Skip to main content

Quickstart

Prerequisites​

  1. Create a RockAPI Account or Sign in.
  2. Navigate to the API key page and create a new API Key.
  3. Python Version Requirements:
    • OpenAI: Python 3.7.1+
    • Claude: Python 3.7+ or TypeScript 4.5+
    • Gemini: Python 3.9+

SDK Installation​

Choose your preferred AI service:

OpenAI&DeepSeek​

Install the OpenAI Python Library:

pip install --upgrade openai

Claude​

Install the Claude Python Library:

pip install anthropic

Gemini​

Install the Gemini Python Library:

pip install -q -U google-generativeai

Authentication​

OpenAI&DeepSeek​

from openai import OpenAI

client = OpenAI(
    api_key='$ROCKAPI_API_KEY',
    base_url='https://api.rockapi.ru/openai/v1'
)

Claude​

import anthropic

client = anthropic.Anthropic(
    api_key='$ROCKAPI_API_KEY',
    base_url='https://api.rockapi.ru/anthropic'
)

Gemini​

import google.generativeai as genai
from google.api_core.client_options import ClientOptions

genai.configure(
    api_key='$ROCKAPI_API_KEY',
    transport='rest',
    client_options=ClientOptions(api_endpoint='https://api.rockapi.ru/google-ai-studio')
)

Making Your First Request​

DeepSeek​

from openai import OpenAI

client = OpenAI(
    api_key='$ROCKAPI_API_KEY',
    base_url='https://api.rockapi.ru/deepseek/v1'
)

response = client.chat.completions.create(
  model='deepseek-reasoner',
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
    {"role": "user", "content": "Where was it played?"}
  ]
)

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

OpenAI​

from openai import OpenAI

client = OpenAI(
    api_key='$ROCKAPI_API_KEY',
    base_url='https://api.rockapi.ru/openai/v1'
)

response = client.chat.completions.create(
  model='gpt-4o-mini',
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?"},
    {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
    {"role": "user", "content": "Where was it played?"}
  ]
)

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

Claude​

import anthropic

client = anthropic.Anthropic(
    api_key='$ROCKAPI_API_KEY',
    base_url='https://api.rockapi.ru/anthropic'
)

message = client.messages.create(
    model='claude-3-opus-20240229',
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude"}
    ]
)

print(message.content)

Gemini​

import google.generativeai as genai
from google.api_core.client_options import ClientOptions

genai.configure(
    api_key='$ROCKAPI_API_KEY',
    transport='rest',
    client_options=ClientOptions(api_endpoint='https://api.rockapi.ru/google-ai-studio')
)

model = genai.GenerativeModel('gemini-1.5-pro')
response = model.generate_content("Write a story about an AI and magic")
print(response.text)

Next Steps​

OpenAI​

Other Endpoints

Claude​

Explore more with the Anthropic API:

For further details, visit the Anthropic API Reference.

Gemini​

To learn more about working with the Gemini API, refer to the getting started tutorial for your preferred language. Explore the comprehensive guides and capabilities offered by the Gemini API.