內容簡介
Opace AI Hub 是一款專為 WordPress 設計的外掛，提供與 OpenAI、Anthropic Claude 和 Google Gemini 的整合，讓使用者能夠簡化 AI 服務的設定與管理，提升網站的智能化功能。
【主要功能】
• 集中管理多個 AI 服務提供者的憑證
• 實時發現可用的 AI 模型
• 提供請求、代幣和發佈費用估算
• 支援文本、圖像及結構化輸出處理
• 提供可匯入和匯出的提示庫
• 加密憑證儲存及卸載時的數據保留選擇
外掛標籤
開發者團隊
② 後台搜尋「Opace AI Prompt Library & API Integration Hub for OpenAI, Claude & Gemini」→ 直接安裝（推薦）
原文外掛簡介
Compatibility: Version 1.0.17 was tested on WordPress 7.1 and PHP 8.4, plus WordPress 6.5 and PHP 7.4. Minimums: WordPress 6.5 and PHP 7.4.
Opace AI Hub is independently developed by Opace Digital Agency and is not affiliated with, endorsed by or sponsored by OpenAI, Anthropic or Google.
Opace AI Hub gives compatible WordPress plugins one shared connection to AI providers. Add an OpenAI, Anthropic Claude or Google Gemini key once, test it, and let compatible plugins use the same saved configuration.
Opace AI Hub is independently installable infrastructure, not a content generator. AI Scribe is a separate companion plugin that sends content-generation requests through it.
Opace AI Hub product page
AI Scribe on WordPress.org
AI Scribe on GitHub
Opace AI Hub on GitHub
Why Opace AI Hub was built
As separate WordPress plugins added AI features, each one risked duplicating provider settings, model lists, request formats, prompt storage and cost calculations. Opace AI Hub moves that security-sensitive infrastructure into one maintained plugin. Site administrators get one place to rotate keys, choose models and review usage, while compatible plugins stay focused on their own workflows.
How AI Scribe uses Opace AI Hub
AI Scribe owns article planning, writing, SEO metadata, editorial review and WordPress publishing. Opace AI Hub supplies its encrypted credentials, provider and model selection, normalised generation requests, reusable prompts, model capabilities and usage records.
AI Scribe on WordPress.org
AI Scribe on GitHub
Opace AI Hub on GitHub
What Opace AI Hub provides
One settings screen for supported provider credentials
Live model discovery based on the models available to your provider account
Provider-aware handling for text, images and structured output
A grouped prompt library with import and export
Request, token and published-rate cost estimates by provider and model
A PHP API for compatible WordPress plugins
Encrypted credential storage and an explicit data-retention choice on uninstall
Supported providers
OpenAI – text and image generation through the Chat Completions, Responses and Images APIs
Anthropic Claude – text generation through the Messages API; Anthropic does not provide image generation
Google Gemini – text and image generation through the Gemini API
Model lists are fetched using your key. Providers may make different models available to different accounts, so two sites can show different choices.
Current providers and live model catalogue
Live catalogue snapshot: 23 August 2026 at 13:03 BST (UTC+1). The Hub refreshed configured provider accounts at that time and received 132 OpenAI, 10 Anthropic Claude and 50 Google Gemini identifiers. Provider access varies by account, region and rollout; Settings always uses the current list returned for your own key. The built-in registry is only a fallback and metadata source when live discovery is unavailable.
Multimodal text models selectable in the Hub
These generate text and accept visual input. Image input does not make them dedicated image generators.
