Run a WordPress chatbot on Together AI open models
SleekAI plugs into Together AI’s OpenAI-compatible endpoint on https://api.together.xyz/v1, so a WordPress chatbot can run on any of the hundreds of open-weight models Together hosts – Llama 3.3, Mixtral, Qwen 2.5, DeepSeek, and more. Bring your own Together key.
Hundreds of open models behind one API key
Together AI hosts a wide library of open-weight LLMs – Llama 3.3, Mixtral, Qwen 2.5, DeepSeek R1, Gemma, and dozens more – behind a single OpenAI-compatible API. For a WordPress chatbot, that breadth is the whole appeal.
SleekAI treats Together as a normal OpenAI-compatible provider. Set the base URL to https://api.together.xyz/v1, paste your Together API key, and pick the model string per bot. Common picks are meta-llama/Llama-3.3-70B-Instruct-Turbo, Qwen/Qwen2.5-72B-Instruct-Turbo, deepseek-ai/DeepSeek-R1, or mistralai/Mixtral-8x22B-Instruct-v0.1.
For teams that want to stay vendor-neutral on the model layer while keeping one billing relationship and one set of API keys, Together is the natural fit.
Features
Wide model library
One Together account exposes hundreds of open-weight models – Llama, Mixtral, Qwen, DeepSeek, Gemma, and family variants. SleekAI picks the exact model per bot, which makes the WordPress site model-agnostic at the bot layer.
Open-weight pricing
Open-weight models on Together are typically cheaper per token than closed-weight frontier US models.
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 Together plus SleekAI fits
Model evaluation
Teams that want a structured way to compare Llama, Qwen, Mistral, and DeepSeek on their own WordPress content run a clone-and-swap experiment across the same Together key over a couple of weeks.
Budget-sensitive sites
High-volume marketing, search, and support chat on smaller open-weight models. Pricing per million tokens often comes in well under what a comparable closed-weight tier costs on a US frontier provider.
Code-heavy chat
DeepSeek Coder, Qwen Coder, and other open-weight code-tuned models give technical docs sites a strong baseline for code-assistant chat without paying for a top-tier closed model on every reply.
Wire SleekAI to Together AI in four steps
Map your data
Choose the posts, fields, taxonomies or users the bot should know and reference them in the instruction.
Add the provider
The provider becomes available across every bot configuration screen on the install.
Pick a model per bot
Multibot scopes each bot to a section of the WordPress site.
Set display conditions
Decide which pages, post types, roles or logged-in states show the chatbot.
Why Together fits a model-agnostic strategy
Picking a single closed-weight provider for a WordPress chatbot used to be the easy choice, because the model gap between top-tier closed and best-available open-weight was wide enough that the conversation ended there. That gap closed in 2024 and is essentially gone for grounded chat in 2025 and 2026.
Llama 3.3, Qwen 2.5, DeepSeek R1, and Mixtral variants all produce comparable answers on the WordPress use case – read a few injected posts and respond with a grounded paragraph plus a link – at a fraction of the cost of frontier US models.
The blocker that remained was integration overhead: standing up a Hugging Face deployment, paying for a separate inference cluster, or signing a contract with each provider separately. Together collapses all of that into one OpenAI-compatible endpoint, one key, and one bill, with hundreds of open-weight models behind it.
SleekAI plugs into that endpoint with a base URL and an API key, and Multibot lets each chatbot on the WordPress install pick its own model string. The end result is a chatbot stack that does not bet the whole strategy on a single vendor’s quarterly roadmap. The cheapest model that does the job wins, and switching takes a minute instead of a quarter.
Frequently asked questions
What is Together AI in one sentence?
Together AI is a US-based inference provider that hosts hundreds of open-weight LLMs – Llama, Mixtral, Qwen, DeepSeek, Gemma, and many more – behind a single OpenAI-compatible API. One account and one key give you access to the whole library.
Which Together model should I pick first?
For grounded WordPress chat, meta-llama/Llama-3.3-70B-Instruct-Turbo is a strong default. For cheaper high-volume bots, the 8B Turbo variant works well. For long-context retrieval, Qwen2.5-72B-Instruct-Turbo is excellent. DeepSeek R1 is interesting for reasoning-heavy questions.
Where does the request go?
WordPress calls api.together.xyz directly using the bearer key from your Together account. There is no Sleek-hosted relay.
Can I run multiple Together models on one WordPress install?
Yes. Multibot lets each chatbot pick its own model string. A common pattern is Llama 3.3 70B Turbo on the docs site for quality, Qwen 2.5 8B Turbo on the marketing pages for speed and cost, and DeepSeek R1 on a research-heavy bot – all from one Together key.
How does pricing compare to closed-weight providers?
Open-weight models on Together generally cost significantly less per million tokens than comparable closed-weight tiers from US frontier labs. Exact rates change often – check the Together pricing page for current numbers – but on the smaller models the gap can be an order of magnitude.
Does this work with Together fine-tuned models?
Yes. If you fine-tune a model on Together, the resulting deployment exposes a normal model string.
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.
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