Web3 AI Chatbot & LLM

Web3 AI Chatbot & LLM

A crypto-native large language model with live on-chain data, Nansen Smart Money insights, token analytics, and support for 33+ blockchains. This is the most versatile and cost-effective product in the ChainGPT suite.

Key Facts

Endpoint	POST /chat/stream
Model	general_assistant
Cost	0.5 credits per request (1.0 with chat history enabled)
SDK	@chaingpt/generalchat
Chains	33+ supported blockchains
Response	Server-Sent Events (streaming) or buffered

What It Does

• Answers general crypto and blockchain questions with current data

• Retrieves live on-chain information (balances, transactions, contract state)

• Provides Nansen Smart Money tracking and wallet analytics

• Delivers token analytics including price, volume, market cap, and holder distribution

• Supports conversational context via chat history

Parameters

Parameter	Type	Required	Description
model	string	Yes	Must be "general_assistant"
question	string	Yes	The user's question or prompt
chatHistory	string	No	"on" or "off" (string, not boolean). Enables conversational memory. Doubles cost to 1.0 credits. Default: "off"
sdkUniqueId	string	No	Unique session identifier for maintaining chat history across requests
useCustomContext	boolean	No	Enable custom context injection
contextInjection	string	No	Custom context to inject into the prompt. Requires useCustomContext: true

Quick Start -- JavaScript

Install the SDK:

npm install @chaingpt/generalchat

Buffered Response

import { GeneralChat } from "@chaingpt/generalchat";

const client = new GeneralChat({
  apiKey: process.env.CHAINGPT_API_KEY,
});

const response = await client.createChatMessage({
  model: "general_assistant",
  question: "What is the current price of ETH and its 24h volume?",
  chatHistory: "off",
});

console.log(response.data.bot);

Streaming Response

import { GeneralChat } from "@chaingpt/generalchat";

const client = new GeneralChat({
  apiKey: process.env.CHAINGPT_API_KEY,
});

const stream = await client.createChatMessageStream({
  model: "general_assistant",
  question: "Explain how Uniswap V3 concentrated liquidity works",
  chatHistory: "off",
});

stream.on("data", (chunk) => {
  process.stdout.write(chunk.toString());
});

stream.on("end", () => {
  console.log("\n[Stream complete]");
});

With Chat History

const response = await client.createChatMessage({
  model: "general_assistant",
  question: "Now compare that to SushiSwap's approach",
  chatHistory: "on",
  sdkUniqueId: "session-abc-123",
});

Quick Start -- Python

pip install chaingpt

Buffered Response

from chaingpt.client import ChainGPTClient

client = ChainGPTClient(api_key="YOUR_API_KEY")

response = client.chat.create(
    model="general_assistant",
    question="What are the top 5 DeFi protocols by TVL?",
    chat_history="off",
)

print(response["data"]["bot"])

Streaming Response

from chaingpt.client import ChainGPTClient

client = ChainGPTClient(api_key="YOUR_API_KEY")

for chunk in client.chat.create_stream(
    model="general_assistant",
    question="Summarize today's major crypto market movements",
    chat_history="off",
):
    print(chunk, end="", flush=True)

Tips

• Use chatHistory: "off" for one-shot questions to save credits.

• Use sdkUniqueId to maintain separate conversation threads for different users or sessions.

• Combine with the Crypto News product by injecting recent headlines via contextInjection for AI-analyzed market summaries.

• The LLM already has access to live on-chain data -- you do not need to fetch and inject chain data manually.