Skip to main content

​
Common Error Symptoms

When you see error messages like this: 
{
  "error": {
    "message": "Incorrect API key provided: sk-QqHvK***...",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}
This usually means NOT that your API Key is wrong, but that the Base URL is misconfigured.
Most Common Mistake: Using APIYI’s Key but sending requests to OpenAI’s official endpoint https://api.openai.com

​
What is Base URL?

Base URL (Base URL / Request Address) is the target server address for API requests. Different API service providers use different Base URLs.

​
Base URL and API Key Must Match

Service ProviderBase URLAPI Key FormatMatch?
APIYIhttps://api.apiyi.comsk-xxxx......✅ Correct
OpenAI Officialhttps://api.openai.comsk-xxxx......✅ Correct
❌ APIYI Keyhttps://api.openai.comsk-xxxx......❌ Wrong
❌ OpenAI Keyhttps://api.apiyi.comsk-xxxx......❌ Wrong
Key Principle: Use the Base URL that matches your API Key provider.

​
Correct Configuration

Simply replace the OpenAI endpoint with APIYI’s, keep everything else unchanged: 
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-apiyi-key",  # Get Key from APIYI dashboard
    base_url="https://api.apiyi.com/v1"  # Change to APIYI address
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)

​
Method 2: Use Environment Variables

Set environment variables so you don’t need to specify Base URL in code: 
export OPENAI_API_KEY="sk-your-apiyi-key"
export OPENAI_BASE_URL="https://api.apiyi.com/v1"

​
Supported Base URL Formats

APIYI supports three Base URL formats depending on your code:

​
Troubleshooting

Possible Causes:
  1. Multiple configuration points: Check if Base URL is set in config files, environment variables, code initialization, etc.
  2. Proxy or middleware: Some proxy tools may redirect requests
  3. Cache issues: Restart the program or clear cache and retry
  4. Typo: Verify apiyi is spelled correctly (not apiyii or apiyl)
Check in APIYI dashboard:
  1. Login to APIYI dashboard console.apiyi.com
  2. Go to “Tokens” page
  3. Check if Key status is “Enabled”
  4. Confirm account has sufficient balance
Most third-party tools have “Custom API” or “Self-hosted Server” options:
  • API Address / Base URL: https://api.apiyi.com/v1
  • API Key: Copy your Key from APIYI dashboard
  • Model Name: Refer to model list in APIYI documentation
Configuration options are usually found in “Settings” → “API” or “Server” sections
APIYI provides complete code examples in multiple languages:
  1. Quick Start Documentation: Homepage → Code Examples
  2. Online Testing Tool: Dashboard → ApiFox Online Testing
  3. GitHub Repository: github.com/apiyi/docs → knowledge-base directory

​
Wrong vs Correct Examples

❌ Wrong Configuration

client = OpenAI(
    api_key="sk-apiyi-key",
    base_url="https://api.openai.com/v1"
    # ❌ Using OpenAI official endpoint
)
Result: OpenAI server will reject APIYI’s Key

✅ Correct Configuration

client = OpenAI(
    api_key="sk-apiyi-key",
    base_url="https://api.apiyi.com/v1"
    # ✅ Using APIYI endpoint
)
Result: Request successfully sent to APIYI server

​
Quick Test Method

Use cURL command to quickly verify your configuration: 
curl https://api.apiyi.com/v1/models \
  -H "Authorization: Bearer sk-your-apiyi-key"
Expected Result: Returns list of available models 
{
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      ...
    }
  ]
}
If you get an error, check:
  1. API Key copied correctly (watch for leading/trailing spaces)
  2. Network connection is working
  3. Account has sufficient balance
Remember the core principle: Match the URL to the Key provider. APIYI’s Key uses https://api.apiyi.com/v1