Fully compatible with the OpenAI API — point base_url at us and every
SDK you already use keeps working. No foreign card, no sanctions to work around,
and you pay only for the tokens you actually spend.
Take your key from the Chabokan panel and change one line of code.
from openai import OpenAI client = OpenAI( api_key="sk-chbk-...", base_url="https://ai.chabokan.net/v1", ) response = client.chat.completions.create( model="openai/gpt-4o-mini", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)
curl https://ai.chabokan.net/v1/chat/completions \ -H "Authorization: Bearer sk-chbk-..." \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-4o-mini", "messages": [{"role": "user", "content": "Hello!"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: "sk-chbk-...", baseURL: "https://ai.chabokan.net/v1", }); const response = await client.chat.completions.create({ model: "openai/gpt-4o-mini", messages: [{ role: "user", content: "Hello!" }], });
Any SDK or tool that speaks to OpenAI works here unchanged — only the base URL differs.
Responses arrive token by token, unbuffered from the model all the way to your client.
Tokens, cost and latency are recorded for every single request and visible in your panel.
Issue a separate key per project, cap its monthly spend, and revoke it the moment you need to.
All prices are in USD per 1 million tokens. Models on promotion show the discount and their previous price.
| Model | Modalities | Input / 1M | Output / 1M | Context | Released |
|---|