AI Provider for OpenCode Zen – Multi-Model LLM Connector

This plugin is an AI connector for OpenCode Zen. It registers OpenCode Zen with the WordPress AI Client, so every AI-enabled plugin on your site can reach 61 large language models through one API key — GPT, Claude, Gemini, Grok, Qwen, DeepSeek, MiniMax, Kimi and more, with no separate account per vendor. This plugin is an independent, third-party integration and is not affiliated with, endorsed by, or sponsored by OpenCode Zen. Why OpenCode Zen? OpenCode Zen is an AI model aggregator — one API key gives you access to 61 frontier models from OpenAI, Anthropic, Google, and others. Instead of managing separate API keys and billing accounts for each AI provider, you connect once to OpenCode Zen and switch between models freely. This makes it ideal for WordPress sites that want to experiment with different AI models, compare output quality, or use specialised models (e.g. a coding model for code-related tasks and a creative model for content). Features

• 61 models from one API key — GPT 5.x, Claude, Gemini 3.x, Qwen, MiniMax, Kimi, Grok, DeepSeek, and more
• Automatic model discovery — live model list fetched from the OpenCode Zen API and cached hourly; falls back to a hardcoded list when offline
• Full parameter control — temperature, max tokens, top P, presence penalty, frequency penalty, stop sequences, system instruction, and function declarations
• Chat history — multi-turn conversations, not just single prompts
• Settings page — configure default model and generation parameters without touching code
• API key via Connectors — enter your key once in Settings > Connectors; all AI-enabled plugins share it automatically
• Environment variable support — OPENCODE_ZEN_API_KEY for server-level configuration, bypassing the database entirely
• OpenAI-compatible API — built on the same protocol as OpenAI, so any model that works with the OpenAI provider works here
• No vendor lock-in — switch between GPT, Claude, and Gemini without changing plugin or configuration

What Can You Do With AI in WordPress? Once this provider is configured, any WordPress plugin or theme that integrates with the WordPress AI Client can use it:

• Block editor (Gutenberg) — AI writing assistance, rephrasing, summarising, and expanding content
• WooCommerce — AI-generated product descriptions, SEO meta titles, and customer review summaries
• SEO plugins — generate meta descriptions, focus keyphrases, and Open Graph content
• Customer support — power AI chatbots and FAQ auto-responses
• Translation and localisation — translate and adapt content for different markets
• Code generation — use a coding-specialised model (GPT 5.3 Codex, Grok Build) directly in the editor
• Image alt text — generate accessible alt attributes for media library images

Supported Models The live model list is fetched directly from the OpenCode Zen API, so you always see the latest models — no API key needed to read the catalogue. If the API is ever unavailable, a built-in fallback list of 61 models keeps everything working. Families include:

• GPT 5.x — Sol, Terra, Luna, plus Pro, Mini, Nano, and Codex variants
• Claude — Fable 5, Opus 4.x, Sonnet 5 / 4.x, Haiku 4.5
• Gemini 3.x — Flash, Flash Lite, and Pro
• More — Grok, Qwen, DeepSeek, MiniMax, GLM, Kimi, and free-tier models

See the full model catalogue for every model ID. Requirements

• PHP 7.4 or higher
• WordPress 7.0 or higher
• An OpenCode Zen account and API key

How the WordPress AI Provider System Works WordPress 7.0 introduced a built-in AI Client SDK. Plugins and themes call a standard API (e.g. "generate text from this prompt") without knowing which AI provider is active. Provider plugins like this one register themselves with WordPress and handle the actual API calls. This means:

1. Install this plugin → OpenCode Zen is registered as an AI provider
2. Enter your API key in Settings > Connectors
3. Every AI-enabled plugin on your site can now use OpenCode Zen automatically

You can also install multiple provider plugins and switch between them from the Connectors screen — no re-configuration of individual plugins needed. Settings Go to Settings > OpenCode Zen to configure:

• Default Model — the model used when no explicit model is requested by a plugin
• Temperature — controls output randomness (0.0–2.0, default 0.7)
• Max Tokens — maximum tokens in the response (1–200,000, default 4096)
• Top P — nucleus sampling threshold (0.0–1.0, default 1.0)
• Presence Penalty — penalises repeated topics (-2.0–2.0, default 0.0)
• Frequency Penalty — penalises repeated tokens (-2.0–2.0, default 0.0)

For Developers This plugin follows the official WordPress AI Provider pattern and works with any plugin built on the WordPress AI Client SDK. It registers the opencode-zen provider and supports the standard generation options (temperature, max tokens, top P, presence/frequency penalties, stop sequences, system instruction, and function declarations). The source code is on GitHub — bug reports and pull requests are welcome:

• Repository: github.com/mralaminahamed/ai-provider-for-opencode-zen
• Report a bug or request a feature: open a new issue
• Contribute code: submit a pull request

Developer documentation:

• Usage and code examples
• Architecture and API key resolution
• Development and contributing

More from us Other free plugins by the same author, all on WordPress.org. Another provider for the same AI Client

• AI Provider for MiniMax - MiniMax M2 and M3 models for text generation, for the WordPress AI Client.

For any site

• Swift Menu Duplicator - Duplicate menus in one click, snapshot revisions, export and import, WP-CLI and REST.
• Author Profile Blocks - Author and team profiles as Gutenberg blocks — grid, carousel, list and single.

For a WooCommerce store

• StoreSeeder - Realistic test data for WooCommerce and Fluent Cart — a whole shop from a recipe, with one-click cleanup.
• StoreSheet - Sync WooCommerce products, orders and coupons to a Google spreadsheet, one way and in the background.

1. Upload the plugin files to /wp-content/plugins/alamin-ai-provider-for-opencode-zen/.
2. Activate the plugin through the Plugins menu in WordPress.
3. Go to Settings > Connectors and enter your OpenCode Zen API key.
4. Go to Settings > OpenCode Zen to choose a default model and tune generation parameters.
5. Install any AI-enabled plugin (e.g. the AI Experiments plugin) to start using AI features.

Getting Your API Key

1. Sign up at opencode.ai
2. Go to opencode.ai/zen/settings/api-keys
3. Create a new API key and copy it
4. Paste it into Settings > Connectors in your WordPress admin

WP-CLI Installation wp plugin install alamin-ai-provider-for-opencode-zen --activate

1.5.0 - 2026-08-09 Added

• Settings are now applied to requests. Temperature, max tokens, top_p and the penalties had been stored since 1.0.0 and never read — nothing outside the settings class touched opencode_zen_settings, so saving the form changed a database row and nothing else. A caller's own value still wins; the saved values fill in what was left unset.
• opencode_zen_generate_text_params filter, which receives the model id — useful because Zen fronts several vendors and they do not all accept the same parameters.
• Custom options. Arbitrary passthrough parameters, which the AI Client's base class already merged into the request body but which no caller could reach, because the option was not declared. It matters more here than for a single-vendor provider: Zen fronts eight vendors, and a parameter only one of them understands has nowhere else to go.
• Chat history — the models are now declared as supporting multi-turn conversations, not just single prompts. They always could (the endpoint takes a messages array and the AI Client already sends one), but the capability was never declared and the AI Client routes on the declaration, so conversation requests were going to other providers. Every official WordPress AI provider declares this.

Changed

• PHP namespace is now OpenCodeZen\OpenCodeZenAiProvider\ (was AlAminAhamed\OpenCodeZenAiProvider\).
• Class names dropped their OpenCodeZen prefix, which the namespace already carries: OpenCodeZenProvider is Provider, OpenCodeZenSettings is Settings, OpenCodeZenModelMetadataDirectory is ModelMetadataDirectory, OpenCodeZenTextGenerationModel is TextGenerationModel, and OpenCodeZenProviderAvailability is ProviderAvailability.
• The model list no longer requires an API key. OpenCode Zen serves its catalogue publicly, and this plugin was returning early without a key — so a site saw the built-in fallback list at exactly the moment it was first being configured. The key is still sent when there is one.
• Synced the built-in fallback list to the live catalogue: 61 models, adding Claude Opus 5, Claude Sonnet 4, Kimi K3, Ling 3.0 Flash Free, Ling 3.0 Tiny Free and LongCat 2.0 Free.
• Restructured the bootstrap. The plugin file is now an entry point — constants, autoloader, boot — and all wiring moved into an AI_Provider_For_OpenCode_Zen singleton in class-ai-provider-for-opencode-zen.php, so every hook the plugin registers is visible in one file. Matches the layout used across this author's other plugins.
• Added OPENCODE_ZEN_VERSION, OPENCODE_ZEN_URL and OPENCODE_ZEN_PATH constants; only OPENCODE_ZEN_PLUGIN_FILE existed before. Both renames are internal. No hook, option, setting or model id changes, and nothing a site has configured is affected — but any code referencing these classes directly needs updating.

