AI research over the actual text
Scribe's AI Bible research is an optional study assistant that reasons over the passage you're reading, its Strong's entries, and the LSJ/BDB lexicons — grounded in the text, not a generic chatbot guessing. Bring your own key (a direct Anthropic key, or OpenRouter to pick a model), unlock it with Scholar, and it runs with no Scribe server in between.
Why bring your own key?
- Your choice of provider. Use a direct Anthropic (Claude) key, or OpenRouter to pick the model — Claude, GPT-4o, and more — for the same grounded study assistant.
- Private. Your questions go straight from the app to your chosen provider (Anthropic or OpenRouter). There's no Scribe server in the middle, and no account.
- No markup. You pay your provider directly for usage — typically cents per study session — with no Scribe markup on top.
- Optional. Reading, word study, and search are fully offline and never depend on the AI or a network.
What it's grounded in
The assistant is given the passage you're studying, the relevant Strong's entries and LSJ/BDB definitions, and the cross-references — so answers stay anchored to the text rather than free-floating.
Search the commentary library, too
If you own the Classical Commentary Library add-on, the assistant can search it as it works — pulling relevant passages from 12 classic commentators and the early church fathers, and quoting them with author attribution. The retrieval runs on-device against the library you've downloaded (on iPhone and iPad); like the rest of AI research, it's optional and stays off until you own the add-on.
Which models can I plug in?
With an OpenRouter key, paste any of these model IDs into Settings → AI Research. All seven run the full multi-step agentic research (a direct Anthropic key runs the same research on Claude):
| Model | Plug-in ID | |
|---|---|---|
| Claude Sonnet 4.6 | anthropic/claude-sonnet-4.6 | Default · balanced |
| Claude Opus 4.1 | anthropic/claude-opus-4.1 | Most capable |
| GPT-4o | openai/gpt-4o | |
| GPT-4o mini | openai/gpt-4o-mini | Cheapest |
| Gemini 2.5 Pro | google/gemini-2.5-pro | |
| Gemini 2.5 Flash | google/gemini-2.5-flash | Fast |
| DeepSeek V3.1 | deepseek/deepseek-chat-v3.1 | Budget |
Any other model from openrouter.ai/models works too — it just runs as a single grounded request rather than the multi-step research.
Setting it up
- Unlock Scholar ($4.99/mo or $59.99 once).
- Get an API key — a direct Anthropic (Claude) key, or an OpenRouter key at openrouter.ai to pick from more models.
- Paste the key into Scribe → Settings → AI Research (choose your provider; with OpenRouter, pick a model).
- Ask questions — the assistant answers grounded in the text, lexicons, and cross-references.
AI research questions
Which AI models can I use?
Bring your own key: a direct Anthropic (Claude) key, or an OpenRouter key to choose from Claude, GPT-4o, Gemini, DeepSeek and more. Queries go straight from the app to your chosen provider — no Scribe server in the middle.
Does AI research cost extra?
There is no Scribe markup. You pay your provider (Anthropic or OpenRouter) directly for usage — typically cents per study session. AI research unlocks with Scholar and requires your own API key.
What is the AI grounded in?
The passage you're studying, its Strong's entries, LSJ/BDB definitions, and TSK cross-references, so answers stay anchored to the text. If you own the Classical Commentary Library, it can also quote commentators with attribution (on iPhone and iPad).
Is AI required to use Scribe?
No. Reading, search, and word study are fully offline and never depend on the AI or a network. AI research is optional and stays off until you add your own key.
Further reading
Study deeper with AI.
Free for 30 days with everything unlocked. On iPhone and Android.
