connecting...
One API key.
Every free model.
OpenAI-compatible gateway. Streaming, tool-calling, vision — ... models live, token usage updating every minute.
https://apikeyopen.biz.id/v1
—
requests served
last hours, from gateway log
—
avg latency
last 50 requests
Live model traffic
hits per model, updating every 60s · —
Live token usage
cumulative from gateway log
Models
Click any model to copy its id. Pass it exactly as model in your request.
Quick start
Drop-in OpenAI replacement — change the base URL, keep everything else.
# pip install openai
from openai import OpenAI
client = OpenAI(base_url="https://apikeyopen.biz.id/v1", api_key="sk-...")
r = client.chat.completions.create(model="cbai/deepseek-v4.1-flash",
messages=[{"role": "user", "content": "hello"}], stream=True)
for c in r: print(c.choices[0].delta.content or "", end="")
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://apikeyopen.biz.id/v1", apiKey: "sk-..." });
const s = await client.chat.completions.create({ model: "cbai/deepseek-v4.1-flash",
messages: [{ role: "user", content: "hello" }], stream: true });
for await (const c of s) process.stdout.write(c.choices[0]?.delta?.content || "");
curl https://apikeyopen.biz.id/v1/chat/completions \
-H "Authorization: Bearer $KEY" \
-H "Content-Type: application/json" \
-d '{"model":"cbai/deepseek-v4.1-flash","stream":true,
"messages":[{"role":"user","content":"hello"}]}'