Bithumb Trading Bot in Python

This guide shows how to build a Bithumb trading bot in Python with LumiBot, for both AI agent trading and algorithmic trading. LumiBot connects to Bithumb through CCXT, the open source library that talks to more than 100 crypto exchanges. You will create a Bithumb account and API key, connect it, and run two examples: a simple algorithmic trading bot and an agentic trading bot where an AI agent makes the calls.

Bithumb at a glance

CCXT exchange id

bithumb

Markets

Spot

Testnet (sandbox)

No

Credentials

API key, API secret

Live data streams

prices, order book, trades, your orders, your balance

CCXT request spacing

about 500 ms between requests

Official site

https://www.bithumb.com

API docs

https://apidocs.bithumb.com

Fees

https://en.bithumb.com/customer_support/info_fee

What is Bithumb?

Bithumb is a crypto exchange where you buy and sell coins against the Korean won (KRW), for example the KRW-BTC market. Its API lets you check prices and balances and place buy and sell orders automatically.

Sign up for Bithumb

  1. Create a Bithumb account on the website or app.

  2. Finish identity verification (customer verification). Bithumb says trading, including API trading, can be blocked until you do.

  3. Bithumb has no testnet, so plan to start with a very small trade.

Open a Bithumb account

Create a Bithumb API key

  1. Log in on a computer, click your name at the top, then Account Management (계정관리), then API Management (API 관리).

  2. Choose the API functions the key may use (API 활성 항목). See the permissions below.

  3. Enter the IP address of the machine that runs your bot. You can enter up to 5 addresses, and the key is limited if you leave this empty.

  4. Agree to the terms and click Create API Key (API Key 생성), then finish the ownership check.

  5. Copy the Secret Key right away. Bithumb shows it only once.

Which permissions to turn on: Turn on asset lookup (자산조회), order lookup (주문조회) and placing orders (주문하기). Leave withdrawals (출금하기) off. Bithumb warns that an API key can withdraw without any extra check, so never give a bot that function. To change functions later you must delete the key and make a new one.

Warning

Never turn on withdrawals for a Bithumb trading bot key. Bind the key to your server’s IP address when Bithumb lets you, keep the secret out of your code and out of Git, and delete the key if it ever leaks.

Connect Bithumb to LumiBot

The simplest way: put these lines in a .env file next to your strategy. LumiBot loads the file, sees TRADING_BROKER=bithumb and connects to Bithumb for you, so your strategy needs no broker code.

TRADING_BROKER=bithumb
BITHUMB_API_KEY=your_apiKey
BITHUMB_API_SECRET=your_secret

LumiBot reads exactly the fields CCXT needs for Bithumb (apiKey, secret). If one is missing, LumiBot stops at start-up and names the variable you still need.

You can also build the broker in code. This is handy when one script talks to more than one exchange, or when you need extra CCXT options. The keys in the config are CCXT’s own credential names for Bithumb:

import os

BITHUMB_CONFIG = {
    "exchange_id": "bithumb",
    "apiKey": os.environ.get("BITHUMB_API_KEY"),
    "secret": os.environ.get("BITHUMB_API_SECRET"),
    "sandbox": False,  # no sandbox for this exchange
}

from lumibot.brokers import Ccxt

broker = Ccxt(BITHUMB_CONFIG)
# then: MyStrategy(broker=broker, ...)

Either way, LumiBot turns on CCXT’s built-in rate limiting for you.

Testing on Bithumb

Bithumb has no sandbox. Test with a very small amount, leave BITHUMB_SANDBOX unset, and in a code config set "sandbox": False.

Algorithmic trading example: a simple Bithumb bot

This bot buys about 70000 KRW of BTC on Bithumb once and then holds it. It is a starting point to check that your keys, balances and orders work. If the exchange’s minimum order is larger, raise the amount.

from lumibot.entities import Asset
from lumibot.strategies import Strategy


class BithumbBuyOnce(Strategy):
    """Buy a small amount of BTC once, then hold it."""

    def initialize(self):
        self.sleeptime = "1H"
        self.set_market("24/7")  # crypto trades all day, every day

    def on_trading_iteration(self):
        coin = Asset("BTC", asset_type=Asset.AssetType.CRYPTO)
        if self.get_position(coin) is not None:
            return  # already holding BTC
        price = self.get_last_price(coin, quote=self.quote_asset)
        if price:
            quantity = round(70000 / price, 6)  # about 70000 KRW worth
            order = self.create_order(coin, quantity, "buy", quote=self.quote_asset)
            self.submit_order(order)


if __name__ == "__main__":
    # LumiBot reads TRADING_BROKER and the keys from your .env file.
    strategy = BithumbBuyOnce(quote_asset=Asset("KRW", asset_type=Asset.AssetType.CRYPTO))
    strategy.run_live()

