Cohere launches Embed 5 Pro and Fast with a shared embedding space

Cohere has released Embed 5, a family of embedding models offered in Pro and Fast tiers. Its September 30 announcement positions Pro for maximum retrieval quality and Fast for workloads where latency and cost matter.

The company lists both models with a 128K-token context window, support for text and image inputs, and coverage of more than 100 languages.

Two tiers, one index

Cohere lists Pro at $0.12 per million tokens and Fast at $0.08 per million tokens. It says the models share an embedding space, allowing teams to index documents with Pro and query with Fast without rebuilding the index. Both sides must use the same output dimension.

That compatibility does not mean identical retrieval quality. Across 40 development datasets, Cohere reports average losses of 1.6% for Fast queries and 2.7% for Pro queries in cross-model combinations, relative to its all-Pro baseline.

Cohere says Embed 5 is available through its API and Model Vault, Microsoft Foundry and Amazon SageMaker, and directly within North.