Groq

Inference8 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: "openai/gpt-oss-120b",
  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 (8)

openai/gpt-oss-120b

Modality: Text
Context: 131K
Output: 65K
Rate limit: 30 RPM, 1,000 RPD

openai/gpt-oss-20b

Modality: Text
Context: 131K
Output: 65K
Rate limit: 30 RPM, 1,000 RPD

qwen/qwen3.8-27b

Modality: Text + Image
Context: 131K
Output: 16K
Rate limit: 30 RPM, 1,000 RPD

allam-2-7b

Modality: text
Context: 8K
Output: 4K

meta-llama/llama-prompt-guard-2-22m

meta-llama-llama-prompt-guard-2-22m

Context: 8K

meta-llama/llama-prompt-guard-2-86m

meta-llama-llama-prompt-guard-2-86m

Context: 8K

whisper-large-v3

Modality: text
Rate limit: 20 RPM, 2,000 RPD

whisper-large-v3-turbo

Modality: text
Context: 448
Output: 448
Rate limit: 20 RPM, 2,000 RPD

Model	Modality	Context	Output	Rate limit
openai/gpt-oss-120b openai/gpt-oss-120b	Text	131K	65K	30 RPM, 1,000 RPD
openai/gpt-oss-20b openai/gpt-oss-20b	Text	131K	65K	30 RPM, 1,000 RPD
qwen/qwen3.8-27b qwen/qwen3.8-27b	Text + Image	131K	16K	30 RPM, 1,000 RPD
allam-2-7b allam-2-7b	text	8K	4K
meta-llama/llama-prompt-guard-2-22m meta-llama-llama-prompt-guard-2-22m		8K
meta-llama/llama-prompt-guard-2-86m meta-llama-llama-prompt-guard-2-86m		8K
whisper-large-v3 whisper-large-v3	text			20 RPM, 2,000 RPD
whisper-large-v3-turbo whisper-large-v3-turbo	text	448	448	20 RPM, 2,000 RPD

Model ini di provider lain (3)

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, models.dev, terakhir di-sync 28 Okt 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di Groq?

8 model tercantum per 28 Okt 2026, termasuk openai/gpt-oss-120b, openai/gpt-oss-20b, qwen/qwen3.8-27b.

Berapa rate limit Groq?

Beda-beda per model, contoh: openai/gpt-oss-120b: 30 RPM, 1,000 RPD; openai/gpt-oss-20b: 30 RPM, 1,000 RPD; qwen/qwen3.8-27b: 30 RPM, 1,000 RPD. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di Groq?

131K (openai/gpt-oss-120b).