Fixed

• Removed qwen3.7-max and qwen3.7-plus, which were offered in the model list and are not served by OpenCode Zen. Selecting either produced a failed generation rather than an invalid-setting warning.
• The model directory no longer calls WordPress functions when running outside WordPress, which the class is documented to support.

1.4.0 - 2026-07-21 Added

• Connection status on the settings page — shows whether an OpenCode Zen API key is configured, with a link to the Connectors screen.
• "Connectors" quick link on the Plugins screen, next to Settings. Changed
• Synced the built-in fallback model list to the current OpenCode Zen catalogue — now 54 models (added GPT 5.6 Sol/Terra/Luna, Claude Sonnet 5, Grok 4.5, DeepSeek V4 Pro/Flash, MiniMax M3, GLM 5.2/5, Kimi K2.7 Code, and free-tier models; removed the retired Claude 3.5 Haiku and Nemotron 3 Super Free).
• A default model (GPT 5.5) is now pre-selected out of the box instead of an empty choice. Fixed
• Autoloader collision with WordPress core's bundled AI Client that could cause a TypeError on AI requests — the plugin no longer ships a conflicting copy of php-ai-client (WordPress core provides it at runtime).

1.3.1 - 2026-06-16 Fixed

• API key stored via Settings > Connectors (connectors_ai_opencode_zen_api_key) now correctly used for live model list fetching — previously fell back to the hardcoded model list even when the Connectors key was set.
• Settings get_settings() now returns all 6 default fields when the saved option is corrupt or missing; previously returned only temperature and max_tokens. Changed
• Added Claude Fable 5 and Claude Opus 4.8 to the fallback model list (42+ models total).

1.3.0 - 2026-06-16 Added

• Top P, Presence Penalty, and Frequency Penalty settings fields on the admin settings page.
• Full SupportedOptions coverage: temperature, top P, presence penalty, frequency penalty, stop sequences, system instruction, function declarations, and max tokens. Changed
• Extracted all admin HTML markup to templates/admin/ for cleaner separation of logic and presentation.
• Renamed plugin class directory from src/ to includes/ per WordPress plugin conventions.
• Removed AI Client SDK from Composer production dependencies — WordPress 7.0+ provides it natively at runtime.
• Updated Requires at least to 7.0.

1.2.1 - 2026-05-01 Fixed

• Connector showing as "Connected" before any API key is entered — provider availability now correctly checks for a configured API key.

1.2.0 - 2026-04-01 Added

• Provider logo displayed on the WordPress Connectors page alongside Anthropic, Google, and OpenAI.
• Expanded test suite from 37 to 48 tests covering all model families, provider logo path, and settings edge cases. Fixed
• False "no valid connector" warning on the AI admin page when API key is set via the Connectors page.

1.1.0 - 2026-03-01 Added

• Updated fallback model list from 4 stale models to 40+ current models (GPT 5.x, Claude 4.x, Gemini 3.x, Qwen, MiniMax, GLM, Kimi, Grok, and free-tier models).
• Domain Path header field to plugin file. Changed
• Improved plugin file header field ordering per WordPress.org standard.
• Added file-level PHPDoc block to plugin bootstrap file.

1.0.0 - 2026-01-01

• Initial release.
• OpenCode Zen provider registration with WordPress AI Client.
• Dynamic model discovery with transient caching and fallback list.
• Settings page for default model configuration.
• Support for OPENCODE_ZEN_API_KEY environment variable.