Skip to main content

​
Quickstart

Get from zero to a working chat completion in a few steps.

​
1. Create an account

Go to openference.com/register. You will receive a verification email. Click the link to activate your account.

​
2. Create an API key

  1. Log in at openference.com.
  2. Go to API Keys in the dashboard.
  3. Click Create API Key.
  4. Give it a name (e.g. “Cursor”) and optionally restrict it to specific models.
  5. Copy the key. It starts with sk-token-.
Keep your key secret. You can create as many keys as you need.

​
3. Make your first request

Use the base URL: https://api.openference.com/v1

​
curl example

curl https://api.openference.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-token-YOUR_KEY_HERE" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Say hello in one short sentence."}
    ]
  }'
You should receive a normal OpenAI-format response.

​
Python (OpenAI SDK)

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openference.com/v1",
    api_key="sk-token-YOUR_KEY_HERE"
)

response = client.chat.completions.create(
    model="your-model-name",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

​
4. Connect your favorite client

Choose your tool and follow the dedicated guide: All clients use the same base URL and same key.

​
5. Check available models

curl https://api.openference.com/v1/models \
  -H "Authorization: Bearer sk-token-YOUR_KEY_HERE"
The list is filtered to models your key is allowed to use.

​
What’s next?