jina-embeddings-v2-base-es
A Spanish-English encoder supporting longer text inputs for bilingual retrieval.
Base Model Family
jina-bert-v2-base-es
Deployment
Related models
Academic Publications
arXiv February 26, 2024 Multi-Task Contrastive Learning for 8192-Token Bilingual Text EmbeddingsApril 29, 2024 • 7 minutes read Jina Embeddings and Reranker on Azure: Scalable Business-Ready AI Solutions Jina Embeddings and Rerankers are now available on Azure Marketplace. Enterprises that prioritize privacy and security can now easily integrate Jina AI's state-of-the-art models right in their existing Azure ecosystem.February 14, 2024 • 4 minutes read Aquí Se Habla Español: Top-Quality Spanish-English Embeddings and 8k Context Jina AI's new bilingual Spanish-English embedding model brings the state-of-the-art in AI to half a billion Spanish speakers.
Compare models 0 / 3
Select two or three models to compare their published specifications.
- Released
- 2024-02-14
- Parameters
- 161M
- Context length
- 8K tokens
- Output dimensions
- 768
- Inputs
- text
- Languages
- en · es
- Outputs
- vector
- Availability
- api · huggingface · aws · azure · airgapped
Choose a representation
The catalog lists 768 output dimensions. Supported dimensions and input types depend on the model; check the request schema before switching a production index.
Model weights and hosted API access
The license shown above applies to the published model assets. Calling a hosted API and downloading weights for commercial self-hosting are separate arrangements.
The catalog marks these model assets as Apache-2.0. Check the official repository for the license, notices, and any third-party dependencies before redistribution.
Read the official licenseExplore newer models
Catalog checked on September 7, 2026. This is an independently prepared Chatsax guide to Jina models.