quick-start.mdx

title	description
Quick Start	Quick Start Guide for Axon Models

Prerequisites

1. You need to have a MatterAI account on https://app.matterai.so
2. You need to have API Key for your MatterAI account. You can generate API Key in https://app.matterai.so/api-keys

Export an environment variable on macOS or Linux systems

export MATTERAI_API_KEY=YOUR_API_KEY

Install the OpenAI SDK and Run an API Call

```javascript OpenAI NodeJS SDK import OpenAI from "openai";

const openai = new OpenAI({ apiKey: "MATTERAI_API_KEY", baseURL: "https://api.matterai.so/v1", });

async function main() { const response = await openai.chat.completions.create({ "model": "axon", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "What is Rust?" } ], "stream": false, "max_tokens": 1000, "reasoning": { "effort": "high", "summary": "none" }, "response_format": { "type": "text" }, "temperature": 0, "top_p": 1 });

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

main();

```python OpenAI Python SDK
from openai import OpenAI

client = OpenAI(
  api_key='MATTER_API_KEY',
  base_url='https://api.matterai.so/v1'
)

response = client.chat.completions.create(
  model='axon',
  messages=[
    {
      'role': 'system',
      'content': 'You are a helpful assistant.'
    },
    {
      'role': 'user',
      'content': 'What is Rust?'
    }
  ],
  stream=False,
  max_tokens=1000,
  reasoning={
    'effort': 'high',
    'summary': 'none'
  },
  response_format={
    'type': 'text'
  },
  temperature=0,
  top_p=1
)

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

curl --request POST \
  --url https://api.matterai.so/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer MATTER_API_KEY' \
  --data '{
  "model": "axon",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is 9,387 * 8,145?"
    }
  ],
  "stream": false,
  "max_tokens": 1000,
  "reasoning": {
    "effort": "high",
    "summary": "none"
  },
  "response_format": {
    "type": "text"
  },
  "temperature": 0,
  "top_p": 1
}'