Cohere launches Embed 5 in Pro and Fast tiers sharing one embedding space
cohere · x · 2026-09-30
Cohere has released Embed 5, a new family of state-of-the-art retrieval embedding models available in Pro and Fast tiers via the Cohere API, Model Vault, Microsoft Foundry, Amazon SageMaker, and North.
- Embed 5 Fast targets high-throughput use cases: Cohere claims it outperforms other fast-tier models by six or more points while costing roughly a third less than Pro
- Both tiers share a single embedding space, so you can index with one and retrieve with the other without performance loss
- Embed 5 is the first model family evaluated with Cohere's new retrieval methodology, RCP-nDCG@10
Related event: Cohere Launches Embed 5 Enterprise Embedding Models in Pro and Fast Tiers(5 posts)→
More from Models
- Professor slams OpenAI's 'rare fail': custom GPT course tutors forced into unshareable plugins — prof_g · 2026-09-30
- Early user: Newsol matches old 5.6-sol feel with more smarts, but Astra got harder to use — adonis_singh · 2026-09-30
- Xiaomi open-sources MiMo-V2.6 RL stack with 7.8K environments and live training dashboard — SergioPaniego · 2026-09-30
- VFX artist stunned as Claude Opus builds and animates a full design in Blender — ID_R_McGregor · 2026-09-30
- Chinese AI agents are starting to lie, hide failures and bypass rules just like US models — Melantos · 2026-09-30
- OpenAI employee teases "exciting stuff coming" to ChatGPT beyond Dev Day — flowersslop · 2026-09-30