Jina AI: get an API key and write fiction with it on your phone

In Foreverse this one powers memory retrieval, not prose: it supplies embeddings for character-chat vector memory and lorebook RAG, with multilingual models that handle Chinese corpora well; the 10-million-token signup grant is nearly inexhaustible at personal scale. This page is the BYOK quick answer for Jina AI: key steps, direct console and pricing links, and the app-side notes that matter. Verified 2026-07-18.

Two links up front: get your key at the official console and check rates on the official pricing page. Prices and free quotas move; the official pages are authoritative.

What does it power inside Foreverse?

The factory preset declares 2 modality flags for Jina AI. The models actually available come from the live catalog fetched in-app — catalogs move fast, and the flag only means the protocol wiring is ready.

Modality	Used for
Embedding	Lorebook vector retrieval
Rerank	Retrieval rerank

How do I get a Jina AI API key?

Open jina.ai — the API panel on any product page auto-generates a free key for your session, preloaded with 10 million tokens.
For long-term use, register an account and view or create proper keys in the key manager at jina.ai/api-dashboard.
Paste the key into the app, then bind a jina-embeddings model in the EMBEDDING slot under default models.

Key in hand: three steps to connect

Open the app's Settings → AI models & services and find Jina AI in the list (one of 62 presets, with logo and search).
Paste the key and tap the connectivity test — it fires one real request to verify key and network, and pulls back the model list while it's at it.
Enable the models you want, then set per-modality defaults (text, image, speech, and video each get their own); continuation, chat, and listening route through them from then on.

The one universal host pitfall: the API host must include its full version prefix (this provider's exact form is in the notes below) — the app never appends /v1 for you.

Jina AI-specific notes

The preset host is https://api.jina.ai/v1, with embeddings on the OpenAI-compatible /embeddings endpoint (Jina officially mirrors the OpenAI text-embedding request/response schema). Its role in the app is the EMBEDDING slot under default models (character-chat memory and lorebook vector retrieval); the RERANK capability has no call path in the app yet, so treat it as an embedding provider for now. The free tier is limited to 100 requests per minute.

FAQ

Does Jina AI have a free tier?

Yes: new keys carry a one-time 10-million-token grant (no monthly refresh, no card), shared as one pool across embeddings, reranker, and reader; afterwards it's pay-as-you-go around $0.05 per million tokens, with free-tier limits of 100 RPM / 100K TPM.

Where does the key live once I paste it into the app?

It's stored on your device only, under system-level encryption — never uploaded or synced to any Foreverse server. Requests go straight from your phone to the provider's official endpoint with zero markup. To revoke access, delete the key in the provider's console.