OpenRouter

Inference14 modelcontext maks 1MGratis: ~22 model free

Catatan dari sumber

~22 free models (marked with :free suffix). OpenAI SDK-compatible.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "nvidia/nemotron-3-ultra-550b-a55b:free",
  messages: [{ role: "user", content: "Halo!" }],
});

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

.env

OPENROUTER_API_KEY=your-api-key-here

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

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi OpenRouter.

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

Model tersedia (14)

NVIDIA: Nemotron 3 Ultra (free)

nvidia/nemotron-3-ultra-550b-a55b:free

Modality: Text
Context: 1M
Output: 66K
Rate limit: 20 RPM, 200 RPD

Google: Gemma 4 26B A4B (free)

google/gemma-4-26b-a4b-it:free

Modality: Text + Vision + Video
Context: 262K
Output: 33K
Rate limit: 200 req/day (free tier)

Google: Gemma 4 31B (free)

google/gemma-4-31b-it:free

Modality: Text + Vision + Video
Context: 262K
Output: 33K
Rate limit: 20 RPM, 200 RPD

Ling-3.0-flash (free)

inclusionai/ling-3.0-flash:free

Modality: Text
Context: 262K
Output: 33K
Rate limit: 200 req/day (free tier)

NVIDIA: Nemotron 3 Super (free)

nvidia/nemotron-3-super-120b-a12b:free

Modality: Text
Context: 262K
Output: 262K
Rate limit: 20 RPM, 200 RPD

Poolside: Laguna S 2.1 (free)

poolside/laguna-s-2.1:free

Modality: Text
Context: 262K
Output: 33K
Rate limit: 200 req/day (free tier)

Poolside: Laguna XS 2.1 (free)

poolside/laguna-xs-2.1:free

Modality: Text
Context: 262K
Output: 33K
Rate limit: 200 req/day (free tier)

Cohere: North Mini Code (free)

cohere/north-mini-code:free

Modality: Text
Context: 256K
Output: 64K
Rate limit: 200 req/day (free tier)

Model	Modality	Context	Output	Rate limit
NVIDIA: Nemotron 3 Ultra (free) nvidia/nemotron-3-ultra-550b-a55b:free	Text	1M	66K	20 RPM, 200 RPD
Google: Gemma 4 26B A4B (free) google/gemma-4-26b-a4b-it:free	Text + Vision + Video	262K	33K	200 req/day (free tier)
Google: Gemma 4 31B (free) google/gemma-4-31b-it:free	Text + Vision + Video	262K	33K	20 RPM, 200 RPD
Ling-3.0-flash (free) inclusionai/ling-3.0-flash:free	Text	262K	33K	200 req/day (free tier)
NVIDIA: Nemotron 3 Super (free) nvidia/nemotron-3-super-120b-a12b:free	Text	262K	262K	20 RPM, 200 RPD
Poolside: Laguna S 2.1 (free) poolside/laguna-s-2.1:free	Text	262K	33K	200 req/day (free tier)
Poolside: Laguna XS 2.1 (free) poolside/laguna-xs-2.1:free	Text	262K	33K	200 req/day (free tier)
Cohere: North Mini Code (free) cohere/north-mini-code:free	Text	256K	64K	200 req/day (free tier)

Model ini di provider lain (10)

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

FAQ

Apakah API OpenRouter gratis?

Ya — ~22 model free. Data dari openrouter.ai/api/v1/models, mnfst/awesome-free-llm-apis, freellm.net, cheahjs/free-llm-api-resources, terakhir di-sync 28 Jul 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di OpenRouter?

14 model tercantum per 28 Jul 2026, termasuk NVIDIA: Nemotron 3 Ultra (free), Google: Gemma 4 26B A4B (free), Google: Gemma 4 31B (free).

Berapa rate limit OpenRouter?

Beda-beda per model, contoh: NVIDIA: Nemotron 3 Ultra (free): 20 RPM, 200 RPD; Google: Gemma 4 26B A4B (free): 200 req/day (free tier); Google: Gemma 4 31B (free): 20 RPM, 200 RPD. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di OpenRouter?

1M (NVIDIA: Nemotron 3 Ultra (free)).