> For the complete documentation index, see [llms.txt](https://docs.3techagency.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.3techagency.com/help-center/setup-and-account/ai-connector-and-models.md).

# AI connector and models

Resolve connector, approval and model selection issues.

WP AI Manager talks to AI through the WordPress core AI Client and a Connector plugin. Keys live in **WordPress Settings > Connectors**, never in WP AI Manager.

**Provider connected but requests fail?** Check, in order:

1. **Connector Approval** for the provider connector plugin (approval belongs to that plugin, not WP AI Manager).
2. The key is valid and has credit.
3. Rate limits. WP AI Manager retries once.
4. **Settings > AI Models > Connection details** and **Check again**.

**Which model is used?** Chat offers **Best quality** and **Faster, lower cost**. With nothing set in Settings, each picks a recommended model for your provider, for example claude-sonnet-5-5 and claude-haiku-5-5 for Anthropic, gpt-6.1-sol and gpt-6-luna for OpenAI, gemini-3.1-pro and gemini-3.7-flash for Google. **Settings > AI Models** shows **Recommended: model** and lets you override each tier. **Settings > Advanced > Model choice in chat** lets users pick any model.

Use models that support tool use. Image tasks such as alt text need a vision model, marked **(vision)** in Settings. Image generation needs an image-capable provider.

See [Connect AI and choose models](https://docs.3techagency.com/documentation/start-here/connect-ai-and-choose-models). Never paste a provider key into a prompt or screenshot.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.3techagency.com/help-center/setup-and-account/ai-connector-and-models.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.