anth2oai 0.1.0

Anthropic to OpenAI API Wrapper - Use Claude models with OpenAI-compatible interface

🔄 anth2oai

Anthropic to OpenAI API Wrapper

Use Anthropic's Claude models with OpenAI-compatible API interface

---

Overview

anth2oai is a lightweight wrapper that allows you to use Anthropic's Claude models through an OpenAI-compatible API interface. This makes it easy to switch between OpenAI and Anthropic models in your existing codebase with minimal changes.

Features

• ✅ OpenAI-compatible interface - Drop-in replacement for OpenAI client
• ✅ Async & Sync support - Both AsyncAnth2OAI and Anth2OAI clients available
• ✅ Streaming support - Full support for streaming responses
• ✅ Tool/Function calling - Automatic conversion of OpenAI tools format to Anthropic format
• ✅ System prompts - Automatic handling of system messages
• ✅ Custom base URL - Support for Anthropic API proxies

---

Installation

pip install anth2oai

Or install from source:

git clone https://github.com/your-repo/anth2oai.git
cd anth2oai
pip install -e .

---

Quick Start

Async Client

import asyncio
from anth2oai import AsyncAnth2OAI

async def main():
    client = AsyncAnth2OAI(
        api_key="your-anthropic-api-key",
        # base_url="https://api.anthropic.com"  # Optional: custom endpoint
    )

    # Non-streaming
    response = await client.chat.completions.create(
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Hello, who are you?"}
        ],
        model="claude-sonnet-4-5-20250929",
    )
    print(response.choices[0].message.content)

    # Streaming
    stream = await client.chat.completions.create(
        messages=[{"role": "user", "content": "Tell me a joke"}],
        model="claude-sonnet-4-5-20250929",
        stream=True,
    )
    async for chunk in stream:
        if chunk.choices[0].delta.content:
            print(chunk.choices[0].delta.content, end="", flush=True)

asyncio.run(main())

Sync Client

from anth2oai import Anth2OAI

client = Anth2OAI(
    api_key="your-anthropic-api-key",
)

# Non-streaming
response = client.chat.completions.create(
    messages=[{"role": "user", "content": "Hello!"}],
    model="claude-sonnet-4-5-20250929",
)
print(response.choices[0].message.content)

# Streaming
for chunk in client.chat.completions.create(
    messages=[{"role": "user", "content": "Count to 5"}],
    model="claude-sonnet-4-5-20250929",
    stream=True,
):
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

---

Tool/Function Calling

The wrapper automatically converts OpenAI's tool format to Anthropic's format:

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "City name, e.g., San Francisco",
                    },
                },
                "required": ["location"],
            },
        },
    },
]

response = await client.chat.completions.create(
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    model="claude-sonnet-4-5-20250929",
    tools=tools,
)

# Check for tool calls
if response.choices[0].message.tool_calls:
    for tool_call in response.choices[0].message.tool_calls:
        print(f"Function: {tool_call.function.name}")
        print(f"Arguments: {tool_call.function.arguments}")

---

Configuration

Environment Variables

You can configure the client using environment variables:

export OPENAI_API_KEY="your-anthropic-api-key"
export OPENAI_BASE_URL="https://api.anthropic.com"  # Optional

Then simply:

client = AsyncAnth2OAI()  # Will use env variables

Available Parameters

Parameter	Description	Default
api_key	Anthropic API key	OPENAI_API_KEY env var
base_url	API endpoint URL	https://api.anthropic.com
max_tokens	Maximum tokens in response	1024
timeout	Request timeout in seconds	None

---

Response Format

Responses are returned in OpenAI's ChatCompletion format:

ChatCompletion(
    id='chatcmpl-xxx',
    choices=[
        Choice(
            finish_reason='stop',
            index=0,
            message=ChatCompletionMessage(
                content='Hello! How can I help you today?',
                role='assistant',
                tool_calls=None,
            ),
        )
    ],
    created=1234567890,
    model='claude-sonnet-4-5-20250929',
    object='chat.completion',
    usage=CompletionUsage(
        completion_tokens=10,
        prompt_tokens=5,
        total_tokens=15,
    ),
)

---

Supported Models

Any Anthropic model can be used. Common models include:

• claude-sonnet-4-5-20250929 (Claude 3.5 Sonnet)
• claude-3-opus-20240229 (Claude 3 Opus)
• claude-3-haiku-20240307 (Claude 3 Haiku)

---

License

MIT License - see LICENSE for details.

---

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Acknowledgements

This project is inspired by the need to easily switch between OpenAI and Anthropic APIs in production applications.