Prerequisites
- AnythingLLM is installed.
- You have created an API key in the APIAny.AI dashboard.
- You have selected a model ID, such as
gpt-5.4-miniorgpt-4o-mini.
Configuration values
| Field | Value |
|---|---|
| LLM mode | Generic OpenAI |
| Base URL | https://apiany.ai/v1 |
| API Key | Your APIAny.AI API key |
| Chat model | gpt-5.4-mini |
Setup
- Open workspace settings and go to LLM configuration.
- Select Generic OpenAI.
- Enter the Base URL, API key, model name, and context window.
- Save and run a test chat in the workspace.
Recommended models
| Model ID | Best for |
|---|---|
gpt-5.5 | Best first choice for complex reasoning, coding, and production workflows. |
gpt-5.4 | Strong general-purpose model for advanced chat and agent tasks. |
gpt-5.4-mini | Balanced speed, quality, and cost for everyday usage. |
gpt-4o-mini | Fast and economical choice for simple chat, translation, and lightweight tasks. |
claude-sonnet-4-6 | Claude-compatible model ID for long-form writing and coding workflows. |
gemini-3.5-flash | Gemini-compatible model ID for fast multimodal usage. |
Walkthrough screenshots
The screenshots below show the key configuration screens in AnythingLLM. API names and endpoints have been adjusted for APIAny.AI.Step 1
Step 2
Step 3
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 usehttps://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.