AcrossAI Model Manager for WordPress

AcrossAI Model Manager gives site administrators full control over three aspects of the WordPress 7.0 AI client: which model is used per capability, how long requests are allowed to run, and a complete audit log of every AI generation call made on the site.

Model Preferences

By default, WordPress picks the first available model from your configured AI connectors. This plugin adds a settings page under Settings > AcrossAI Model Manager where you can pin a specific model per capability — and that model will always be prioritised.

Text Generation — preferred model for all text-generation tasks

Image Generation — preferred model for image-generation tasks

Vision / Multimodal — preferred model for vision and multimodal tasks

HTTP Request Timeout

Set a site-wide timeout (in seconds) for all wp_ai_client_prompt() calls. Works directly with the WordPress 7.0 built-in AI client — no additional plugins required.

AI Request Logging

Every successful AI generation call is automatically logged to a dedicated database table. The Settings > AI Logs admin page provides a sortable, paginated view of all requests with:

Provider, model, and capability for each call

Full prompt text and response text (expandable detail view)

Token usage (prompt, completion, total) and request duration

Source tracking — which plugin, theme, mu-plugin, or WordPress core file triggered the request, including the file path and line number