Cohere · Cohere
Embed v3 English
ActiveEmbedding model for semantic search/clustering; Matryoshka support (1024/512/256 dims). $0.10 per 1M tokens. Released year known, exact month not stated.
About this version
Embed v3 English is an active embedding model from Cohere released in 2024, designed for semantic search and clustering tasks. It introduces Matryoshka support, allowing embeddings at multiple dimensionalities (1024, 512, or 256). The service is priced at $0.10 per million tokens.
- API string
- embed-english-v3.0
- Tier
- Embedding
- Released
- Jan 1, 2024
Release & change timeline
No dated events logged for this version yet.
Patches, price changes, benchmarks, and deprecations for Embed v3 English will appear here as they’re recorded. Follow the broader Catch Me Up digest in the meantime.
Report an issue with Cohere
Posts to your status feed
Pick the closest match below, edit the body, and post. Your report carries the #cohere tag automatically so it surfaces here + in the trending-tags rail. Reporting also follows Cohere so you’ll get status updates.
Part of the Cohere version timeline. Catch Me Up — everything that changed across AI & smart home ↗