Kilo Code

A Cline fork that ships with free models included.

Kilo Code is a Cline fork, but the thing on this page is the gateway behind it: api.kilo.ai/api/gateway, OpenAI-compatible, one key, hundreds of models, 19 of them tagged :free right now — Nemotron, Laguna, MiniMax, Ling.

Free :free models answer without a key — no email, no account. Anonymous traffic is 200 requests an hour per IP. NVIDIA’s free endpoints on the gateway are trial-use only — no personal data. A Kilo account is only needed for paid models or to bring your own upstream key.

Free models: 19
Max context: 1M
Free tier: 200 requests per hour
Requirement: Nothing — no account

Endpoint

Base URLhttps://api.kilo.ai/api/gateway

Env varKILO_API_KEY

Rate limit200 requests per hour per IP

OpenAI-compatible
text
image
audio
video
code
reasoning

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.kilo.ai/api/gateway',
  apiKey: process.env.KILO_API_KEY
})

const response = await client.chat.completions.create({
  model: 'nvidia/nemotron-3-ultra-550b-a55b:free',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

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

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.kilo.ai/api/gateway",
    api_key=os.environ["KILO_API_KEY"],
)

response = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b:free",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl https://api.kilo.ai/api/gateway/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $KILO_API_KEY" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b:free",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

Worth knowing

Free :free models answer without a key. Anonymous traffic is 200 requests an hour per IP.
A Kilo account is only needed for paid models or to bring your own upstream key.

Models you get for free20

Auto Freekilo-auto/free
StepFun Step 3.7 Flashstepfun/step-3.7-flash:free
Laguna S 2.1poolside/laguna-s-2.1:free
MiniMax M3minimax/minimax-m3:free
Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin:free
Dots 3 Note Previewdots-studio/dots-3-note-preview:free
LFM 2.5 2.6Bliquid/lfm-2.5-2.6b:free
Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning:free
Inkling Smallthinkingmachines/inkling-small:free
Inklingthinkingmachines/inkling:free
Laguna XS 2.1poolside/laguna-xs-2.1:free
North Mini Codecohere/north-mini-code:free
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety:free
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b:free
Nemotron 3 Nano Omninvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Lyria 3 Pro Previewgoogle/lyria-3-pro-preview
Lyria 3 Clip Previewgoogle/lyria-3-clip-preview
MiniMax M2.7minimax/minimax-m2.7:free
Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b:free
OpenRouter Free Models Routeropenrouter/free