Groq

Inference21 modelcontext maks 131K

Catatan dari sumber

Free tier, no credit card. Ultra-fast LPU inference.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.groq.com/openai/v1",
  apiKey: process.env.GROQ_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-oss-20b",
  messages: [{ role: "user", content: "Halo!" }],
});

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

.env

GROQ_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi Groq ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi Groq.

1.Buka halaman API key Groq ↗
2.Daftar akun baru, atau login kalau udah punya.
3.Generate API key di dashboard / settings.
4.Pakai API key + Base URL https://api.groq.com/openai/v1 di SDK atau HTTP client.

Model tersedia (21)

GPT OSS 20B

gpt-oss-20b

Modality: reasoning + text
Context: 131K
Rate limit: 1,000 requests/day, 8,000 tokens/minute

GPT-OSS Safeguard 20B

gpt-oss-safeguard-20b

Modality: text + reasoning
Context: 131K
Rate limit: 1,000 requests/day, 8,000 tokens/minute

gpt-oss-120b

Modality: Text
Context: 131K
Output: 32K
Rate limit: 30 RPM, 1,000 RPD

llama-3.1-8b-instant

Modality: Text
Context: 131K
Output: 131K
Rate limit: 30 RPM, 1,000 RPD

llama-3.3-70b-versatile

Modality: Text
Context: 131K
Output: 32K
Rate limit: 30 RPM, 1,000 RPD

llama-4-scout-17b-16e-instruct

Modality: Text + Vision
Context: 131K
Output: 8K
Rate limit: 30 RPM, 1,000 RPD

Moonshot Kimi K2

moonshot-kimi-k2

Modality: text
Context: 131K

Moonshot Kimi K2 0905

moonshot-kimi-k2-0905

Modality: text
Context: 131K

Model	Modality	Context	Output	Rate limit
GPT OSS 20B gpt-oss-20b	reasoning + text	131K		1,000 requests/day, 8,000 tokens/minute
GPT-OSS Safeguard 20B gpt-oss-safeguard-20b	text + reasoning	131K		1,000 requests/day, 8,000 tokens/minute
gpt-oss-120b gpt-oss-120b	Text	131K	32K	30 RPM, 1,000 RPD
llama-3.1-8b-instant llama-3.1-8b-instant	Text	131K	131K	30 RPM, 1,000 RPD
llama-3.3-70b-versatile llama-3.3-70b-versatile	Text	131K	32K	30 RPM, 1,000 RPD
llama-4-scout-17b-16e-instruct llama-4-scout-17b-16e-instruct	Text + Vision	131K	8K	30 RPM, 1,000 RPD
Moonshot Kimi K2 moonshot-kimi-k2	text	131K
Moonshot Kimi K2 0905 moonshot-kimi-k2-0905	text	131K

Model ini di provider lain (7)

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

FAQ

Apakah API Groq gratis?

Ya — menurut sumber: "Free tier, no credit card. Ultra-fast LPU inference." 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 Groq?

21 model tercantum per 28 Jul 2026, termasuk GPT OSS 20B, GPT-OSS Safeguard 20B, gpt-oss-120b.

Berapa rate limit Groq?

Beda-beda per model, contoh: GPT OSS 20B: 1,000 requests/day, 8,000 tokens/minute; GPT-OSS Safeguard 20B: 1,000 requests/day, 8,000 tokens/minute; gpt-oss-120b: 30 RPM, 1,000 RPD. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di Groq?

131K (GPT OSS 20B).