Cohere launches Embed 5 embedding models for enterprise retrieval
Cohere has released Embed 5, an embedding model family designed for enterprise search, retrieval-augmented generation and agentic retrieval. It includes Embed 5 Pro, aimed at maximum retrieval quality, and Embed 5 Fast, optimized for lower latency and cost during live queries. Both models process text, images and combined text-image inputs, support 100+ languages and accept up to 128K tokens.
The models use one embedding space, allowing a corpus to be indexed with Pro and queried with Fast. In Cohere’s tests across 40 development datasets, this combination scored 98.4 when Pro plus Pro was normalized to 100, while an all-Fast setup scored 96.6. Fast processed 377.3 documents per second, compared with 159.7 for Pro. Both sides must use the same output dimension.
The API model IDs are embed-v5.0-pro and embed-v5.0-fast. They are generally available through the Cohere API and Model Vault, Microsoft Foundry and Amazon SageMaker, with private VPC or on-premises serving via vLLM. Pro costs $0.12 per 1M text tokens and Fast $0.08; image inputs cost $0.40 per 1M tokens for both. Cohere-reported benchmarks put Pro ahead of Voyage 4 Large, Gemini Embedding 2 and OpenAI text-embedding-3-large on several evaluations, although the company’s metric emphasizes reranking and independent replication is pending.
Written by Sakhanda Wire AI from reporting by MarkTechPost. Facts, quotes and full context are in the original article below.