CloudRouter Supported Models and Configuration Guide

1. Anthropic Models

Channels and Models

Official Business Channel	Official Premium Channel	Official Flagship Channel
claude-opus-4-6	claude-opus-4-6	claude-opus-4-6
claude-sonnet-4-6	claude-sonnet-4-6	claude-sonnet-4-6
claude-3-5-sonnet-20241022	claude-3-5-sonnet-20241022	claude-3-5-sonnet-20241022
claude-3-opus-20240229	claude-3-opus-20240229	claude-3-opus-20240229
claude-3-sonnet-20240229	claude-3-sonnet-20240229	claude-3-sonnet-20240229

Typical Configuration Example

Python

"""
Claude API call example
Configure the API Key and Base URL via the .env file
"""

import os
from dotenv import load_dotenv
import anthropic

# Load environment variables from the .env file
load_dotenv()

# Initialize the client (custom base_url and api_key)
client = anthropic.Anthropic(
    api_key=os.getenv("ANTHROPIC_AUTH_TOKEN"),
    base_url=os.getenv("ANTHROPIC_BASE_URL"),
)

# Send the request (use streaming output to avoid timeouts)
with client.messages.stream(
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=[{"role": "user", "content": "Introduce yourself in one sentence"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

print()  # newline

2. OpenAI Models

[Early Access] GPT Series Model Channel

• gpt-5.4 (available via CLI, not available for Python scripts)
• gpt-5.3-codex
• gpt-5.2-codex
• gpt-5.1-codex-mini
• gpt-5.1-codex-max
• gpt-5.1-codex
• gpt-5.1
• gpt-5-codex
• gpt-5
• o4-mini
• o3-pro
• o3-mini
• o1-pro
• o1-mini
• o1-preview
• o1
• gpt-4.1-nano
• gpt-4.1-mini
• gpt-4.5-preview
• gpt-4o-mini-2024-07-18
• gpt-4o-mini
• gpt-4o-2024-11-20
• gpt-4o-2024-08-06
• gpt-4o
• chatgpt-4o-latest
• gpt-4-turbo
• gpt-4-turbo-preview
• gpt-4
• gpt-3.5-turbo-16k
• gpt-3.5-turbo-1106
• gpt-3.5-turbo

Typical Configuration Example

Python

"""
OpenAI (Codex/GPT) API call example
Configure the API Key and Base URL via the .env file
"""

import os
from dotenv import load_dotenv
from openai import OpenAI

# Load environment variables from the .env file
load_dotenv()

# Initialize the client (custom base_url and api_key)
client = OpenAI(
    api_key=os.getenv("OPENAI_API_KEY"),
    base_url=os.getenv("OPENAI_BASE_URL"),
)

# Send the request (use streaming output to avoid timeouts)
stream = client.responses.create(
    model="gpt-5.2",
    input="Introduce yourself in one sentence",
    stream=True,
)

for event in stream:
    # Output text delta events
    if event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)

print()  # newline

3. Google Models

[Early Access] Gemini Series Model Channel

• gemini-3.1-pro-preview
• gemini-3-flash-preview
• gemini-2.5-pro
• gemini-2.5-flash

Typical Configuration Example

Python

"""
Gemini API call example
Configure the API Key and Base URL via the .env file
"""

import os
from dotenv import load_dotenv
from google import genai

# Load environment variables from the .env file
load_dotenv()

# Initialize the client (custom base_url and api_key)
client = genai.Client(
    api_key=os.getenv("GEMINI_API_KEY"),
    http_options={"base_url": os.getenv("GEMINI_BASE_URL")},
)

# Send the request (use streaming output to avoid timeouts)
stream = client.models.generate_content_stream(
    model="gemini-2.5-pro",
    contents="Introduce yourself in one sentence",
)

for chunk in stream:
    print(chunk.text, end="", flush=True)

print()  # newline