Skip to main content
Every request you send to the NexLLM API must include your API key for authentication. For standard OpenAI-compatible requests, you pass the key as a Bearer token in the Authorization header. NexLLM also supports native provider authentication formats for Claude and Gemini, which use different header conventions.

​
Standard Authentication

Include your API key in the Authorization header as a Bearer token on every request: 
Authorization: Bearer sk-xxxxxxxxxxxxxxxx

​
Example: curl

curl https://www.nexllm.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'

​
Example: OpenAI SDK (Python)

Configure the OpenAI client with your NexLLM API key and base URL — all subsequent calls are authenticated automatically: 
from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxxxxxxxxxx",
    base_url="https://www.nexllm.ai/v1"
)

​
Native Provider Authentication

If you prefer to use provider-native request formats, NexLLM supports their authentication conventions as well.

​
Claude Native Format

Instead of the Authorization header, pass your key in the x-api-key header. You must also include the anthropic-version header: 
curl https://www.nexllm.ai/v1/messages \
  -H "x-api-key: sk-xxxxxxxxxxxxxxxx" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "aws/claude-haiku-4-5",
    "system": "You are a helpful assistant.",
    "max_tokens": 100,
    "messages": [
      {
        "role": "user",
        "content": "Write a short welcome message for a new user."
      }
    ]
  }'

​
Gemini Native Format

Pass your API key as a key query parameter on the Gemini-format endpoint: 
curl "https://www.nexllm.ai/v1beta/models/gemini-2.5-flash:generateContent?key=sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Hello"}]}]}'

​
Security Best Practices

Keep your API key secret at all times. Never hard-code it in client-side code, commit it to source control, or share it publicly. If a key is compromised, rotate it immediately from the NexLLM dashboard.
Use environment variables to manage your key in application code: 
export NEXLLM_API_KEY="sk-xxxxxxxxxxxxxxxx"

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["NEXLLM_API_KEY"],
    base_url="https://www.nexllm.ai/v1"
)
Don’t have an API key yet? Visit the Getting Your API Keys guide to create one from the NexLLM dashboard.