Quickstart

Get up and running with SandBase in under 5 minutes. By the end of this guide, you'll have made your first API call to an LLM through SandBase.

1. Create an Account

Sign up for a free SandBase account at www.sandbase.ai. You can sign up with your email or use Google/GitHub OAuth.

2. Get Your API Key

1. Go to the Console
2. Navigate to API Keys in the sidebar (or go directly to console/keys)
3. Click Create API Key
4. Give your key a name (e.g., "Development")
5. Copy the key — it starts with sk-sb- and won't be shown again

WARNING

Store your API key securely. Never commit it to version control or share it publicly.

3. Make Your First API Call

SandBase is fully compatible with the OpenAI SDK. Just point it at https://api.sandbase.ai/v1 and use your SandBase API key.

cURL

curl https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-sb-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-sb-YOUR_API_KEY",
    base_url="https://api.sandbase.ai/v1"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from 'openai';

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

const response = await client.chat.completions.create({
  model: 'deepseek/deepseek-v3',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);

4. See the Response

A successful response looks like this:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1719000000,
  "model": "deepseek/deepseek-v3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 8,
    "total_tokens": 17
  }
}

That's it! You've successfully made your first API call through SandBase.

Using the Anthropic SDK

SandBase also supports the Anthropic Messages API. You can use the Anthropic SDK by pointing it at SandBase:

Python

import anthropic

client = anthropic.Anthropic(
    api_key="sk-sb-YOUR_API_KEY",
    base_url="https://api.sandbase.ai"
)

message = client.messages.create(
    model="anthropic/claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)
print(message.content[0].text)

JavaScript

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: 'sk-sb-YOUR_API_KEY',
  baseURL: 'https://api.sandbase.ai',
});

const message = await client.messages.create({
  model: 'anthropic/claude-sonnet-4-20250514',
  max_tokens: 1024,
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(message.content[0].text);

Try Different Models

SandBase supports 1400+ models. Just change the model parameter:

Model	Provider	Use Case
openai/gpt-4o	OpenAI	General purpose, multimodal
anthropic/claude-sonnet-4-20250514	Anthropic	Complex reasoning, long context
deepseek/deepseek-v3	DeepSeek	Cost-effective, fast
google/gemini-2.5-pro	Google	Multimodal, large context
meta/llama-4-maverick	Meta	Open-weight, fast inference

Next Steps

• API Keys — Learn about key management and security
• First API Call — Understand request/response anatomy in detail
• API Reference — Full endpoint documentation
• Models — Browse all available models and pricing