Agentic trading example: an AI agent that trades on Bithumb

Agentic trading means an AI agent reads the market and decides what to do. In this example one LumiBot agent looks at prices and your Bithumb account, then places the orders itself. There is no Python logic in between: you set the rules in plain English in the prompt, such as what it may trade and how big each order can be. This follows the same pattern as LumiBot’s AI trading team examples.

from lumibot.entities import Asset
from lumibot.strategies import Strategy


class BithumbAITrader(Strategy):
    """One AI agent researches the market and places the trades itself."""

    def initialize(self):
        self.sleeptime = "4H"
        self.set_market("24/7")
        self.agents.create(
            name="trader",
            model="openai/gpt-6-luna",
            reasoning_effort="high",
            allow_trading=True,
            system_prompt=(
                "You manage a small crypto account on Bithumb. "
                "You may trade BTC and ETH against KRW (asset_type 'crypto', quote_symbol 'KRW'), or hold cash. "
                "Before every order, call account_portfolio, account_positions and "
                "market_last_price for that exact symbol in the same run. "
                "Keep each order under 10% of the account value. "
                "Explain each decision in one short paragraph."
            ),
        )

    def on_trading_iteration(self):
        self.agents["trader"].run(
            task_prompt="Review recent BTC/KRW and ETH/KRW prices and your current holdings, then decide whether to buy, sell or hold.",
            context={"exchange": "Bithumb", "quote": "KRW", "date": self.get_datetime().isoformat()},
        )


if __name__ == "__main__":
    # LumiBot reads TRADING_BROKER and the keys from your .env file.
    strategy = BithumbAITrader(quote_asset=Asset("KRW", asset_type=Asset.AssetType.CRYPTO))
    strategy.run_live()

The agent needs a model key such as OPENAI_API_KEY in your environment. See the AI agents quickstart for models, tools and memory.

What you can trade on Bithumb through CCXT

Market

Listed by CCXT

Spot

Yes

Margin

No

Perpetual swaps

No

Dated futures

No

Options

No

CCXT lists these order features for Bithumb: market orders, limit orders, editing open orders, canceling orders.

Bithumb tips

  • Bithumb keys last one year and cannot be extended. When a key expires, delete it and create a new one. Each account can hold up to 10 keys, counting expired ones.

  • Bithumb now issues both API 1.0 and API 2.0 keys. CCXT’s bithumb exchange calls the older API 1.0 endpoints (such as info/balance), so make an API 1.0 key if Bithumb asks you to choose.

  • Bithumb writes markets as KRW-BTC (quote first). In LumiBot and CCXT the same market is BTC/KRW.

  • Bithumb’s help center and API docs are in Korean. The menu names above are given in Korean so you can find them.

Frequently asked questions

Can I build a Bithumb trading bot in Python?

Yes. Install LumiBot (pip install lumibot), set your Bithumb keys and use the bithumb CCXT exchange id as shown above.

Does Bithumb have a testnet?

No testnet is set up for Bithumb in LumiBot. Start with a small amount, and in a code config set "sandbox": False.

Which API permissions does a Bithumb bot need?

Turn on asset lookup (자산조회), order lookup (주문조회) and placing orders (주문하기). Leave withdrawals (출금하기) off. Bithumb warns that an API key can withdraw without any extra check, so never give a bot that function. To change functions later you must delete the key and make a new one.

Can an AI agent trade on Bithumb by itself?

Yes. The agentic example above gives one agent permission to trade. You control what it may trade and how much through its prompt.

Can I trade Bithumb perpetual futures with LumiBot?

CCXT does not list perpetual swaps for Bithumb, so use spot markets.

Is LumiBot free?

Yes. LumiBot is open source on GitHub at https://github.com/Lumiwealth/lumibot. You pay only your exchange’s trading fees and, for AI agents, your model provider.

Run it in the cloud with BotSpot

Do not want to keep a computer running for your Bithumb bot? BotSpot is the hosted home for LumiBot strategies and AI trading agents: build with AI, backtest, connect a broker, and watch every trade with logs and alerts.

Try BotSpot

Sources