> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Flowise

> Use TokenLab chat models in Flowise workflows

## Overview

Flowise can call TokenLab through a TokenLab chat node when available, or through an OpenAI-compatible chat model node pointed at TokenLab.

<Note>
  **Type**: Workflow Builder

  **Primary Path**: OpenAI-compatible chat completions

  **Support Confidence**: Supported with scope limits
</Note>

## TokenLab Node

If your Flowise build includes a **TokenLab** chat model node:

1. Add **Chat Models** -> **TokenLab**
2. Create a TokenLab API credential
3. Set **Model Name** to `gpt-5.4-mini`
4. Connect it to your chain, agent, or workflow
5. Run a test prompt.

## OpenAI-Compatible Fallback

If the TokenLab node is not available yet, use an OpenAI-compatible chat model node with:

| Field    | Value                        |
| -------- | ---------------------------- |
| Base URL | `https://api.tokenlab.sh/v1` |
| API Key  | `sk-your-tokenlab-key`       |
| Model    | `gpt-5.4-mini`               |

## Recommended Models

* `gpt-5.4-mini` for most workflow tests
* `claude-sonnet-5` for stronger writing and reasoning
* `gemini-3.5-flash` for fast multimodal-friendly workflows
* `deepseek-v4-flash` for fast code or reasoning iterations