Skip to main content

​
Common Error

When you see an error like this: 
{
  "error": {
    "message": "Incorrect API key provided: sk-QqHvK***...",
    "type": "invalid_request_error",
    "code": "invalid_api_key"
  }
}
This usually isn’t a problem with your API Key itself, but rather a Base URL misconfiguration.
Most common mistake: Using Nebula Lab’s Key but the request URL still points to OpenAI’s https://api.openai.com

​
What is Base URL?

Base URL is the target server address for API requests. Different providers use different Base URLs.

​
Base URL and API Key Must Match

ProviderBase URLAPI Key FormatMatch?
Nebula Labhttps://llm.ai-nebula.comsk-xxxx…✅ Correct
OpenAI Officialhttps://api.openai.comsk-xxxx…✅ Correct
❌ Nebula Keyhttps://api.openai.comsk-xxxx…❌ Wrong
❌ OpenAI Keyhttps://llm.ai-nebula.comsk-xxxx…❌ Wrong
Key principle: Use the provider’s Base URL that matches your API Key

​
Correct Configuration

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-nebula-key",
    base_url="https://llm.ai-nebula.com/v1"
)

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

​
Method 2: Environment Variables

export OPENAI_API_KEY="sk-your-nebula-key"
export OPENAI_BASE_URL="https://llm.ai-nebula.com/v1"

​
Supported URL Formats

FormatURLUse Case
With /v1 (recommended)https://llm.ai-nebula.com/v1Most libraries
With trailing slashhttps://llm.ai-nebula.com/v1/Some frameworks
Full pathhttps://llm.ai-nebula.com/v1/chat/completionscURL requests

​
Troubleshooting

Possible causes:
  1. Multiple configurations: Check config files, env vars, code initialization
  2. Proxy or middleware: Some tools may redirect requests
  3. Cache issues: Restart program or clear cache
  4. Typos: Verify the URL spelling
Check in Nebula Lab console:
  1. Login to Nebula Lab
  2. Go to “Tokens” page
  3. Check if Key status is “Enabled”
  4. Confirm account balance is sufficient
Most tools have “Custom API” options:
  • API URL / Base URL: https://llm.ai-nebula.com/v1
  • API Key: Copy from Nebula Lab console
  • Model name: Refer to model list

​
Wrong vs Correct Examples

​
❌ Wrong Configuration

client = OpenAI(
    api_key="sk-nebula-key",
    base_url="https://api.openai.com/v1"
    # ❌ Using OpenAI's URL
)
Result: OpenAI server rejects Nebula Lab’s Key

​
✅ Correct Configuration

client = OpenAI(
    api_key="sk-nebula-key",
    base_url="https://llm.ai-nebula.com/v1"
    # ✅ Using Nebula Lab URL
)
Result: Request successfully sent to Nebula Lab

​
Quick Test

Verify configuration with cURL: 
curl https://llm.ai-nebula.com/v1/models \
  -H "Authorization: Bearer sk-your-nebula-key"
Expected result: Returns available models list 
{
  "data": [
    {
      "id": "gpt-4o",
      "object": "model"
    }
  ]
}
If you get an error, check:
  1. API Key copied correctly (no extra spaces)
  2. Network connection is working
  3. Account balance is sufficient
Remember: Match the Key to its URL. Nebula Lab Key uses https://llm.ai-nebula.com/v1