@apicity/zaicoding

Z.ai GLM Coding Plan provider for Apicity — OpenAI-compatible chat completions plus coding-plan usage and quota monitoring.

Runtime dependencies:

zod@^4.4.3 — request schemas attached to every POST endpoint as .schema

Installation

npm install @apicity/zaicoding
# or
pnpm add @apicity/zaicoding

Quick Start

import { createZaiCoding } from "@apicity/zaicoding";

const zaicoding = createZaiCoding({
  apiKey: process.env.ZAI_CODING_PLAN_API_KEY!,
});

API Reference

4 endpoints across 2 groups. Each method mirrors an upstream URL path.

post

POST zaicoding.post.api.coding.paas.v4.chat.completions

POST https://api.z.ai/api/coding/paas/v4/chat/completions

Upstream docs ↗

const res = await zaicoding.post.api.coding.paas.v4.chat.completions({
  model: "glm-4-flash",
  messages: [{ role: "user", content: "Say hello." }],
});
console.log(res.choices[0].message.content);

Source: packages/provider/zaicoding/src/zaicoding.ts

get

GET zaicoding.get.api.monitor.usage.quota.limit

GET https://api.z.ai/api/monitor/usage/quota/limit

Upstream docs ↗

const res = await zaicoding.get.api.monitor.usage.quota.limit();
console.log(res.data?.level, res.data?.limits);

Source: packages/provider/zaicoding/src/zaicoding.ts

GET zaicoding.get.api.monitor.usage.modelUsage

GET https://api.z.ai/api/monitor/usage/model-usage

Upstream docs ↗

const res = await zaicoding.get.api.monitor.usage.modelUsage();
console.log(res.data?.totalUsage);

Source: packages/provider/zaicoding/src/zaicoding.ts

GET zaicoding.get.api.monitor.usage.toolUsage

GET https://api.z.ai/api/monitor/usage/tool-usage

Upstream docs ↗

const res = await zaicoding.get.api.monitor.usage.toolUsage();
console.log(res.data?.totalUsage);

Source: packages/provider/zaicoding/src/zaicoding.ts