Quickstart

This guide takes about five minutes. You need a BreachLine account with credit in your organization’s wallet.

1. Create an API key

1. Sign in to the console.
2. Open Settings, then API & Developer.
3. Create a key. Give it a name that says where it will run, for example ci-staging.
4. Copy the key when it is shown. It is displayed once and cannot be retrieved later.

The key dialog preselects llm:access, llm:chat and cli:knowledge:read. llm:access and llm:chat are everything this guide needs, so you can clear the others. Creating a key needs a recent sign-in: if your session is older than five minutes, the console asks for your password.

2. Store the key in an environment variable

ShellCopy

export BREACHLINE_API_KEY="bl_live_YOUR_KEY"

Security

Never commit a key, paste it into a ticket or put it in client-side code. Load it from your secret manager or CI secrets at run time. If a key is exposed, revoke it in the console straight away; revocation takes effect immediately.

3. Make a request

cURL

cURLCopy

curl https://api.breachline.io/api/v1/llm/v1/chat/completions \
  -H "Authorization: Bearer $BREACHLINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nebula-4.5",
    "messages": [
      {"role": "system", "content": "You are a concise security assistant."},
      {"role": "user", "content": "What should I check first on a login form?"}
    ]
  }'

Python

Python (OpenAI SDK)Copy

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BREACHLINE_API_KEY"],
    base_url="https://api.breachline.io/api/v1/llm/v1",
)

response = client.chat.completions.create(
    model="nebula-4.5",
    messages=[
        {"role": "system", "content": "You are a concise security assistant."},
        {"role": "user", "content": "What should I check first on a login form?"},
    ],
)
print(response.choices[0].message.content)

TypeScript

TypeScript (OpenAI SDK)Copy

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.BREACHLINE_API_KEY,
  baseURL: 'https://api.breachline.io/api/v1/llm/v1',
});

const response = await client.chat.completions.create({
  model: 'nebula-4.5',
  messages: [
    { role: 'system', content: 'You are a concise security assistant.' },
    { role: 'user', content: 'What should I check first on a login form?' },
  ],
});
console.log(response.choices[0].message.content);

A successful call returns a chat.completion object. Every response carries an X-Request-ID header; quote it if you contact support.

4. Stream the answer

Add stream: true to receive tokens as they are generated, as server-sent events.

Python streamingCopy

stream = client.chat.completions.create(
    model="nebula-4.5",
    messages=[{"role": "user", "content": "List three common causes of SSRF."}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content if chunk.choices else None
    if delta:
        print(delta, end="", flush=True)

See Streaming for the event format and how errors arrive mid-stream.

If something goes wrong

Status	Meaning	Fix
401	The key is missing, mistyped, expired or revoked.	Check the header and the key’s status in the console.
402	The organization has no spendable credit, or its spend cap is reached.	Top up in Settings, Billing & Credits, or raise the cap.
403	The key lacks a scope, for example llm:chat.	Create a key with the right scopes.
429	A rate limit was hit.	Back off and retry; see Rate limits.

Next steps

• Learn the key lifecycle and scopes.
• Choose a model.
• Make retries safe with idempotency keys.
• Browse the API reference.