Cohere has introduced Embed 5, a new embedding model family built for enterprise search, retrieval-augmented generation, and agentic retrieval use cases. The release includes two tiers: Embed 5 Pro, which is aimed at maximum retrieval quality, and Embed 5 Fast, which is tuned for lower latency and lower cost in real-time query workloads. Both models support text, image, and mixed text-image inputs, cover more than 100 languages, and offer a context window of up to 128,000 tokens. Cohere said the two tiers share the same embedding space, allowing users to build indexes with Pro and run queries with Fast to balance quality and efficiency. The models are now available through Cohere API, Model Vault, Microsoft Foundry, and Amazon SageMaker, with support for private VPC or on-premises deployment through vLLM. In benchmark testing, Embed 5 Pro posted an average score of 85.8 on the ViDoRe V3 dataset, ahead of Voyage 4 Large, Gemini Embedding 2, and OpenAI’s text-embedding-3-large. MarkTechPost also said the model ranked first on FinanceBench and other finance-related datasets.
Cohere has released Embed 5, a new family of embedding models aimed at enterprise search, retrieval-augmented generation, and agentic retrieval.
Two tiers target different workloads
The lineup includes two versions. Embed 5 Pro is designed for maximum retrieval quality, while Embed 5 Fast is optimized for latency and cost in real-time query scenarios.
Both models support text, image, and mixed text-image inputs. They cover more than 100 languages and support context lengths of up to 128,000 tokens.
Shared embedding space
The two models operate in the same embedding space, which lets users build indexes with Pro and query them with Fast. Cohere said this setup is intended to balance quality and efficiency.
Availability and deployment
Embed 5 is available on Cohere API, Model Vault, Microsoft Foundry, and Amazon SageMaker. It also supports private VPC or on-premises deployment through vLLM.
Benchmark results
In benchmark testing, Embed 5 Pro recorded an average score of 85.8 on the ViDoRe V3 dataset, ahead of Voyage 4 Large, Gemini Embedding 2, and OpenAI’s text-embedding-3-large.
According to MarkTechPost, the model also stood out in finance-related evaluations, ranking first on datasets including FinanceBench.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
