Skip to main content
CC-Switch can connect to APIAny.AI through environment variables or local configuration files. It is useful for terminal, editor, and automated development workflows.

​
Prerequisites

  • CC-Switch is installed.
  • You have created an API key in the APIAny.AI dashboard.
  • You have selected a model ID.

​
Configure Claude Code

In CC-Switch, switch to Claude Code, add a configuration, and enter:
FieldValue
NameAPIAny.AI
Endpoint URLhttps://apiany.ai
API Keysk-xxxxxxxxxxxx
API FormatAnthropic Messages

​
Configure Codex

Fill auth.json with: 
{
  "OPENAI_API_KEY": "sk-xxxxxxxxxxxx"
}
Then fill config.toml with: 
model = "gpt-5.5"
model_provider = "apiany"

[model_providers.apiany]
name = "APIAny.AI"
base_url = "https://apiany.ai/v1"
wire_api = "responses"
requires_openai_auth = true
Save the configuration and enable APIAny.AI in CC-Switch.
Model IDBest for
gpt-5.5Best first choice for complex reasoning, coding, and production workflows.
gpt-5.4Strong general-purpose model for advanced chat and agent tasks.
gpt-5.4-miniBalanced speed, quality, and cost for everyday usage.
gpt-4o-miniFast and economical choice for simple chat, translation, and lightweight tasks.
claude-sonnet-4-6Claude-compatible model ID for long-form writing and coding workflows.
gemini-3.5-flashGemini-compatible model ID for fast multimodal usage.

​
Walkthrough screenshots

The screenshots below show the key configuration screens in CC-Switch. API names and endpoints have been adjusted for APIAny.AI.

​
Step 1

CC-Switch setup screenshot 1

​
Step 2

CC-Switch setup screenshot 2

​
Troubleshooting

​
401 or authentication errors

Make sure the API key is copied completely, has no extra spaces, and is enabled in the APIAny.AI dashboard.

​
The model does not appear in the app

Enter the model ID manually and confirm it is available in the model catalog. Some tools do not fetch model lists automatically.

​
Which Base URL should I use?

OpenAI-compatible settings usually use https://apiany.ai/v1; Claude-compatible settings usually use https://apiany.ai; tools that ask for a full endpoint use https://apiany.ai/v1/chat/completions.