judge/long", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
"state": "Section 1. The tenant pays rent on the first of each month. Section 2. Either party may end this lease with 60 days written notice.",
"questions": {
"has_notice": {
"type": "noul",
"instructions": "Does the document set a notice period for ending the agreement?"
}
}
}),
});
Related tools
Judge images (preview)
POST /v1/judge/visionAsk typed questions about up to 4 images (PNG or JPEG) and get answers your code can branch on: noul (yes/no.
Decisions (OpenAI wire)
POST /v1/decisionsOpenAI's Decisions API on its own wire: point an OpenAI SDK's base URL here and client.decisions.create works unchanged.
Typed judgment
POST /v1/judgeAsk a typed question about any content and get an answer your code can branch on, not prose to parse.
Locate in image (preview)
POST /v1/judge/locateFind up to 4 things in one image: each comes back with whether it is there (a probability) and its box, as edges from 0.
Image generation
POST /api/image-genGenerate an image from a text prompt using GPT Image 2 (low quality, 1024x1024).
Image generation (HD)
POST /api/image-gen-hdGenerate a higher-quality image from a text prompt using GPT Image 2 (medium quality, 1024x1024).