Kilo Code

Inference12 modelcontext maks 1M

Catatan dari sumber

Free models with no credit card and no API key required. kilo-auto/free auto-router dynamically routes to models in the free pool.

Setup dalam 5 menit

Model

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.kilo.ai/api/gateway",
  apiKey: process.env.KILO_CODE_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

KILO_CODE_API_KEY=your-api-key-here

Belum punya API key? Ambil di halaman resmi Kilo Code ↗.

Cara claim API key gratis

Langkah umum — detail pastinya ikutin halaman resmi Kilo Code.

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

Model tersedia (12)

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

Modality: Text
Context: 1M
Output: 65K
Rate limit: 200 req/hr

nvidia/nemotron-3.5-lightning:free

Modality: Text
Context: 1M
Output: 65K
Rate limit: 200 req/hr

inclusionai/ling-3.0-flash:free

inclusionai-ling-3-0-flash-free

Modality: text + reasoning
Context: 262K
Rate limit: ~200 req/hr

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

Modality: Text
Context: 262K
Output: 262K
Rate limit: 200 req/hr

poolside/laguna-s-2.1:free

Modality: Text (code)
Context: 262K
Output: 32K
Rate limit: 200 req/hr

poolside/laguna-xs-2.1:free

Modality: Text (code)
Context: 262K
Output: 32K
Rate limit: 200 req/hr

stepfun/step-3.7-flash:free

Modality: Text + Vision
Context: 262K
Output: 262K
Rate limit: 200 req/hr

tencent/hy3:free

Modality: Text
Context: 262K
Output: 128K
Rate limit: 200 req/hr

Model	Modality	Context	Output	Rate limit
nvidia/nemotron-3-ultra-550b-a55b:free nvidia/nemotron-3-ultra-550b-a55b:free	Text	1M	65K	200 req/hr
nvidia/nemotron-3.5-lightning:free nvidia/nemotron-3.5-lightning:free	Text	1M	65K	200 req/hr
inclusionai/ling-3.0-flash:free inclusionai-ling-3-0-flash-free	text + reasoning	262K		~200 req/hr
nvidia/nemotron-3-super-120b-a12b:free nvidia/nemotron-3-super-120b-a12b:free	Text	262K	262K	200 req/hr
poolside/laguna-s-2.1:free poolside/laguna-s-2.1:free	Text (code)	262K	32K	200 req/hr
poolside/laguna-xs-2.1:free poolside/laguna-xs-2.1:free	Text (code)	262K	32K	200 req/hr
stepfun/step-3.7-flash:free stepfun/step-3.7-flash:free	Text + Vision	262K	262K	200 req/hr
tencent/hy3:free tencent/hy3:free	Text	262K	128K	200 req/hr

Model ini di provider lain (8)

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

FAQ

Apakah API Kilo Code gratis?

Ya — menurut sumber: "Free models with no credit card and no API key required. kilo-auto/free auto-router dynamically routes to models in the free pool." Data dari mnfst/awesome-free-llm-apis, freellm.net, terakhir di-sync 2 Sep 2026 — cek sumber untuk kondisi terbaru.

Ada berapa model gratis di Kilo Code?

12 model tercantum per 2 Sep 2026, termasuk nvidia/nemotron-3-ultra-550b-a55b:free, nvidia/nemotron-3.5-lightning:free, inclusionai/ling-3.0-flash:free.

Berapa rate limit Kilo Code?

Beda-beda per model, contoh: nvidia/nemotron-3-ultra-550b-a55b:free: 200 req/hr; nvidia/nemotron-3.5-lightning:free: 200 req/hr; inclusionai/ling-3.0-flash:free: ~200 req/hr. Limit lengkap per model, lihat tabel di atas.

Berapa context window maksimal di Kilo Code?

1M (nvidia/nemotron-3-ultra-550b-a55b:free).