​
Quickstart

Follow these steps to get started with Apifree and start using GenAI capabilities.

​
1. Log in to the Platform

Create an Apifree account and sign in to the web console. If you are a new user, you can start with trial credits (if enabled) or top up via Stripe prepaid billing to unlock model usage and higher limits.

​
2. View Model List and Details

Go to the Models page to review currently available models, including:
  • Model pricing (per token / per image / per second, depending on modality)
  • Rate limits / quotas and usage constraints
  • Supported capabilities (text, image, video, speech, code)
  • An “Online Experience” (if available) to test the model quickly before integration
Use this step to shortlist the models you want to use in production and validate cost/latency trade-offs.

​
3. Experience GenAI Capabilities in the Playground

Open Playground to do real-time testing without writing code:
  • Select a model (text / image / video / speech)
  • Enter prompt and configure key parameters
  • Run inference and preview results
  • Export outputs when needed (e.g., generated image/video files)

​
4. Use Apifree API to Access GenAI Capabilities

​
4.1 Create an API Key

In the Developer Console → API Keys, click Create API Key to generate a key for your application. Apifree supports a simplified one account + multiple keys pattern, so you can:
  • Separate dev/staging/prod keys
  • Assign keys by team/service
  • Rotate keys without impacting other environments

​
4.2 Make Service Calls via REST API

Use your API key to call Apifree endpoints via REST. Below is an example request pattern (confirm the exact endpoint path and payload schema on your API Reference / Documentation page): 
curl https://api.apifree.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
Recommended practice:
  • Start with a small request to validate auth, model ID, and response schema
  • Monitor spend and quotas in the Console (usage stats + billing breakdown)

​
4.3 Call via OpenAI-Compatible Interface (Python)

Apifree supports OpenAI-compatible calling patterns. Here’s an example using Python: 
from openai import OpenAI

client = OpenAI(
    base_url="https://api.apifree.ai/v1",
    api_key="YOUR_API_KEY"
)

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

print(response.choices[0].message.content)
Notes:
  • Replace YOUR_API_KEY with your actual API key from the Developer Console
  • Replace the model ID with the model identifier from the Models page
  • If you support multimodal (image/video/speech), use the corresponding API method and payload defined in your API Reference