Quick Start

Overview

AltLLM provides a unified API for accessing AI models with built-in crypto intelligence. Eligible catalogue-model requests can receive query-selected crypto data tools including:

• Token Prices - Live prices from CoinGecko
• Crypto News - Latest news from multiple sources
• Gas Prices - Real-time gas on Ethereum, Polygon, Arbitrum
• Project Data - Alpha on 100+ crypto projects
• IL Calculator - Impermanent loss calculations

Plans: Personal (subscription tiers: Free, Basic, Pro, Power) and Business (Flex tier; token-based access to frontier SKUs like GPT-5.6 Sol, and Gemini 3.6 Flash).

API Configuration

Get your API key from the API Keys page in the portal.

Using OpenAI SDK

The fastest way to integrate is using the official OpenAI SDK with our base URL.

Python

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://api.altllm.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="altllm-basic",
    messages=[
        {"role": "user", "content": "What's the price of Bitcoin?"}
    ]
)

print(response.choices[0].message.content)

TypeScript

npm install openai

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.altllm.ai/v1',
  apiKey: 'YOUR_API_KEY'
});

const response = await client.chat.completions.create({
  model: 'altllm-basic',
  messages: [
    { role: 'user', content: "What's the price of Bitcoin?" }
  ]
});

console.log(response.choices[0].message.content);

Direct API Call

You can also call the API directly using cURL or any HTTP client.

curl https://api.altllm.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "altllm-basic",
    "messages": [
      {"role": "user", "content": "What is the price of ETH?"}
    ],
    "max_tokens": 500
  }'

Available Models

* Text models are priced per 1M input/output tokens. GPT-5.6 Sol applies long-context rates above 272K input tokens.

Crypto Tools in Action

AltLLM models automatically use crypto tools when relevant. Here are some example queries:

Next Steps