OpenAI (45): gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5-pro, gpt-5.5-pro-2026-04-23, gpt-5.5, gpt-5.5-2026-04-23, gpt-5.4-pro, gpt-5.4-pro-2026-03-05, gpt-5.4, gpt-5.4-2026-03-05, gpt-5.4-mini, gpt-5.4-mini-2026-03-17, gpt-5.4-nano, gpt-5.4-nano-2026-03-17, gpt-5.2-pro, gpt-5.2-pro-2025-12-11, gpt-5.2, gpt-5.2-2025-12-11, gpt-5.1, gpt-5.1-2025-11-13, gpt-5-pro, gpt-5-pro-2025-10-06, gpt-5, gpt-5-2025-08-07, gpt-5-mini-2025-08-07, gpt-5-mini, gpt-5-nano-2025-08-07, gpt-4.1-2025-04-14, gpt-4.1, gpt-4.1-mini-2025-04-14, gpt-4.1-mini, gpt-4.1-nano, gpt-4.1-nano-2025-04-14, gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-4-0613, gpt-4o, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4o-mini-2024-07-18, gpt-4o-mini, o3, o3-mini
Anthropic Claude (7): claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6, claude-opus-4-5-20251101, claude-sonnet-4-5-20250929
Google Gemini (6): gemini-3.6-flash, gemini-3.1-pro-preview, gemini-3.1-pro-preview-customtools, gemini-2.5-pro, gemini-2.5-flash, gemini-pro-latest
Text and reasoning models selectable in the Hub
OpenAI (17): gpt-5-nano, gpt-4, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, gpt-3.5-turbo-16k, gpt-3.5-turbo, o4-mini-2025-04-16, o4-mini, o3-pro, o3-pro-2025-06-10, o3-2025-04-16, o3-mini-2025-01-31, o1-pro, o1-pro-2025-03-19, o1, o1-2024-12-17, chat-latest
Anthropic Claude (3): claude-sonnet-5, claude-fable-5, claude-haiku-4-5-20251001
Google Gemini (11): gemini-3.7-flash, gemini-3.5-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite-preview, gemini-3.1-flash-lite, gemini-3-flash-preview, gemini-2.5-flash-lite, gemini-flash-latest, gemini-flash-lite-latest, gemma-4-26b-a4b-it, gemma-4-31b-it
Image-generation models selectable in the Hub
OpenAI (6): gpt-image-2, gpt-image-2-2026-04-21, gpt-image-1.5, gpt-image-1, gpt-image-1-mini, chatgpt-image-latest
Google Gemini (7): gemini-3.1-flash-image, gemini-3.1-flash-image-preview, gemini-3.1-flash-lite-image, gemini-3-pro-image, gemini-3-pro-image-preview, gemini-2.5-flash-image, nano-banana-pro-preview
Anthropic Claude: no image-generation models were returned.
Live specialist models catalogued, not currently invoked
The Hub retains these live identifiers for capability-aware add-ons, but its present public helpers only execute text, structured-output and image requests. Listing a specialist model here does not claim a working Hub request path for that category.
OpenAI audio, speech and realtime (31): gpt-4o-transcribe, gpt-4o-transcribe-diarize, gpt-4o-mini-transcribe, gpt-4o-mini-transcribe-2025-03-20, gpt-4o-mini-transcribe-2025-12-15, gpt-4o-mini-tts, gpt-4o-mini-tts-2025-03-20, gpt-4o-mini-tts-2025-12-15, gpt-realtime-2.1, gpt-realtime-2.1-mini, gpt-realtime-2, gpt-audio-1.5, gpt-realtime-1.5, gpt-transcribe, gpt-audio, gpt-audio-2025-08-28, gpt-audio-mini, gpt-audio-mini-2025-10-06, gpt-audio-mini-2025-12-15, gpt-live-transcribe, gpt-realtime, gpt-realtime-2025-08-28, gpt-realtime-mini, gpt-realtime-mini-2025-12-15, gpt-realtime-translate, gpt-realtime-whisper, whisper-1, tts-1, tts-1-1106, tts-1-hd, tts-1-hd-1106
Gemini audio, music and live (10): gemini-3.5-live-translate-preview, gemini-3.1-flash-live-preview, gemini-3.1-flash-tts-preview, gemini-2.5-pro-preview-tts, gemini-2.5-flash-native-audio-latest, gemini-2.5-flash-native-audio-preview-09-2025, gemini-2.5-flash-native-audio-preview-12-2025, gemini-2.5-flash-preview-tts, lyria-3-pro-preview, lyria-3-clip-preview
Embeddings (6): OpenAI text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002; Gemini gemini-embedding-2-preview, gemini-embedding-2, gemini-embedding-001
Video (5): OpenAI sora-2-pro, sora-2; Gemini veo-3.1-fast-generate-preview, veo-3.1-generate-preview, veo-3.1-lite-generate-preview
OpenAI code (6): gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5-codex
OpenAI research and search (10): o4-mini-deep-research, o4-mini-deep-research-2025-06-26, o3-deep-research, o3-deep-research-2025-06-26, gpt-5-search-api, gpt-5-search-api-2025-10-14, gpt-4o-search-preview, gpt-4o-search-preview-2025-03-11, gpt-4o-mini-search-preview, gpt-4o-mini-search-preview-2025-03-11
Gemini research (3): deep-research-max-preview-04-2026, deep-research-preview-04-2026, deep-research-pro-preview-12-2025
Computer-use and agent models (4): OpenAI computer-use-preview, computer-use-preview-2025-03-11; Gemini gemini-2.5-computer-use-preview-10-2025, antigravity-preview-05-2026
Gemini robotics and question answering (4): gemini-robotics-er-2-preview, gemini-robotics-er-2-streaming-preview, gemini-robotics-er-1.6-preview, aqa
OpenAI moderation (2): omni-moderation-2024-09-26, omni-moderation-latest
Legacy or provider-specific text IDs excluded from the prose picker (9): OpenAI gpt-5.3-chat-latest, gpt-5.2-chat-latest, gpt-5.1-chat-latest, gpt-5-chat-latest, gpt-3.5-turbo-instruct, gpt-3.5-turbo-instruct-0914, babbage-002, davinci-002; Gemini gemini-omni-flash-preview
Dynamic model defaults
A valid saved choice is always preserved. If it is missing or retired, Opace AI Hub ranks the configured account’s live list within the intended family: newest Terra with medium reasoning for OpenAI writing; newest Claude Opus with medium effort for Anthropic writing; newest non-Lite Gemini Flash with medium thinking for Gemini writing; newest GPT Image for OpenAI images; and newest Gemini Flash Image / Nano Banana for Gemini images.
