n8n-nodes-brainiall

This is an n8n community node for the Brainiall LLM Gateway -- access 113+ AI models from 17 providers through a single OpenAI-compatible API.

n8n is a fair-code licensed workflow automation platform.

Installation

Follow the installation guide in the n8n community nodes documentation.

Quick steps:

1. Open your n8n instance
2. Go to Settings > Community Nodes
3. Click Install
4. Enter n8n-nodes-brainiall
5. Click Install

Credentials

1. Go to brainiall.com and sign up for an API key
2. In n8n, go to Credentials > New Credential
3. Search for Brainiall API
4. Enter your API key
5. Click Save -- the credential will be tested automatically against the /models endpoint

Node: Brainiall LLM

Operations

| Operation | Description | |-----------|-------------| | Chat Completion | Send messages to any model and get a response | | List Models | Retrieve the full catalog of available models |

Available Models

The node includes a dropdown with popular models pre-configured:

Anthropic: Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 4.6, Claude Haiku 4.5

DeepSeek: DeepSeek R1, DeepSeek V3

Meta: Llama 4 Scout 17B, Llama 3.3 70B, Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B

Qwen: Qwen 3 235B, Qwen 3 30B

Mistral: Mistral Large 3, Mistral Small 3

Amazon: Nova Pro, Nova Lite, Nova Micro

MiniMax: MiniMax M2

You can also select Custom Model ID to use any model from the full catalog of 113+ models.

Options

| Option | Description | Default | |--------|-------------|---------| | Temperature | Controls randomness (0-2) | 1.0 | | Max Tokens | Maximum tokens in the response | 4096 | | Top P | Nucleus sampling threshold | 1.0 | | Frequency Penalty | Penalize repeated tokens (-2 to 2) | 0 | | Presence Penalty | Penalize tokens already in text (-2 to 2) | 0 | | JSON Mode | Force valid JSON output | false | | Stop Sequences | Comma-separated stop strings | - | | System Message | System prompt (used with simple Prompt field) | - |

Input

You can provide input in two ways:

1. Messages (structured): Add multiple messages with role (system/user/assistant) and content
2. Prompt (simple): Enter a single user prompt. Optionally add a System Message in Options

If both are provided, Messages takes precedence.

Output

Each item returns:

{
  "content": "The model's response text",
  "model": "claude-sonnet-4-6",
  "finish_reason": "stop",
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  },
  "id": "chatcmpl-...",
  "full_response": { ... }
}

Compatibility

• n8n version 1.0+
• Tested with n8n 1.70+

API Information

• Base URL: https://apim-ai-apis.azure-api.net/v1
• Auth: Bearer token (OpenAI-compatible)
• Endpoints: /chat/completions, /models
• Format: 100% OpenAI API compatible

Resources

• Brainiall Website
• n8n Community Nodes Documentation

License

MIT