CHAOTOKEN API — Unified AI Model Gateway

chaotoken.xyz / v1

● Live

Python

Node.js

cURL

Anthropic SDK

# pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://chaotoken.xyz/v1",
    api_key="sk-your-chaotoken-key",
)

response = client.chat.completions.create(
    model="claude-sonnet-4",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://chaotoken.xyz/v1',
  apiKey: 'sk-your-chaotoken-key',
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(response.choices[0].message.content);
curl https://chaotoken.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-chaotoken-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
  }'
import anthropic

client = anthropic.Anthropic(
    api_key="sk-your-chaotoken-key",
    base_url="https://chaotoken.xyz",
)

message = client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)
print(message.content[0].text)

Features

Why CHAOTOKEN

⇄

Unified Interface

Fully compatible with the OpenAI SDK. Just swap the base_url — no other code changes needed.

◎

Load Balancing

Weighted multi-account scheduling with automatic failover. Service stays available even when one account goes down.

◈

Precise Metering

Token-level usage tracking. Every call is logged with cost, model, and latency. Real-time balance deduction.

≋

Streaming Output

Full SSE streaming support. The experience is identical to calling the provider's API directly.

⊘

Balance Control

Pre-paid model with automatic request rejection when balance runs out. No surprise overage charges.

⊞

Admin Console

Web dashboard to manage API keys, view usage and billing history, and configure upstream providers.

Documentation

Quick Start

Replace base_url and you're done. Migration takes under 3 minutes.

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-key",
    base_url="https://chaotoken.xyz/v1"
)
resp = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)

Node.js · OpenAI SDK

import OpenAI from 'openai';
const client = new OpenAI({
  apiKey: 'sk-your-key',
  baseURL: 'https://chaotoken.xyz/v1',
});

cURL

curl https://chaotoken.xyz/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-4","messages":[{"role":"user","content":"Hello"}]}'

Plans

Choose Your Plan

Pre-paid credits that never expire. Pick the plan that fits your usage.

Free

Try before you buy

Limited free models

RPM 5

No login required

Try Free →

Starter

$9.9

≈ 7M tokens

based on average model pricing

Get $14.9 credits · +50% bonus

All models

RPM 60

Priority support

Buy Now →

One-Stop AI Token
Management Platform

Choose Your Plan

Start Using CHAOTOKEN

One-Stop AI TokenManagement Platform

Choose Your Plan

Start Using CHAOTOKEN

One-Stop AI Token
Management Platform