# Zactonz AI Connector for Groq

> Groq connector for the WordPress AI Client. Very low latency inference on GroqCloud, with every model on your account discovered automatically.

- **Type:** Plugin (WordPress plugins)
- **Version:** 1.0.1, released 5 Oct 2026
- **Requires:** WordPress 7.0+, PHP 7.4+, A Groq account and API key
- **Tested with:** WordPress 7.1.2
- **Licence:** GPL-2.0-or-later
- **Download:** https://downloads.wordpress.org/plugin/zactonz-ai-connector-for-groq.latest-stable.zip
- **WordPress.org:** https://wordpress.org/plugins/zactonz-ai-connector-for-groq/
- **Source:** https://github.com/zactonz/zactonz-ai-connector-for-groq
- **Documentation:** https://developers.zactonz.com/wordpress/plugins/zactonz-ai-connector-for-groq/

## Overview

Zactonz AI Connector for Groq registers Groq as a connector for the WordPress AI Client. It is built for the **Settings › Connectors** screen and for the plugin-directory connector search, so when WordPress asks for a connector you can add Groq in a couple of clicks. Once active, every model on your GroqCloud account is available to AI features in WordPress.

Groq runs open models on its own LPU hardware and is built around one thing: speed. The connector reads your GroqCloud catalogue, takes each model's context window from it, skips the models Groq has retired or that serve tasks WordPress cannot use, and keeps the default request timeout short because Groq rarely needs a long one.

### Features

- Text generation with every Groq chat model your credentials can reach.
- Automatic model discovery, with each model's context window taken from your GroqCloud catalogue.
- Models Groq has marked inactive, and models that serve tasks the AI Client cannot represent, are left out.
- A separate default model per capability, or automatic selection by the WordPress AI Client.
- Vision input on models that accept images.
- Tool calling and structured output with a JSON schema.
- Reasoning effort control for the default text model.
- Cancellable server-sent event streaming for content, reasoning and tool-call chunks.
- A configurable request timeout for text generation.
- API key supplied by a PHP constant or an environment variable instead of the database.
- An API base URL override for a proxy or gateway, within the hosts and ports WordPress allows outbound requests to.
- Redacted diagnostics and a WordPress Site Health connectivity test.

### A note on capabilities

Groq's model catalogue publishes each model's identifier, owner and context window, but not a per-model capability list. The connector therefore takes the context window from the catalogue and determines vision and reasoning support from the model family, offering tool calling and structured output across the chat models, which GroqCloud supports broadly. Where a provider does publish per-model capabilities, the connectors in this family use them in preference to any inference.

### Part of a family

This connector is one of the Zactonz AI Connector plugins, which add the providers WordPress core leaves out. They follow one set of conventions, so every connector behaves the same way in the admin. [Zactonz AI Connector for Ollama](https://developers.zactonz.com/wordpress/plugins/zactonz-ai-provider-ollama/) covers local, self-hosted and Ollama Cloud models; [Zactonz AI Connector for OpenRouter](https://developers.zactonz.com/wordpress/plugins/zactonz-ai-connector-for-openrouter/) covers hundreds of hosted models behind one key; [Zactonz AI Connector for DeepSeek](https://developers.zactonz.com/wordpress/plugins/zactonz-ai-connector-for-deepseek/) covers a very long context window and thinking mode; [Zactonz AI Connector for Mistral AI](https://developers.zactonz.com/wordpress/plugins/zactonz-ai-connector-for-mistral-ai/) covers Mistral AI's open-weight and commercial models with capabilities read from its catalogue; [Zactonz AI Connector for xAI Grok](https://developers.zactonz.com/wordpress/plugins/zactonz-ai-connector-for-xai-grok/) covers Grok text, vision and image generation. All of them are listed under [WordPress](https://developers.zactonz.com/wordpress/).

### Not affiliated

This connector is developed by Zactonz Technologies and is not affiliated with, endorsed by or sponsored by Groq. Groq and GroqCloud are trademarks of Groq, Inc.

## Installation & setup

### Install the plugin

From the dashboard, go to **Plugins › Add New**, search for **Zactonz AI Connector for Groq** and click **Install Now**, then **Activate**. WordPress also links here directly from **Settings › Connectors** when it needs a connector that is not installed yet.

