@apicity/google

Google Gemini provider for express-mode generateContent.

Runtime dependencies:

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

Installation

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

Quick Start

import { createGoogle } from "@apicity/google";

const google = createGoogle({ apiKey: process.env.GOOGLE_API_KEY! });

API Reference

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

publishers

POST https://aiplatform.googleapis.com/v1/publishers/google/models/{model}:countTokens

Cost tier: expensive

Upstream docs ↗

const res = await google.v1.publishers.google.models.countTokens(
  "gemini-2.5-flash",
  {
    contents: [{ role: "user", parts: [{ text: "How does AI work?" }] }],
  }
);

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

POST https://aiplatform.googleapis.com/v1/publishers/google/models/{model}:generateContent

Cost tier: expensive

Upstream docs ↗

const res = await google.v1.publishers.google.models.generateContent(
  "gemini-2.5-flash",
  {
    contents: [{ role: "user", parts: [{ text: "How does AI work?" }] }],
  }
);

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

v1internal

POST https://cloudcode-pa.googleapis.com/v1internal:retrieveUserQuota

Cost tier: expensive

Upstream docs ↗

const res = await google.v1internal.retrieveUserQuota({ /* ... */ });

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

POST https://cloudcode-pa.googleapis.com/v1internal:retrieveUserQuotaSummary

Cost tier: expensive

Upstream docs ↗

const res = await google.v1internal.retrieveUserQuotaSummary({ /* ... */ });

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

Part of the apicity monorepo.

License

MIT — see LICENSE.