Integration Guide
Set up your coding tool or application with the Brainiall LLM Gateway
API Endpoint
https://apim-ai-apis.azure-api.net/v1
OpenAI-compatible. Supports Authorization: Bearer, api-key, and Ocp-Apim-Subscription-Key headers.
Coding Tools
Cline / Roo Code / Kilo Code
Settings > API Provider > OpenAI Compatible (or Brainiall if available)
Base URL: https://apim-ai-apis.azure-api.net/v1
API Key: [your brnl- key]
Model: claude-opus-4-6
Continue.dev
Add to your ~/.continue/config.yaml:
models:
- provider: brainiall
model: claude-opus-4-6
apiKey: YOUR_KEY
Or use openai provider with apiBase:
models:
- provider: openai
model: claude-opus-4-6
apiBase: https://apim-ai-apis.azure-api.net/v1
apiKey: YOUR_KEY
Aider
export OPENAI_API_BASE=https://apim-ai-apis.azure-api.net/v1 export OPENAI_API_KEY=YOUR_KEY aider --model openai/claude-opus-4-6
curl / REST API
curl https://apim-ai-apis.azure-api.net/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-haiku-4-5",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
base_url="https://apim-ai-apis.azure-api.net/v1",
api_key="YOUR_KEY",
)
response = client.chat.completions.create(
model="claude-opus-4-6",
messages=[{"role": "user", "content": "Hello!"}],
)
Node.js (OpenAI SDK)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://apim-ai-apis.azure-api.net/v1",
apiKey: "YOUR_KEY",
});
const response = await client.chat.completions.create({
model: "claude-opus-4-6",
messages: [{ role: "user", content: "Hello!" }],
});
Popular Models
| Model | Input $/MTok | Output $/MTok |
|---|---|---|
| claude-opus-4-6 | $5.00 | $25.00 |
| claude-sonnet-4-6 | $3.00 | $15.00 |
| claude-haiku-4-5 | $1.00 | $5.00 |
| deepseek-r1 | $1.35 | $5.40 |
| deepseek-v3 | $0.27 | $1.10 |
| llama-3.3-70b | $0.72 | $0.72 |
| nova-pro | $0.80 | $3.20 |
| nova-micro | $0.035 | $0.14 |
Full list: GET /v1/models — 113+ models available.
Flex pricing saves 50% on supported models.