💡 Quick Summary:
- API Endpoint:https://free.empero.org/v1(Standard OpenAI-compatible format, completions athttps://free.empero.org/v1/chat/completions)
- Available Model:glm-5.3-flash(Zhipu AI 320B-A18B MoE flagship coding & agentic model with 1M token native context)
- Authentication: No sign-up required! Any API key is accepted (e.g., usefreeorsk-freeif required by your client)
- ⚠️ Privacy Notice: This is a public research endpoint funded by Empero Lab. All prompts and completions are logged (with hashed IPs) to train future open-source AI models. Do not send sensitive or proprietary data!
🔬 What is Empero?
Empero (empero.org) is an independent AI research lab based in Germany, built on open-by-default principles.
To accelerate research into open models, Empero hosts community endpoints that allow developers worldwide to test frontier models without credit cards or account registrations. In exchange, anonymized interaction traces help train better open-weights models.
🚀 Quick Start Examples
1. cURL
bash
curl https://free.empero.org/v1/chat/completions \
-H "Authorization: Bearer free" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3-flash",
"messages": [
{"role": "user", "content": "Write a quicksort implementation in TypeScript with generics"}
]
}'2. Python (OpenAI SDK)
python
from openai import OpenAI
client = OpenAI(
base_url="https://free.empero.org/v1",
api_key="free" # Any non-empty string works
)
response = client.chat.completions.create(
model="glm-5.3-flash",
messages=[{"role": "user", "content": "Explain hybrid attention in GLM-5.3-Flash."}]
)
print(response.choices[0].message.content)3. Node.js / TypeScript
typescript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://free.empero.org/v1",
apiKey: "free",
});
const response = await client.chat.completions.create({
model: "glm-5.3-flash",
messages: [{ role: "user", content: "Hello GLM-5.3-Flash!" }],
});
console.log(response.choices[0].message.content);⚠️ Data Privacy & Boundaries
- Best for: Open-source coding, benchmarking, prototyping, and study.
- Do NOT use for: Proprietary commercial code, confidential enterprise tokens, personal identifiable information (PII).
Community Feedback
Comments are tied to your GitHub account — sign in to join the discussion.