All models
Jina AI

Jina Reranker v3.5

Jina's compact listwise reranker for long, multilingual, structured, legal, financial, and domain-specific candidate sets.

Plain-English overview

What Jina Reranker v3.5 actually is

Jina Reranker v3.5 reads the query and candidate list together instead of scoring every item in complete isolation. Its 131K shared context can preserve cross-document comparisons and accommodate long candidates, while the 0.6B model is small enough for more controlled deployment options.

Jina emphasizes structured and professional-domain retrieval and publishes both hosted and self-hosted routes. The weights are available for non-commercial use; commercial deployment requires the appropriate Jina or Elastic license.

Good fit for

  • Long candidate lists that benefit from listwise comparison
  • Legal, financial, multilingual, or structured retrieval
  • Air-gapped and controlled search infrastructure

Category comparison

The facts that matter for reranking models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Price basis
Token packages; no single public dollar rateThe provider's billing unit, with the document or token assumptions needed to compare it fairly.
Text capacity
131K tokens shared by query and candidatesHow much query and candidate text the model can consider in one scoring pass.
Candidates per request
No fixed count published; bounded by shared contextThe maximum number of possible results accepted in one request, when the provider publishes it.
Language coverage
93 supported; trained on 24Published multilingual support; an exact count is shown only when the provider gives one.
Structured data
Tables, JSON, XML, legal and domain textWhether the model is documented for JSON, tables, XML, or other data beyond normal prose.
Where it runs
Jina API, Elastic, clouds, Hugging Face, air-gappedHosted API, cloud marketplace, private deployment, or self-hosted weights.

API and provider access

Where to get Jina Reranker v3.5

Availability

Regions and access stage

Available through the Jina API, Elastic Inference Service, cloud marketplaces, Hugging Face, and air-gapped deployment.

Hosted region coverage depends on Jina, Elastic, or the selected cloud. Self-hosting gives the operator direct location control.

Check live availability

Data and training

The route matters.

Self-hosted and air-gapped deployments keep request data inside infrastructure you control. The reviewed hosted API pages do not state a complete retention or training-use commitment, so confirm Jina or Elastic terms for sensitive search data.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

Jina Reranker v3.5 FAQ

What is Jina Reranker v3.5?

Jina's compact listwise reranker for long, multilingual, structured, legal, financial, and domain-specific candidate sets. Jina Reranker v3.5 reads the query and candidate list together instead of scoring every item in complete isolation. Its 131K shared context can preserve cross-document comparisons and accommodate long candidates, while the 0.6B model is small enough for more controlled deployment options.

When was Jina Reranker v3.5 released?

Jina Reranker v3.5 was released on July 27, 2026 according to the cited provider materials.

Where can I access Jina Reranker v3.5?

Available through the Jina API, Elastic Inference Service, cloud marketplaces, Hugging Face, and air-gapped deployment. The access routes listed in this guide are Jina AI, Hugging Face, and Elastic.

How much does Jina Reranker v3.5 cost?

Token-package pricing; starter tokens included. Jina publishes token-based billing but not a single comparable dollar rate on the model page. Open weights use CC BY-NC 4.0, so commercial self-hosting requires a commercial license.

Where is Jina Reranker v3.5 available?

Available through the Jina API, Elastic Inference Service, cloud marketplaces, Hugging Face, and air-gapped deployment. Hosted region coverage depends on Jina, Elastic, or the selected cloud. Self-hosting gives the operator direct location control.

Is my Jina Reranker v3.5 API data used for training?

Self-hosted and air-gapped deployments keep request data inside infrastructure you control. The reviewed hosted API pages do not state a complete retention or training-use commitment, so confirm Jina or Elastic terms for sensitive search data. The policy belongs to the provider route and account terms, so verify it again before production use.