With WP-CLI:

```bash
wp plugin install zactonz-ai-connector-for-groq --activate
```

To install manually, download the zip from the Download button above, upload the folder to `/wp-content/plugins/zactonz-ai-connector-for-groq/` and activate it from the **Plugins** menu.

### Connect to Groq

1. Create an API key in the [GroqCloud console](https://console.groq.com/keys).
2. Go to **Settings › Connectors** and paste the key into the Groq connector.
3. Go to **Settings › Groq** to review the discovered models and choose a default model per capability, a reasoning effort for the default text model, and the request timeout.

The key is stored in the option WordPress registers for the connector, so the Connectors screen and the connector's own settings screen always show the same credential.

### Keep the key out of the database

Define `GROQ_API_KEY` in `wp-config.php`, or set an environment variable of the same name. When either is present the connector uses it, the settings field is disabled, and nothing is written to the database.

```php
define( 'GROQ_API_KEY', 'gsk_…' );
```

### Use a proxy or gateway

**Settings › Groq** has an API base URL field. Leave it empty to use `https://api.groq.com/openai/v1`, or point it at a gateway that speaks the same API.

AI features reach the gateway through the WordPress AI Client, which sends every request with `wp_safe_remote_request()`. WordPress refuses such requests to loopback and private network addresses and to any port other than 80, 443 and 8080, so a gateway on a LAN address or a non-standard port will not work unless the site allows that host with the `http_request_host_is_external` filter. The connector's own connection check and Site Health test do not apply that restriction, so with such a gateway they can report a healthy connection while AI features still cannot reach it. Use a public hostname on a standard port, or add the filter.

### Check the connection

**Tools › Site Health** includes a connectivity test for Groq, which runs in the background so it never holds the screen open. **Settings › Groq** has a diagnostics button that reports the endpoint, HTTP status, latency, the number of discovered models, any configured defaults missing from the current catalogue, and the AI Client version. The key never appears in the report.

## FAQ

### Where do I get an API key?

Create one in the GroqCloud console at [console.groq.com/keys](https://console.groq.com/keys).

### Which models will I see?

Every model your GroqCloud account can reach, minus two groups: models Groq reports as inactive, and models that serve a task the WordPress AI Client cannot represent, such as speech-to-text, text-to-speech and safety classifiers. Each model's context window is read from your catalogue.

### Does this replace the connectors in WordPress core?

No. WordPress core ships its own connectors. This plugin adds Groq alongside them, and you can keep several connectors active at once and pick a default model per capability.

### Can I keep the key out of the database?

Yes. Define `GROQ_API_KEY` in `wp-config.php` or as an environment variable. The settings field is then disabled and nothing is stored.

### Is my key ever displayed or logged?

No. It is never rendered back into the settings screen, and it is excluded from the diagnostics report and from Site Health debug information.

### Does the connector support embeddings or image generation?

Not through Groq. GroqCloud serves chat models, so this connector offers text generation, vision input, tool calling, structured output and reasoning. Other connectors in the family cover embeddings and images where their provider supports them.

### Which WordPress and PHP versions are supported?

WordPress 7.0 or newer and PHP 7.4 or newer. The connector is tested against the AI Client build that ships with WordPress 7.1 as well as the newest release.

## Changelog

### 1.0.1 — 5 October 2026

**Fixed**

- The settings screen reported no saved API key, and hid the control that removes it, on a site where AI support is switched off.
- The model-discovery answer in the FAQ described capability detection for embeddings, which this connector does not offer, and claimed capabilities are read from the provider rather than guessed. Where Groq publishes no capability data for a model the connector falls back to inference.

**Changed**

- The saved API key is read back from the WordPress AI Client rather than straight from the option WordPress registers for the connector, which is how a connector is meant to obtain its credentials.

### 1.0.0 — 29 September 2026

- Initial release.
- Registers Groq with the WordPress AI Client and the Settings › Connectors screen.
- Discovers models from your GroqCloud catalogue, with context windows, and leaves out models Groq reports as inactive.
- Per-capability default model selection, reasoning effort, a configurable request timeout and an API base URL override.
- Cancellable server-sent event streaming for content, reasoning and tool-call chunks.
- Redacted diagnostics report and an asynchronous WordPress Site Health connectivity test.
- API key from a PHP constant or an environment variable.
