Quick Start

Get started with Nextbit AI Platform in minutes. This guide will walk you through installation, authentication, and making your first API request.

Installation

First, install the OpenAI SDK for your preferred language. Our API is fully compatible with OpenAI's client libraries.

Python

Install OpenAI SDK

PYTHON

pip install openai

TypeScript/JavaScript

Install OpenAI SDK

NODE

npm install openai
# or
yarn add openai
# or
pnpm add openai

Authentication

To authenticate with the Nextbit API, you'll need an API key. Generate one from your API Keys dashboard.

Keep your API keys secure. Never expose them in client-side code or commit them to version control.

Setting Your API Key

Set API Key

export NEXTBIT_API_KEY="your-api-key-here"

First Request

Now let's make your first API request. We'll create a simple chat completion.

The following example shows how to create a basic chat completion using the OpenAI SDK configured to use Nextbit's API endpoint.

Key Configuration

base_url: Set to https://api.nextbit256.com/v1
api_key: Your Nextbit API key
model: Choose from available models (e.g., llama3.3:70b)

Chat Completion

POST

/v1/chat/completions

from openai import OpenAI
import os

# Initialize client with Nextbit endpoint
client = OpenAI(
    base_url="https://api.nextbit256.com/v1",
    api_key=os.environ.get("NEXTBIT_API_KEY")
)

# Create chat completion
response = client.chat.completions.create(
    model="llama3.3:70b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ]
)

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

Streaming

For better user experience, you can stream responses token by token as they're generated.

Set stream=true to enable streaming. The response will be sent as server-sent events (SSE), with each chunk containing a portion of the completion.

Streaming Request

stream = client.chat.completions.create(
    model="llama3.3:70b",
    messages=[
        {"role": "user", "content": "Write a haiku about AI"}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Error Handling

Always handle potential errors in your API requests:

Error Handling

from openai import OpenAI, APIError, RateLimitError
import os

client = OpenAI(
    base_url="https://api.nextbit256.com/v1",
    api_key=os.environ.get("NEXTBIT_API_KEY")
)

try:
    response = client.chat.completions.create(
        model="llama3.3:70b",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    print(response.choices[0].message.content)
except RateLimitError:
    print("Rate limit exceeded. Please try again later.")
except APIError as e:
    print(f"API error: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")

Next Steps

Now that you've made your first request, explore more features:

Chat Completions - Detailed API reference for chat completions
Models - Explore available models and their capabilities
Dashboard - Monitor your usage and manage billing
API Keys - Create and manage API keys

Explore API Reference