OpenAI Integration

Use OpenAI's models through their official API while maintaining Bastio's security protection.

Overview

Bastio offers full support for OpenAI models, allowing you to:

Access latest models - GPT-5, GPT-4o, o1-preview, and more
Seamless integration - Drop-in replacement for OpenAI SDKs
Full security coverage - All Bastio security features work with OpenAI
Cost control - Track usage and set limits

Supported Models

Bastio supports all current OpenAI models:

Model	Context	Input/Output Price
GPT-5.1	272K	$1.25/$10.00 per 1M tokens
GPT-5	272K	$1.25/$10.00 per 1M tokens
GPT-5 Mini	272K	$0.25/$2.00 per 1M tokens
GPT-4o	128K	$2.50/$10.00 per 1M tokens
GPT-4o Mini	128K	$0.15/$0.60 per 1M tokens
o1-preview	128K	$15.00/$60.00 per 1M tokens
o1-mini	128K	$3.00/$12.00 per 1M tokens

Quick Start

Prerequisites

OpenAI API Key
OpenAI account with credits

Step 1: Get Credentials

Go to OpenAI Platform
Create a new secret key
Save it securely

Configuration

Via Dashboard

Go to Dashboard → Proxies → Create New Proxy
Select OpenAI as provider
Enter your OpenAI API key

Via API

# Create OpenAI proxy
curl -X POST https://api.bastio.ai/proxy \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Production OpenAI",
    "provider": "openai",
    "llm_mode": "byok",
    "model_behavior": "passthrough"
  }'

# Add API Key
curl -X POST https://api.bastio.ai/keys/provider \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "provider": "openai",
    "key_name": "OpenAI Production",
    "api_key": "sk-..."
  }'

Making Requests

Bastio is a drop-in replacement for the OpenAI API. Just change the baseURL and apiKey.

Python Example

from openai import OpenAI

client = OpenAI(
    base_url="https://api.bastio.ai/v1/guard/{PROXY_ID}/v1",
    api_key="your-bastio-api-key"
)

response = client.chat.completions.create(
    model="gpt-5.1",
    messages=[
        {"role": "user", "content": "Explain quantum computing"}
    ]
)

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

JavaScript Example

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.bastio.ai/v1/guard/{PROXY_ID}/v1',
  apiKey: process.env.BASTIO_API_KEY,
});

const response = await client.chat.completions.create({
  model: 'gpt-5.1',
  messages: [
    { role: 'user', content: 'Hello from OpenAI!' }
  ],
});

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

Streaming Example

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)

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

Features & Limitations

Supported Features

Chat Completions: Full support
Streaming: Real-time token streaming
Function Calling: Support for tools and function calling
Vision: Multimodal support (GPT-4o, GPT-5)
JSON Mode: Structured output support

Vision Example

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg"
                    }
                }
            ]
        }
    ]
)

Troubleshooting

Invalid API Key

Error: 401 Unauthorized or Incorrect API key provided Solution: Check that your OpenAI key is correct and active.

Quota Exceeded

Error: 429 Too Many Requests or You exceeded your current quota Solution: Check your OpenAI billing settings and credit balance.