Quickstart

Make your first API call in 2 minutes.

1. Create an Account

Sign up for a free account. Verify your email by clicking the link in your inbox.

2. Create an Organization

Go to your Dashboard > API Keys page. You'll be prompted to create an organization on first visit.

3. Generate an API Key

Click "Create Key", give it a name, and copy the key immediately — it's only shown once. Your key starts with sk-bc-.

4. Make Your First Request

The gateway is OpenAI-compatible. Use any OpenAI SDK or plain HTTP:

curl

curl https://gateway.broadcomms.net/v1/chat/completions \
  -H "Authorization: Bearer sk-bc-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="sk-bc-YOUR_API_KEY",
    base_url="https://gateway.broadcomms.net/v1",
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-bc-YOUR_API_KEY",
  baseURL: "https://gateway.broadcomms.net/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Streaming

Add "stream": true to get real-time token delivery via SSE:

curl https://gateway.broadcomms.net/v1/chat/completions \
  -H "Authorization: Bearer sk-bc-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4",
    "messages": [{"role": "user", "content": "Write a haiku"}],
    "stream": true
  }'

5. Switch Models

Change the model parameter to use any supported provider:

• gpt-4o, gpt-4o-mini — OpenAI
• claude-sonnet-4, claude-haiku-4 — Anthropic
• gemini-2.5-flash, gemini-2.5-pro — Google

No code changes needed — just a different model name.

6. Monitor Usage

Visit your Usage Dashboard to see requests, tokens, cost by model, and daily breakdowns in real time.