Chabokan AI Gateway

One endpoint, hundreds of AI models

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.

412models available
99.9%uptime
< 15msgateway overhead
Per tokenusage metering

Quick start

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)

Why this gateway

OpenAI compatible

Any SDK or tool that speaks to OpenAI works here unchanged — only the base URL differs.

Real streaming

Responses arrive token by token, unbuffered from the model all the way to your client.

Transparent usage

Tokens, cost and latency are recorded for every single request and visible in your panel.

Unlimited keys

Issue a separate key per project, cap its monthly spend, and revoke it the moment you need to.

Supported models

All prices are in USD per 1 million tokens. Models on promotion show the discount and their previous price.

Plan level
Model Modalities Input / 1M Output / 1M Context Released