JOVION AI Assistant adds an AI chat panel to your WordPress admin. Ask JOVION to help with content, SEO, marketing, code, or just answer questions about your site setup. Bring your own AI: Google Gemini (free tier available), OpenAI, Anthropic Claude, Groq, or a fully self-hosted local model via Ollama \/ LM Studio \u2014 with a local model, requests go only to the server you run.<\/p>\n\n
Features:<\/strong><\/p>\n\n The admin assistant, the Playground and every setting are available only to users who can manage options. The Editor Copilot is available to anyone who can edit posts, so authors and editors can use it on their own drafts. The visitor chatbot is the one public-facing part, and it stays switched off until you enable it.<\/p>\n\n JOVION works with five providers: Google Gemini, OpenAI, Anthropic Claude, Groq, or a local model (Ollama \/ LM Studio). You only need ONE. A few things are worth understanding before you pick, because every provider's FREE tier has limits that are easy to hit during normal use.<\/p>\n\n The most important thing to know:<\/strong> free tiers are for trying a provider out, not for daily production use. AI agents like JOVION make several API requests for a single chat message (one for the reply, plus one per tool the assistant uses to get something done), so a handful of chats can add up to dozens of API requests quickly. If you plan to use JOVION regularly, add billing to your provider key or choose a provider with a higher free allowance.<\/p>\n\n Google Gemini<\/strong> \u2014 Easiest to start (free key, no card needed at first). JOVION's default Gemini model, Gemini 3.1 Flash-Lite, has the most generous free allowance (about 500 requests a day at the time of writing); other Flash models allow only about 20 a day on the free tier. When you pass the limit you will see an \"HTTP 429 \/ quota exceeded\" message \u2014 that is Google's limit, not a JOVION error. To lift it, add billing in Google AI Studio (Flash is very cheap pay-as-you-go \u2014 typically a fraction of a cent per request). Note: Google's published free-tier limits change periodically; check https:\/\/ai.dev\/rate-limit for the current numbers and your live usage.<\/p>\n\n Groq<\/strong> \u2014 A strong free choice for everyday use. Much more generous free limits than Gemini's free tier and very fast, using open-weight models. Good if you want to stay free without hitting a wall after a few chats.<\/p>\n\n OpenAI \/ Anthropic Claude<\/strong> \u2014 Pay-as-you-go from the first request (no free tier to run out of). The most predictable option if you don't want to think about daily caps; you simply pay for what you use.<\/p>\n\n Local (Ollama \/ LM Studio)<\/strong> \u2014 No key, no cost, no limits, and requests go only to the server you run. Requires you to run a local model, so it suits self-hosters comfortable with that setup.<\/p>\n\n One key per app.<\/strong> If you use the same Gemini key in more than one place (for example, another app on the same Google project), they SHARE the same daily quota and compete for it. If JOVION seems to hit limits faster than your own usage explains, check whether another app is using the same key\/project, and give each app its own key (or its own Google project) so they don't compete.<\/p>\n\n A 429 \/ \"rate limit\" \/ \"quota exceeded\" message is never a JOVION bug.<\/strong> It comes directly from your AI provider and means you have reached that provider's free-tier limit for the minute or the day. The fix is always on the provider side: wait for the window to reset, add billing, switch providers, or use a separate key.<\/p>\n\n JOVION talks to no service of its own. It contacts the AI providers you have saved a key for, in the situations listed below. Nothing is sent on activation or on a schedule. When you ask JOVION to install or update a plugin, theme or WordPress itself, WordPress's own installer and update check contact WordPress.org, exactly as they do from the Plugins and Updates screens.<\/p>\n\n AI providers (you choose one; hosted providers need your key).