API Reference

Welcome to the Segmind API Docs! This guide will help you get started with using our REST APIs.

Authentication

Create an API key

The Segmind AI Gateway uses API keys for authentication. To create one, login to your account and head to the API Keys page on the dashboard.

Use the API

You can authenticate by including your Segmind API key in the Request Header and pass it as x-api-key section of the request.

Example cURL request:

curl --location 'https://api.segmind.com/v1/instantid' \
--header 'x-api-key: YOUR-API-KEY' \
--header 'Content-Type: application/json' \
--data '{
    }'

Example Python request:

import requests

api_key = "YOUR-API-KEY"
url = "https://api.segmind.com/v1/face-to-sticker"

# Request payload
data = {
}

response = requests.post(url, json=data, headers={'x-api-key': api_key})
print(response)

APIs

To integrate an API, visit the model's page and click on the "API" tab. You can see the list of parameters and example code to get started with the API.

Endpoints

Base URL

POST https://api.segmind.com/...

Version 1 (v1)

Some endpoints that typically complete their requests within 60 seconds are on version 1. For example: https://api.segmind.com/v1/sdxl1.0-newreality-lightning

Version 2 (v2)

We created v2 to serve APIs that typically take longer than 60 seconds to process.

API error codes

Below are the HTTP status codes returned by the Segmind API:

| Code | Status | Description | Billed? |
|---|---|---|---|
| **200** | Output Generated | Request completed successfully and output was produced. | Yes |
| **401** | Unauthorized | User authentication failed. Check your API key. | No |
| **404** | Not Found | The requested model endpoint or URL does not exist. | No |
| **405** | Method Not Allowed | The requested HTTP method is not supported for this endpoint. | No |
| **406** | Not Acceptable | Not enough credits in your account to process the request. | No |
| **422** | Validation Error | Invalid or missing parameters in the request body. | No |
| **429** | Too Many Requests | Rate limit exceeded. Retry after a short delay. | No |
| **500** | Server Error | An internal server error occurred during processing. | No |

Billing note: You are only charged for requests that return HTTP 200 (successful output). All error responses (4xx and 5xx) result in a full credit rollback — no charges are applied. See Pricing and Billing for more details on the credit reservation system.

Postman Collection

Use this Postman collection to get started faster.