-

Elastic Makes High-Accuracy, Cost-Efficient Jina AI Models Available on Microsoft Foundry

Compact Jina v5 model family delivers multilingual, multimodal retrieval for AI agents and search applications on Microsoft Azure, with frontier-grade accuracy at lower costs

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC) today announced that jina-embeddings-v5-text and jina-embeddings-v5-omni models are now available in the Microsoft Foundry model catalog, deploying as a dedicated endpoint in the customer’s own Microsoft Azure environment. Developers building AI agents and search applications on Azure can run the models as dedicated endpoints in their own Azure accounts, bringing highly accurate semantic search and retrieval to their applications without the compute costs of larger models.

Jina AI by Elastic builds small, purpose-built models that rank at or near the top of industry benchmarks. Jina embeddings v5 for text bring high accuracy in a small footprint across more than 100 languages. The models serve as the backbone for the v5 embeddings omni models, which add multimodal support for images, audio, and video over the same languages. In standard benchmarks, Jina embeddings v5 omni models deliver frontier-class results across all four of these modalities. They outperform models up to 20x larger on image benchmarks (MIEB and ViDoRe), lead their size class on audio (MAEB), and compete with video grounding models several times their size (MMEB-v2).

The Jina embeddings v5 model family includes two types of models, each available in two parameter sizes:

  • Text models: jina-embeddings-v5-text-small and jina-embeddings-v5-text-nano are multilingual text embeddings for retrieval, matching, clustering and classification.
  • Omni models: jina-embeddings-v5-omni-small and jina-embeddings-v5-omni-nano add support for images, audio and video, all in one vector space, allowing unified cross-modal search with a single query.

“AI applications succeed or fail on retrieval, and the best embedding model is the one a team can run where its data already lives,” said Han Xiao, vice president of AI, Elastic. “Bringing Jina embeddings v5 to Microsoft Foundry means teams building on Microsoft Azure can add accurate multilingual, multimodal retrieval to their AI agents and search applications, running in their own Azure accounts, without the compute costs of larger models.”

"Customers need the flexibility to choose the right model for each workload,” said Uli Homann, corporate vice president and distinguished architect, Microsoft. “Adding Jina embeddings v5 to Microsoft Foundry broadens the choice of specialized models for multilingual and multimodal retrieval. These models deploy as dedicated endpoints in the customer's Microsoft Azure environment, helping teams build search and agent experiences within their established security and governance boundaries."

Availability

Jina embeddings v5 text and omni models are available now in the Microsoft Foundry model catalog as dedicated endpoints. Get started here.

About Elastic

Elastic (NYSE: ESTC) integrates its deep expertise in search technology with artificial intelligence to help everyone transform all of their data into answers, actions, and outcomes. Elasticsearch, which is the foundation for its search, observability, and security solutions, is used by thousands of companies, including more than 75% of the Fortune 100. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of elasticsearch B.V. and its subsidiaries. All other company and product names may be trademarks of their respective owners.

Contacts

Media Contact
Elastic PR
PR-team@elastic.co

Elastic N.V.

NYSE:ESTC

Release Versions

Contacts

Media Contact
Elastic PR
PR-team@elastic.co

More News From Elastic N.V.

Elastic to Announce Second Quarter Fiscal 2027 Earnings Results on Thursday, November 19, 2026

SAN FRANCISCO--(BUSINESS WIRE)--Elastic to announce second quarter Fiscal 2027 earnings results on Thursday, November 19, 2026...

Elastic’s Threat Report Reveals Attackers Are Turning Trusted AI and IT Tools Against the Enterprises That Deploy Them

SAN FRANCISCO--(BUSINESS WIRE)--Elastic’s threats, etc. report finds attackers abusing trusted IT and AI tools and using stolen credentials an average of 8 minutes after infection....

Elastic Announces Multi-Year Partnership with Audi Revolut F1® Team, Expanding Search and Observability Collaboration

SAN FRANCISCO--(BUSINESS WIRE)--Elastic (NYSE: ESTC) and today announced a new multi-year partnership with Audi Revolut F1® Team, building on the team’s existing use of Elastic technology to support its engineering software operations. Elastic joins as Official Race Partner for the 2026 United States Grand Prix in Austin, Texas, and will become its Official Search and Observability Supplier starting from the 2027 season. The agreement brings an established technical collaboration onto a global...
Back to Newsroom