Bring your own OpenAI key and run GPT-4o on your WordPress data
SleekAI talks directly to the OpenAI Chat Completions endpoint with your own key, picks the model per chatbot, and stuffs the prompt with the right slice of your live WordPress posts and postmeta before each reply.
OpenAI without a SaaS middleman
SleekAI keeps you in a direct relationship with OpenAI. You paste an API key from platform.openai.com, pick a model from the dropdown (GPT-4o, GPT-4o-mini, o1, o3-mini, GPT-4.1 when available), and SleekAI hits https://api.openai.com/v1/chat/completions directly from your WordPress server. The pricing you see on OpenAI’s billing page is exactly what you pay.
OpenAI’s API has no idea what is on your site.
Features
Your own OpenAI key
Paste a key from platform.openai.com into SleekAI settings and you are live. Usage hits your OpenAI billing tier directly. No reseller, no markup, no shared quota with other sites on a vendor platform.
Per-bot model picker
Pick GPT-4o-mini for cheap FAQ bots and GPT-4o or o1 for complex reasoning tasks. Under multibot, the support bot can run on one model while the sales bot runs on another, all with the same key.
Answers from your data
Map post titles, content, post meta, taxonomies or a WP_Query into the instruction, and the bot answers from what your site actually publishes.
Where OpenAI-powered SleekAI shines
Course tutors
Stronger reasoning on GPT-4o or o1 powers tutor bots inside LearnDash modules, with lesson content streamed into the system prompt per question.
Support deflection
Knowledge-base sites point a GPT-4o-mini bot at their published articles. Live tickets drop because the bot answers from current docs, not a quarterly training snapshot.
Repeat questions
Answer the questions visitors ask every day from the pages and posts where you already answer them.
How SleekAI talks to OpenAI
Set display conditions
Decide which pages, post types, roles or logged-in states show the chatbot.
Pick a model per bot
In each chatbot’s settings, pick a model from the OpenAI dropdown. GPT-4o-mini for cheap volume, GPT-4o for higher quality, o1 or o3-mini when you need reasoning. Different bots on the same site can use different models.
Pick a model
Store your OpenAI, Anthropic, Google or OpenRouter key once in the shared AI settings, or add a compatible endpoint, and choose the chatbot’s model.
Map your data
Choose the posts, fields, taxonomies or users the bot should know and reference them in the instruction.
Why a direct OpenAI integration beats reseller widgets
Vendor chat platforms that advertise GPT-4o have a structural conflict with you. They want their margin on every token, so they batch your traffic with thousands of other sites against one shared OpenAI account.
When OpenAI bumps prices, the vendor passes through 2x or 5x to protect their margin. When OpenAI ships a new model, the vendor takes weeks to expose it because their pricing tiers need to be reworked. You sit downstream of all those decisions with no leverage.
The direct path is simpler and cheaper. Your WordPress server calls OpenAI with your key. The bill is what OpenAI charges. The latency is what OpenAI delivers. New models appear the day OpenAI ships them, because SleekAI is just a dropdown.
The role SleekAI plays is the boring middle layer that nobody else is willing to be. It maps your WordPress data into the prompt, formats the response, and stays out of the way. The relationship with the model provider belongs to you.
Frequently asked questions
Which OpenAI models can I use with SleekAI?
Any chat-completion model your OpenAI account has access to: GPT-4o, GPT-4o-mini, o1, o1-mini, o3-mini, GPT-4-turbo, and GPT-3.5-turbo. Tier-gated models like o1 require the right OpenAI usage tier on your key.
Do my prompts pass through any SleekAI server?
No. SleekAI runs entirely inside your WordPress install. The plugin is the only piece of SleekAI infrastructure that touches the request.
How does pricing compare to vendor platforms?
You pay OpenAI list prices directly. As of 2025, GPT-4o-mini is around 15 cents per million input tokens and 60 cents per million output. A typical 2000-token chat costs well under a tenth of a cent. Vendor platforms that bundle GPT-4o usually charge 5 to 20 cents per chat in credits.
What about streaming responses?
Streaming is enabled by default. SleekAI uses Server-Sent Events from the OpenAI API and pipes them to the chat widget so the reply appears token by token.
Can I switch from OpenAI to Anthropic or Google later?
Yes, with no rewrite. The provider is a setting per chatbot. You can run the same bot on GPT-4o on Monday and Claude Sonnet on Tuesday by swapping the provider and key in the UI. The variable mapping, display conditions, and conversation log all carry over.
Which AI providers does it support?
OpenAI, Anthropic, Google and OpenRouter, plus custom OpenAI-compatible endpoints. You bring your own API key and the provider bills you directly.
Where does the chatbot get its answers?
From the WordPress data you map into its instruction: post titles and content, post meta, ACF and Meta Box fields, taxonomies, terms, users and user meta, or a WP_Query. Values resolve on every request.
Can it act on a visitor’s behalf?
No. A chatbot answers questions.
Pricing
Explore our flexible licensing options tailored to your needs. Upgrade your license anytime to access more features, or opt for a lifetime license for ongoing value, including lifetime updates and lifetime support. Our hassle-free upgrade process ensures that our platform can grow with you, starting from whichever plan you choose.
…or get the Bundle Deal
and save €250
The Bundle (unlimited sites)
Pay once, own it forever
Elevate your WordPress site with our exclusive plugin bundle that includes all of our premium plugins in one package. Enjoy lifetime updates and lifetime support. Save significantly compared to buying plugins individually.
What’s included
SleekAI
SleekByte
SleekMotion
SleekPixel
SleekView
SleekRank
SleekTrack