Quickstart
Aiberm provides a unified API that gives you access to hundreds of AI models through a single endpoint. Get started in minutes with our simple integration process.
Tip
Looking for information about free models and rate limits? Please see the FAQ.
Using the OpenAI SDK
The easiest way is to use the official OpenAI SDK, just change the base_url to start using it.
1from openai import OpenAI2 3client = OpenAI(4 api_key="sk-your-api-key-here",5 base_url="https://aiberm.com/v1"6)7 8response = client.chat.completions.create(9 model="google/gemini-2.5-flash",10 messages=[11 {"role": "user", "content": "Hello!"}12 ]13)14 15print(response.choices[0].message.content)Using the Aiberm API directly
You can use HTTP requests to call the API directly.
Info
Use our interactive Request Builder to generate API requests.
1import requests2 3response = requests.post(4 "https://aiberm.com/v1/chat/completions",5 headers={6 "Authorization": "Bearer YOUR_API_KEY",7 "Content-Type": "application/json"8 },9 json={10 "model": "google/gemini-2.5-flash",11 "messages": [12 {"role": "user", "content": "Hello!"}13 ]14 }15)16 17print(response.json())Next Steps
Our API also supports advanced features such as streaming and batch processing. Learn more by checking out the detailed documentation for the Chat Completions API.
The API also supports streaming.
Supported Models
We support various AI models, including but not limited to:
OpenAI Models
- GPT-4
- GPT-4 Turbo
- GPT-3.5 Turbo
Anthropic Models
- Claude-3 Opus
- Claude-3 Sonnet
- Claude-3 Haiku
Other Models
- Gemini Pro
- Llama 2
- More…