Migration Guide

Switch from any provider by changing your base URL and API key — your existing code, SDKs, and tools continue to work unchanged.

From OpenAI Direct

Change base_url and api_key. No other code changes needed.

terminal

bash

# Before
export OPENAI_API_KEY=sk-...
export OPENAI_BASE_URL=https://api.openai.com/v1

# After
export OPENAI_API_KEY=ck-your-key-here
export OPENAI_BASE_URL=https://api.chuizi.ai/v1

From Anthropic Direct

Use the /anthropic endpoint for native protocol support. No format conversion, full feature parity.

terminal

bash

# Before
export ANTHROPIC_API_KEY=sk-ant-...

# After
export ANTHROPIC_API_KEY=ck-your-key-here
export ANTHROPIC_BASE_URL=https://api.chuizi.ai/anthropic

example.py

python

from anthropic import Anthropic

# Before
client = Anthropic()

# After — add base_url and api_key
client = Anthropic(
    base_url="https://api.chuizi.ai/anthropic",
    api_key="ck-your-key-here",
)

# Everything else stays the same
message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)

This is the recommended setup for Claude Code, Cline, and other tools that use the Anthropic SDK.

From OpenRouter

Chuizi.AI uses the same OpenAI-compatible protocol. Change the base URL and API key:

terminal

bash

# Before
export OPENAI_BASE_URL=https://openrouter.ai/api/v1
export OPENAI_API_KEY=sk-or-...

# After
export OPENAI_BASE_URL=https://api.chuizi.ai/v1
export OPENAI_API_KEY=ck-your-key-here

Model names are largely compatible. Chuizi.AI uses the provider/model format (e.g., anthropic/claude-sonnet-4-6), which matches OpenRouter conventions.

From Azure OpenAI

Azure OpenAI uses a different URL structure and API version parameter. Switch to the standard OpenAI SDK format:

example.py

python

from openai import OpenAI

# Before (Azure)
from openai import AzureOpenAI
client = AzureOpenAI(
    azure_endpoint="https://your-resource.openai.azure.com",
    api_version="2024-12-01-preview",
    api_key="your-azure-key",
)

# After (Chuizi.AI)
client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

# Update model names: deployment name → provider/model
response = client.chat.completions.create(
    model="openai/gpt-4.1",  # was: your Azure deployment name
    messages=[{"role": "user", "content": "Hello!"}],
)

From Vertex AI (Google)

Use the Gemini native protocol endpoint:

terminal

bash

export GEMINI_API_BASE=https://api.chuizi.ai/gemini
export GEMINI_API_KEY=ck-your-key-here

Or use the OpenAI-compatible endpoint with Google models:

example.py

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.chuizi.ai/v1",
    api_key="ck-your-key-here",
)

response = client.chat.completions.create(
    model="google/gemini-2.5-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)

Environment Variable Reference

Provider	Before	After (Chuizi.AI)
OpenAI	`OPENAI_API_KEY=sk-...`	`OPENAI_API_KEY=ck-...`
OpenAI	`OPENAI_BASE_URL=https://api.openai.com/v1`	`OPENAI_BASE_URL=https://api.chuizi.ai/v1`
Anthropic	`ANTHROPIC_API_KEY=sk-ant-...`	`ANTHROPIC_API_KEY=ck-...`
Anthropic	—	`ANTHROPIC_BASE_URL=https://api.chuizi.ai/anthropic`
OpenRouter	`OPENAI_BASE_URL=https://openrouter.ai/api/v1`	`OPENAI_BASE_URL=https://api.chuizi.ai/v1`
Azure	`AZURE_OPENAI_ENDPOINT=...`	`OPENAI_BASE_URL=https://api.chuizi.ai/v1`

What Changes, What Doesn't

Aspect	Changes	Stays the Same
Base URL	New Chuizi.AI endpoint
API key	`ck-` prefixed key
Model names	Use `provider/model` format
		Request/response format
		SDK methods and parameters
		Streaming behavior
		Error response structure
		Function calling / tool use

Next Steps

First Request — verify your migration works
Choosing a Protocol — decide between OpenAI, Anthropic, or Gemini protocol
Error Handling — Chuizi.AI-specific error codes