<\/strong> A request goes to the provider you have made active when you send a chat message, run a tool, test a connection, use the Editor Copilot on a post (the selected text or the post content), run a Playground prompt, or when a visitor uses the site chatbot. For the admin chat, the request contains your message and the conversation so far, any screenshot you attach, the results of tools JOVION runs for you (for example post content, or a file you asked it to read), your saved Memory notes, and a short description of the site so answers fit it: the site name and address, WordPress and PHP versions, timezone, your first or display name, the active theme, and the active plugins with their versions. The site chatbot sends only the visitor's messages, the site name and the persona you set. Your key goes with each request:<\/p>\n\n Model lists.<\/strong> When you open the Setup screen, JOVION asks each hosted provider you have saved a key for which models it currently offers, so the Model menu only lists models that exist. This sends your key to that provider's model-list endpoint and nothing else. The answer is kept for 12 hours (a failed attempt is retried after 15 minutes), and the Refresh models button asks again on demand. This only happens when an administrator opens that screen or presses the button.<\/p>\n\n Broken image check (optional).<\/strong> If you turn on the broken-image check in the SEO inventory, JOVION sends a HEAD request (no page content, no key) to each image address found in your posts and pages, to see whether the image still loads. Those addresses can point to any host your content links to. The check runs only when you ask for it.<\/p>\n\n Voice.<\/strong> The admin chat's microphone uses your browser's built-in speech recognition. JOVION sends no audio itself, but some browsers (for example Chrome and Edge) send the audio to their own vendor's servers to recognise it. Spoken replies use your browser's built-in voices.<\/p>\n\n Connections (optional).<\/strong> The Connections screen is there to facilitate clients running an Agency Hub: it lets a site be monitored by a JOVION Agency Hub, which is part of JOVION Agency, a paid product. The client site itself needs only this free plugin. If you create a pairing on the Connections screen, the site you paired with can call this site's REST API with the pairing token and read a status report: the site name and address, the WordPress, PHP and JOVION versions, which plugins, themes and core have updates pending (with their current and new versions), and whether the site uses HTTPS. The request comes from that site; this plugin sends nothing out. Nothing is readable until you create a pairing, and revoking it on the same screen cuts off access immediately.<\/p>\n\n Everything bundled with this plugin is licensed compatibly with GPLv2 or later.<\/p>\n\n Fonts<\/strong> (served from the plugin; no external font requests are made):<\/p>\n\n Everything described above is part of this plugin and works without a licence key. JOVION Pro is a separate plugin, available from jovionwp.com, that adds its own tools alongside it:<\/p>\n\n Pro's licence key is entered in the Pro plugin; this plugin never asks for one.<\/p>\n\n If JOVION Pro is installed but not yet switched on, or switched on without its licence key, this plugin shows a setup notice naming the missing step, so someone who has installed Pro is not left with it silently doing nothing. These notices appear only when JOVION Pro is installed, and disappear once both steps are done.<\/p>\n\n\n First public release.<\/p>\n\n\n
Choosing an AI Provider (and understanding rate limits)<\/h3>\n\n
External Services<\/h3>\n\n
\n
Bundled Resources and Credits<\/h3>\n\n
\n
JOVION Pro (a separate plugin)<\/h3>\n\n
\n
\n
1.0.9<\/h4>\n\n
\n
1.0.8<\/h4>\n\n
\n
1.0.7<\/h4>\n\n
\n
1.0.6<\/h4>\n\n
\n
1.0.5<\/h4>\n\n
\n
1.0.4<\/h4>\n\n
\n
1.0.3<\/h4>\n\n
\n
1.0.2<\/h4>\n\n
\n
llama-3.3-70b-versatile<\/code> does not exist or you do not have access to it\". Groq has retired the Llama models, which took the plugin's default and two of its five dropdown options with it. The list is now openai\/gpt-oss-20b, qwen\/qwen3.8-27b and openai\/gpt-oss-120b \u2014 each checked against the live API for both availability and tool-calling support, since a model that connects but cannot call tools would fail on the first real request instead of at setup.<\/li>\n1.0.1<\/h4>\n\n
\n
1.0.0<\/h4>\n\n
\n