Novita AI provides a compatibility API that allows you to use the Anthropic SDK with Novita AI models. This is useful if you are already using the Anthropic SDK and want to switch to Novita AI models.

​
Supported Models

Currently, only the following models are compatible with the Anthropic SDK:
  • moonshotai/kimi-k2-instruct

​
Quick Start Guide

This guide demonstrates how to use the Anthropic SDK with the Novita AI models step by step.

​
1. Install the Anthropic SDK

pip install anthropic

​
2. Initialize the Client

The Anthropic SDKs are designed to pull the API key and base URL from the environmental variables: ANTHROPIC_API_KEY and ANTHROPIC_BASE_URL. Also, you can supply the parameters to the Anthropic client when initializing it.
You can view and manage your API keys on the settings page.
  • Using Environment Variables
export ANTHROPIC_BASE_URL="https://api.novita.ai/anthropic"
export ANTHROPIC_API_KEY="<YOUR_NOVITA_API_KEY>"
  • Set the parameters while initializing the Anthropic client
import anthropic

client = anthropic.Anthropic(
    base_url="https://api.novita.ai/anthropic",
    api_key="<YOUR_NOVITA_API_KEY>",
    # Rewrite header
    default_headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer <YOUR_NOVITA_API_KEY>",
    }
)

​
3. Call the API

import anthropic

# Initialize the client, if you already set `ANTHROPIC_BASE_URL` and `ANTHROPIC_API_KEY` 
# in the environment variables, you can omit the `api_key` and `base_url` parameters.
client = anthropic.Anthropic(
    base_url="https://api.novita.ai/anthropic",
    api_key="<YOUR_NOVITA_API_KEY>",
    # Rewrite header
    default_headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer <YOUR_NOVITA_API_KEY>",
    }
)

message = client.messages.create(
    model="moonshotai/kimi-k2-instruct",
    max_tokens=1000,
    temperature=1,
    system=[
        {
            "type": "text",
            "text": "You are a world-class poet. Respond only with short poems."
        }
    ],
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Why is the ocean salty?"
                }
            ]
        }
    ]
)

print(message.content)