Google Gemini

Provider API22 modelcontext maks 2M

Catatan dari sumber

Free tier unavailable in EU/UK/Switzerland. Free-tier prompts may be used by Google to improve products.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://generativelanguage.googleapis.com/v1beta",
  apiKey: process.env.GOOGLE_GEMINI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gemini-2.5-pro",
  messages: [{ role: "user", content: "Halo!" }],
});

console.log(response.choices[0].message.content);

.env

GOOGLE_GEMINI_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi Google Gemini ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi Google Gemini.

1.Buka halaman API key Google Gemini ↗
2.Daftar akun baru, atau login kalau udah punya.
3.Generate API key di dashboard / settings.
4.Pakai API key + Base URL https://generativelanguage.googleapis.com/v1beta di SDK atau HTTP client.

Model tersedia (22)

Gemini 2.5 Pro

gemini-2.5-pro

Modality: Text + Image + Audio + Video
Context: 2M
Output: 65K
Rate limit: 5 RPM, 50 RPD

Gemini 2.5 Flash

gemini-2.5-flash

Modality: Text + Image + Audio + Video
Context: 1M
Output: 65K
Rate limit: 15 RPM, 1,500 RPD

Gemini 2.5 Flash-Lite

gemini-2-5-flash-lite

Modality: vision + audio + reasoning
Context: 1.0M
Output: 64K
Rate limit: 250,000 tokens/minute, 20 requests/day, 10 requests/minute

Gemini 3 Flash (Preview)

gemini-3-flash-preview

Modality: text
Context: 1.0M
Rate limit: Preview limits

Gemini 3.1 Flash-Lite

gemini-3.1-flash-lite

Modality: Text + Image + Audio + Video
Context: 1M
Output: 65K
Rate limit: 30 RPM, 1,500 RPD

Gemini 3.5 Flash

gemini-3.5-flash

Modality: Text + Image + Audio + Video
Context: 1M
Output: 64K
Rate limit: 15 RPM, 1,500 RPD

Gemini 3.5 Flash Lite

gemini-3-5-flash-lite

Modality: vision + audio + reasoning
Context: 1.0M
Output: 64K
Rate limit: 250,000 tokens/minute, 500 requests/day, 15 requests/minute

Gemini 3.6 Flash

gemini-3-6-flash

Modality: vision + audio + reasoning
Context: 1.0M
Output: 64K
Rate limit: 250,000 tokens/minute, 20 requests/day, 5 requests/minute

Model	Modality	Context	Output	Rate limit
Gemini 2.5 Pro gemini-2.5-pro	Text + Image + Audio + Video	2M	65K	5 RPM, 50 RPD
Gemini 2.5 Flash gemini-2.5-flash	Text + Image + Audio + Video	1M	65K	15 RPM, 1,500 RPD
Gemini 2.5 Flash-Lite gemini-2-5-flash-lite	vision + audio + reasoning	1.0M	64K	250,000 tokens/minute, 20 requests/day, 10 requests/minute
Gemini 3 Flash (Preview) gemini-3-flash-preview	text	1.0M		Preview limits
Gemini 3.1 Flash-Lite gemini-3.1-flash-lite	Text + Image + Audio + Video	1M	65K	30 RPM, 1,500 RPD
Gemini 3.5 Flash gemini-3.5-flash	Text + Image + Audio + Video	1M	64K	15 RPM, 1,500 RPD
Gemini 3.5 Flash Lite gemini-3-5-flash-lite	vision + audio + reasoning	1.0M	64K	250,000 tokens/minute, 500 requests/day, 15 requests/minute
Gemini 3.6 Flash gemini-3-6-flash	vision + audio + reasoning	1.0M	64K	250,000 tokens/minute, 20 requests/day, 5 requests/minute

Model ini di provider lain (6)

Nama model yang sama juga muncul di provider lain menurut sumber masing-masing — versi/kuantisasi bisa beda.

FAQ

Apakah API Google Gemini gratis?

Ya — menurut sumber: "Free tier unavailable in EU/UK/Switzerland. Free-tier prompts may be used by Google to improve products." Data dari mnfst/awesome-free-llm-apis, freellm.net, cheahjs/free-llm-api-resources, models.dev, terakhir di-sync 28 Jul 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di Google Gemini?

22 model tercantum per 28 Jul 2026, termasuk Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash-Lite.

Berapa rate limit Google Gemini?

Beda-beda per model, contoh: Gemini 2.5 Pro: 5 RPM, 50 RPD; Gemini 2.5 Flash: 15 RPM, 1,500 RPD; Gemini 2.5 Flash-Lite: 250,000 tokens/minute, 20 requests/day, 10 requests/minute. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di Google Gemini?

2M (Gemini 2.5 Pro).