Antbase/Documentation

Python Integration

Use ANT with the OpenAI SDK, Anthropic SDK, or raw HTTP requests.

OpenAI SDK (Recommended)

Install the SDK if you haven't already:

pip install openai

Basic Usage

from openai import OpenAI

client = OpenAI(
    base_url="https://antbase.ai/v1",
    api_key="sk-ant-your-api-key",
)

response = client.chat.completions.create(
    model="ant:auto",  # Let ANT pick the best model
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."},
    ],
)

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

Streaming

stream = client.chat.completions.create(
    model="ant:auto",
    messages=[{"role": "user", "content": "Write a short poem about coding."}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Async

from openai import AsyncOpenAI
import asyncio

client = AsyncOpenAI(
    base_url="https://antbase.ai/v1",
    api_key="sk-ant-your-api-key",
)

async def main():
    response = await client.chat.completions.create(
        model="ant:best",  # Use best quality for complex tasks
        messages=[{"role": "user", "content": "Review this code for bugs..."}],
    )
    print(response.choices[0].message.content)

asyncio.run(main())

Environment Variables

Both SDKs support reading from environment variables:

# .env or shell
export OPENAI_API_BASE=https://antbase.ai/v1
export OPENAI_API_KEY=sk-ant-your-api-key

# Then in Python (no need to pass base_url or api_key)
from openai import OpenAI
client = OpenAI()  # Reads from environment

Tips

  • Use ant:fast for simple queries to minimize latency
  • Use ant:best for code review, complex reasoning, or when quality matters most
  • Check the X-Antbase-Model response header to see which model was actually used
  • Implement retry logic for 5xx errors — ANT has automatic failover but upstream providers can still fail