Embedding and reranker API from Berlin-based Jina AI, part of Elastic since October 2025, with multilingual and multimodal models.

Jina Reranker AI features, pricing and GDPR (October 2026)
Reranker models from Berlin-based Jina AI, part of Elastic since 2025: multilingual, with long context and a multimodal variant.
Pricing: Usage-based
API billed by tokens across all Jina APIs; new API keys come with starter tokens. Commercial use runs through the paid API. Weights of the current models (v2, v3, v3.5, m0) are licensed under CC BY-NC 4.0 and are free for non-commercial self-hosting only; for commercial self-hosting Elastic sells the Jina On-Prem license. Only the older v1 models are under Apache 2.0.
What is Jina Reranker?
Jina Reranker is a family of reranking models that score how well documents match a query, used to sharpen the results of search and RAG systems. The models are offered through Jina's API and as weights on Hugging Face.
Jina AI GmbH, based in Berlin, was acquired by Elastic in October 2025; data processing now follows the Elastic customer DPA. The current lineup includes jina-reranker-v3.5 and v3 with 0.6 billion parameters and a 131,000-token context, the multimodal jina-reranker-m0, the smaller cross-encoder jina-reranker-v2-base-multilingual and jina-colbert-v2 for late interaction. The v2 multilingual model had about 1 million downloads on Hugging Face in the last month as of September 28, 2026. Weights of the current models are licensed CC BY-NC 4.0; production use needs a commercial license.
Jina Reranker AI features and use cases
- Sharpens RAG resultsThe reranker scores each retrieved passage against the query and sorts them, so the language model receives the most relevant context. This reduces wrong or vague answers in document chat and search.
- Ranks long documents in one passjina-reranker-v3.5 compares many candidates together in a 131K-token window. Teams can rank long passages without cutting them into small pieces first.
- Scores visual documentsjina-reranker-m0 handles documents with visual content such as scanned pages or charts. Search over slide decks and PDFs with images becomes more precise.
What sets Jina Reranker apart
- Covers text, long context and visual documents within one model family.
- Current weights are non-commercial by license; commercial self-hosting is sold by Elastic as Jina On-Prem.
- The API shares one token-based pricing model with Jina's other search APIs.
Where Jina Reranker is strongest
Jina AI GmbH is based in Berlin and has been part of Elastic since October 2025.
Questions to ask before you buy Jina Reranker
Check the license before downloading weights: current models are CC BY-NC 4.0 and production use requires a commercial license from Elastic. For the API, data processing follows the Elastic customer DPA; confirm processing regions for your contract. Token-based billing means costs grow with document length and query volume.
Using Jina Reranker 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 Reranker 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 Reranker
Can I use Jina Reranker models commercially?
Not under the default license of the current weights, which is CC BY-NC 4.0. Commercial self-hosting is available through Elastic's Jina On-Prem license, and the API can be used commercially.
Is there a free tier?
The reranker page names no permanent free plan. New API keys come with starter tokens, and the free key is limited to 100 requests per minute.
Who owns Jina AI?
Jina AI GmbH in Berlin was acquired by Elastic in October 2025.
Jina Reranker update historyno updates yet
No changes recorded for Jina Reranker 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 Reranker
Tools in the same category (Rerankers) with the most overlapping markets.
Embedding model from Canadian vendor Cohere for text and images in 100+ languages, via API, dedicated or private deployment.
Reranking API from Toronto-based Cohere that reorders search results by semantic relevance, multilingual and also for JSON.
Open reranker models from Mixedbread under Apache 2.0 for more than 100 languages and code, also available through the vendor's search API.