The maintained offline fallbacks are currently gpt-5.6-terra, claude-opus-5, gemini-3.6-flash, gpt-image-2 and gemini-3.1-flash-image (Nano Banana 2). Live discovery takes precedence, so a later model in the same preferred family can become the default without a plugin update. Opace AI Hub never silently replaces an explicit valid choice made by an administrator.
Compatible plugins
AI Scribe 3.0 or later – AI content creation and SEO optimisation. Hub 1.0.13 or newer supports AI Scribe 3.2.36’s corrected install and upgrade flow. The Add-ons screen installs the public AI Scribe package after explicit consent, then waits for the administrator to activate it from the same card.
Developers can also use Opace AI Hub’s PHP API in their own plugins.
What comes next
AI-Imagen is a planned image-generation workflow intended to use Opace AI Hub. It is not included in this release and has no announced release date. Other compatible plugins can use the same PHP API as the project grows.
Security and privacy
Provider keys are stored in the ai_core_settings option on your WordPress site. They are encrypted at rest with AES-256-CBC, using a random initialisation vector per value and a key derived from the site’s WordPress salts. If encryption fails, Opace AI Hub does not save the key as plain text.
Rotating the salts in wp-config.php makes saved keys unreadable. Re-enter them after a salt rotation.
Opace AI Hub does not include analytics or user tracking. Generation data is sent only when an administrator tests a provider or a compatible plugin requests a generation.
External services
Opace AI Hub connects to the following third-party services. Each provider bills you directly under the terms of your account.
OpenAI
Used when an administrator tests an OpenAI key or refreshes its model list, and when OpenAI is chosen for a generation. Opace AI Hub sends the OpenAI API key, requested model, request settings and prompt or image instructions supplied by the calling plugin. Requests go to api.openai.com.
OpenAI Terms of Use
OpenAI Privacy Policy
Anthropic Claude
Used when an administrator tests an Anthropic key or refreshes its model list, and when Anthropic is chosen for a generation. Opace AI Hub sends the Anthropic API key, requested model, request settings and prompt supplied by the calling plugin. Requests go to api.anthropic.com.
Anthropic Consumer Terms
Anthropic Privacy Policy
Google Gemini
Used when an administrator tests a Gemini key or refreshes its model list, and when Gemini is chosen for a generation. Opace AI Hub sends the Gemini API key, requested model, request settings and prompt or image instructions supplied by the calling plugin. Requests go to generativelanguage.googleapis.com.
Gemini API Additional Terms of Service
Google Privacy Policy
LiteLLM public model catalogue
Used when Opace AI Hub needs current published pricing for a discovered model and when an administrator selects Refresh Model Pricing. Opace AI Hub sends only the provider name and model identifier to api.litellm.ai. API keys, prompts, generated content, site details and usage totals are not sent. Successful results are cached for 12 hours. Opace AI Hub uses its bundled catalogue when no current result is available and shows Cost unavailable rather than treating an unknown price as zero.
LiteLLM catalogue and licence
LiteLLM privacy and data security
WordPress.org plugin directory
Used only when an administrator chooses Install AI Scribe on the Add-ons screen. Opace AI Hub asks the WordPress plugin API for AI Scribe’s public package and passes its download URL to WordPress’s core installer. WordPress.org receives the normal plugin-information and package-download requests; Opace AI Hub does not send API keys, prompts, generated content, site settings or usage records. Installation stops for the administrator to choose Activate AI Scribe and continue.
AI Scribe on WordPress.org
Cost figures shown by Opace AI Hub are published-rate estimates. Free tiers, cached-token rates, batch pricing, negotiated rates and provider billing changes can make an invoice differ from the estimate.
Video demonstration
Watch the current Opace AI Hub walkthrough, covering provider setup, live model discovery, the Prompt Library, usage statistics and companion-plugin integration.
Opace and related links
AI Scribe on WordPress.org
AI Scribe on GitHub
Opace AI Hub on GitHub
Opace Digital Agency
Web design and development
WordPress development
AI SEO services
