APIKEY FUN Documentation

Welcome to the APIKEY FUN developer documentation. APIKEY FUN is a unified AI API gateway that lets you access OpenAI, Anthropic Claude, Google Gemini, DeepSeek, xAI Grok, and more with a single API key and a familiar OpenAI-compatible interface.

Quickstart

Get up and running in under 5 minutes.

Step 1 — Sign Up and Get Your API Key

Create a free account at apikey.fun. You'll receive $5 in free credits instantly. From your dashboard, navigate to API Keys and click Generate New Key.

Step 2 — Install the OpenAI SDK

# Python
pip install openai

# Node.js
npm install openai

Step 3 — Make Your First API Call

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_APIKEYFUN_KEY",
    base_url="https://api.apikey.fun/v1"
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Tell me a fun fact about Boulder, CO."}]
)

print(response.choices[0].message.content)

Authentication

All API requests must include your API key in the Authorization HTTP header using Bearer authentication:

Authorization: Bearer YOUR_APIKEYFUN_KEY

Never expose your API key in client-side code. Always load it from environment variables on your server.

Base URL

All API requests should be directed to:

https://api.apikey.fun/v1

When using any OpenAI-compatible SDK, set the base_url / baseURL parameter to this URL.

Your First Request

The endpoint POST /v1/chat/completions is the primary interface for all chat models. Here is a minimal example with cURL:

curl https://api.apikey.fun/v1/chat/completions \
  -H "Authorization: Bearer YOUR_APIKEYFUN_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Chat Completions

Create a model response for the given chat conversation. This endpoint is fully compatible with the OpenAI Chat Completions API.

Parameters

Streaming

Set stream: true to receive Server-Sent Events (SSE) as tokens are generated. All models support streaming.

response = client.chat.completions.create(
    model="claude-sonnet-4.6",
    messages=[{"role": "user", "content": "Write me a poem."}],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")

Function Calling

Function calling (tool use) is supported for models that natively support it, including GPT-5.4 and Claude Sonnet 4.6. Pass the tools parameter as you would with the standard OpenAI API.

Supported Models

All models below are accessible with your single APIKEY FUN key.

Model Pricing

Pricing is per 1 million tokens (blended input+output average). Exact rates are shown in your dashboard.

Rate Limits

When a rate limit is exceeded, the API returns a 429 Too Many Requests status. Implement exponential backoff for production applications.

Error Codes

Best Practices

• Always load API keys from environment variables — never hardcode them.
• Implement retry logic with exponential backoff for 429 and 5xx errors.
• Use the cheapest appropriate model for your use case (e.g. gpt-5.4-mini for simple tasks).
• Set max_tokens to limit output length and prevent runaway costs.
• Use streaming for long outputs to improve user-perceived latency.
• Monitor your usage in the dashboard and set spending alerts.