OpenAI SDK Integration

Route all OpenAI SDK calls through the Curate-Me gateway with two line changes. Works with both the Python and TypeScript/Node.js SDKs.

Before and after

The only changes are base_url and the X-CM-API-Key header. Your existing code, prompts, and model names stay the same.

Python


# Before — direct to OpenAI
from openai import OpenAI
 
client = OpenAI(
    api_key="sk-your-openai-key",
)
 
# After — through Curate-Me gateway
from openai import OpenAI
 
client = OpenAI(
    api_key="sk-your-openai-key",
    base_url="https://api.curate-me.ai/v1/openai",      # ← added
    default_headers={"X-CM-API-Key": "cm_sk_YOUR_KEY"},  # ← added
)

TypeScript / Node.js


// Before — direct to OpenAI
import OpenAI from 'openai';
 
const client = new OpenAI({
  apiKey: 'sk-your-openai-key',
});
 
// After — through Curate-Me gateway
import OpenAI from 'openai';
 
const client = new OpenAI({
  apiKey: 'sk-your-openai-key',
  baseURL: 'https://api.curate-me.ai/v1/openai',          // ← added
  defaultHeaders: { 'X-CM-API-Key': 'cm_sk_YOUR_KEY' },   // ← added
});

Full Python example


from openai import OpenAI
 
client = OpenAI(
    api_key="sk-your-openai-key",
    base_url="https://api.curate-me.ai/v1/openai",
    default_headers={
        "X-CM-API-Key": "cm_sk_YOUR_KEY",
        "X-CM-Tags": "project=my-app,env=production",  # optional cost tags
    },
)
 
# Non-streaming
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "What is AI governance?"}],
)
print(response.choices[0].message.content)
 
# Streaming
stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Explain rate limiting."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Full TypeScript example


import OpenAI from 'openai';
 
const client = new OpenAI({
  apiKey: 'sk-your-openai-key',
  baseURL: 'https://api.curate-me.ai/v1/openai',
  defaultHeaders: {
    'X-CM-API-Key': 'cm_sk_YOUR_KEY',
    'X-CM-Tags': 'project=my-app,env=production',
  },
});
 
// Non-streaming
const response = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{ role: 'user', content: 'What is AI governance?' }],
});
console.log(response.choices[0].message.content);
 
// Streaming
const stream = await client.chat.completions.create({
  model: 'gpt-4o-mini',
  messages: [{ role: 'user', content: 'Explain rate limiting.' }],
  stream: true,
});
for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

Environment variable approach

If your app reads OPENAI_BASE_URL from the environment, you can route through the gateway with zero code changes:


export OPENAI_BASE_URL=https://api.curate-me.ai/v1/openai
export OPENAI_API_KEY=sk-your-openai-key

Then add your gateway key as a default header in your SDK initialization, or store your provider key in the gateway and use your cm_sk_ key directly as the API key.

What you get

Every request through the gateway automatically receives:

Feature	Description
Cost tracking	Per-request token and dollar cost recorded in real time
Rate limiting	Per-org, per-key request throttling
PII scanning	Regex scan for secrets and PII before hitting the provider
Model allowlists	Only approved models per your org policy
Budget caps	Daily and monthly spend limits enforced
Audit trail	Full request metadata logged for compliance

Working examples

Python example — non-streaming, streaming, system prompts
TypeScript example — non-streaming, streaming, system prompts

Next steps

Gateway Quickstart — full setup walkthrough
Cost Tracking — budget alerts and cost attribution
Governance Chain — deep dive into each governance step