360 Secure SkillHub
360 安全技能中心

agentgates-inference

通过标准聊天补全接口调用保密或开放模型：每次请求先取 402 报价，再签名以 USDC 结算；可预付余额并用钱包认证或可撤销的 bearer 密钥批量调用。报价免费，服务失败可免费重放，该 Skill 会花费使用者的资金。

分类：自动化
agentgates
热度 9.88
最近更新 2026-11-03 13:18:16

安装

发给 Agent
帮我安装这个技能：npx secure-skills-cli add agentgates/agentgates-inference
兼容性
通用兼容
联网要求
需要联网
数据出网
必须出网
Metadata
name
agentgates-inference
description
Ask confidential or open models in the standard chat format, one request one x402 USDC payment, priced before the model runs; prepaid balances and bearer keys for volume.

Agentgates Inference: models by the request, paid in USDC (x402)

Ask models in the standard chat format. Confidential models run in attested hardware; an open tier is cheaper and carries no attestation, and every model names its tier. One request, one USDC payment. No signup: the paying wallet is the customer.

Endpoints (all on https://api.agentgates.ai)

  • GET /api/inference/docs: models, live prices, and the full contract. Read this first; prices move with gas and are never cached here.
  • GET /api/inference/catalog: models and prices, machine-readable JSON.
  • POST /api/inference/chat: ask. Body: {"model","messages","max_tokens"}.
  • POST /api/inference/credits: prepay a balance so one on-chain settle covers many requests.

The x402 loop

  1. POST with no X-PAYMENT header: 402 with an accepts array; each entry is one network's own offer for YOUR body. Quoting is free and repeatable.
  2. Sign that entry's amount as an EIP-3009 TransferWithAuthorization.
  3. Retry the same request with the signature in X-PAYMENT. The answer carries the completion and the settlement.

What a request costs

You pay for the tokens the provider counts, at the model's input and output rates, plus one settle per x402 request. The 402 asks for the ceiling (your prompt and your max_tokens); what the tokens did not cost comes back to your balance.

Cheaper at volume

Prepay a balance (POST /api/inference/credits) and then ask with an X-Wallet-Auth header and NO payment header: the settle happens once for the whole top-up. A wallet can also mint revocable bearer API keys on its prepaid balance, so plain Authorization: Bearer clients work; the mint contract is in GET /api/inference/docs.

Rules that keep you safe

  • Give reasoning models room: a ceiling too small can end at finishReason: "length" with little or no content, billed at its tokens.
  • A serve failure is a free replay, never a refund.

Spending

This skill spends its owner's money. Pay only what your owner allowed: ask your human before you pay, or stay inside a budget they set. Asking the price is free and never charges.