Skip to main content

​
Introduction

The Flowise API provides programmatic access to manage chatflows, execute predictions, upsert vectors, and handle credentials. The API is RESTful, returns JSON responses, and uses standard HTTP response codes.

​
Base URL

All API endpoints are relative to your Flowise instance base URL: 
http://localhost:3000/api/v1
For production deployments, replace localhost:3000 with your domain.

​
API Endpoints

The Flowise API is organized around these main resources:

Chatflows

Create, read, update, and delete chatflows

Predictions

Execute chatflows and get AI predictions

Vector Upsert

Upsert documents into vector stores

Credentials

Manage API credentials for integrations

Tools

Create and manage custom tools

Authentication

Learn about API authentication methods

​
Additional Endpoints

Flowise also provides endpoints for:
  • API Keys (/api/v1/apikey) - Manage API keys for authentication
  • Assistants (/api/v1/assistants) - Create and manage OpenAI-style assistants
  • Document Stores (/api/v1/documentstore) - Manage document stores and chunking
  • Datasets (/api/v1/dataset) - Create and manage datasets for testing
  • Variables (/api/v1/variables) - Manage global and runtime variables
  • Executions (/api/v1/executions) - View chatflow execution history
  • Statistics (/api/v1/stats) - Get usage statistics

​
Response Format

All API responses are returned in JSON format. Successful responses return a 200 status code along with the requested data. 
{
  "id": "chatflow-id",
  "name": "My Chatflow",
  "deployed": true,
  "isPublic": false
}

​
Error Handling

The API uses standard HTTP status codes to indicate success or failure:
Status CodeDescription
200Success
400Bad Request - Invalid parameters
401Unauthorized - Invalid API key
403Forbidden - Insufficient permissions
404Not Found - Resource doesn’t exist
412Precondition Failed - Missing required parameters
500Internal Server Error
Error responses include a message describing the issue: 
{
  "message": "Error: chatflowsController.getChatflowById - id not provided!"
}

​
Rate Limiting

Prediction and vector upsert endpoints may be subject to rate limiting based on your chatflow configuration. Rate limit details are configured per chatflow.

​
Pagination

List endpoints support pagination using page and limit query parameters: 
GET /api/v1/chatflows?page=1&limit=10
​
page
number
default:"1"
Page number for pagination
​
limit
number
default:"10"
Number of items per page

​
SDKs and Libraries

While Flowise doesn’t provide official SDKs, the API is designed to work with any HTTP client: 
const response = await fetch('http://localhost:3000/api/v1/chatflows', {
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  }
});
const data = await response.json();

​
Next Steps

Set Up Authentication

Configure API keys for secure access

Execute Predictions

Start making predictions with your chatflows

Build docs developers (and LLMs) love

Get started for freeTalk to us