Multilingual embedding models from Berlin-based Jina AI; the small version has 677 million parameters and 32,768 tokens of input.

Jina AI Embeddings AI features, pricing and GDPR (October 2026)
Embedding and reranker API from Berlin-based Jina AI, part of Elastic since October 2025, with multilingual and multimodal models.
Pricing: Usage-based
Billed by processed tokens through top-up API keys; new users get free tokens; on-premises license through Elastic by quote (as of September 2026).
What is Jina AI Embeddings?
Jina AI offers embedding and reranker models through an API for search, retrieval-augmented generation and agents. The Berlin company has been part of Elastic since October 2025 and also sells its models for private deployment.
Jina's Search Foundation API covers embeddings, rerankers, a reader that converts web pages to text and a search endpoint. Current models include multilingual text embeddings and omni models for text, image, audio and video. The models are available on the AWS, Azure and Google Cloud marketplaces, and Elastic sells a Jina On-Prem license with offline Docker containers since August 10, 2026. Data processing is governed by Elastic's customer DPA.
Jina AI Embeddings AI features and use cases
- Embeds multilingual documentsText embedding models map documents in many languages into vectors, and the nano model covers 15 major languages including German, French and Japanese. Teams can run one search index across markets.
- Searches across media typesOmni models place text, images, audio and video in one embedding space. A text query can find a matching image or video clip, which helps media and product teams search mixed archives.
- Improves ranking of resultsRerankers rescore a candidate list against the query. Search and RAG applications return more relevant passages to users and language models.
What sets Jina AI Embeddings apart
- Berlin-based GmbH owned by Elastic, with data processing under Elastic's customer DPA.
- Offline on-premises containers through the Jina On-Prem license and deployment via cloud marketplaces.
- Omni models for text, image, audio and video in one vector space.
Where Jina AI Embeddings is strongest
Jina AI GmbH is registered with the Berlin commercial register and has its address in Berlin.
Questions to ask before you buy Jina AI Embeddings
Read the current Elastic privacy statement and customer DPA, since Jina's older terms predate the acquisition and may no longer reflect how data is processed. Ask where the hosted API processes data. For private deployment, contact Elastic sales about the Jina On-Prem license. Prices per token are shown in the account area, so request figures before you plan volumes.
Using Jina AI Embeddings in the EU: GDPR and AI Act
- Data locationNot published by the vendor.
- Data processing agreementPublic, read it here (opens in a new tab).
- EU AI ActCheck whether the AI prepares decisions about people. If not, the high-risk rules usually do not apply. The high-risk obligations apply from December 2, 2027 (Digital Omnibus).
Jina AI Embeddings reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about Jina AI Embeddings
Who is behind Jina AI?
Jina AI GmbH in Berlin was acquired by Elastic N.V. in October 2025. Data processing for Jina products is now governed by Elastic's data processing terms.
Is there a free trial?
Yes. New users get an auto-generated API key with free tokens that can be used across all models. After that, tokens are purchased as top-ups.
Can I host Jina models myself?
Yes. Models are available on the AWS, Azure and Google Cloud marketplaces, and Elastic sells Jina On-Prem for offline and air-gapped environments.
Jina AI Embeddings update historyno updates yet
No changes recorded for Jina AI Embeddings yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to Jina AI Embeddings
Tools in the same category (Embedding APIs) with the most overlapping markets.
Embedding model from Canadian vendor Cohere for text and images in 100+ languages, via API, dedicated or private deployment.
MongoDB's embedding and reranker API with general, multilingual and domain models for finance, legal and code.
Open embedding model from the Beijing Academy of AI for more than 100 languages, with dense, sparse and multi-vector retrieval in one model.



