Access 40+ state-of-the-art models through a single OpenAI-compatible API. Fast, reliable, and cost-optimized.
# OpenAI-compatible — just change the base URL
from openai import OpenAI
client = OpenAI(
api_key="sk-your-key",
base_url="https://llm.harmonyrise.id/v1"
)
response = client.chat.completions.create(
model="glm-4.7:cloud",
messages=[{"role": "user",
"content": "Hello!"}]
)
# Response
"Hi! I'm GLM-4.7, ready to help 🚀"Everything you need to build AI-powered applications, in one gateway.
Drop-in replacement for OpenAI API. Just change the base URL — your existing code works as-is.
GLM, DeepSeek, Qwen, Kimi, Gemini, MiniMax, and more. Switch models with one parameter change.
Transparent per-token pricing in Rupiah. No hidden fees, no currency conversion. Pay only for what you use.
Hosted in Indonesia with optimized routing. Fast response times for production workloads.
Curated collection of the best AI models, ready to use.
Simple, per-token pricing in IDR. No hidden fees. Pay only for what you use.
| Model | Category | Input / 1M | Output / 1M |
|---|
Connect your applications in seconds using our OpenAI-compatible endpoint.
Get your secure API key from the HarmonyLLM Dashboard.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.harmonyrise.id/v1"
)
response = client.chat.completions.create(
model="glm-4.7:cloud",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)curl https://llm.harmonyrise.id/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "glm-4.7:cloud",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_API_KEY",
baseURL: "https://llm.harmonyrise.id/v1"
});
const response = await client.chat.completions.create({
model: "glm-4.7:cloud",
messages: [{ role: "user", content: "Hello!" }]
});
console.log(response.choices[0].message.content);