Cohere's Embed 5 and Rerank 5 models go live on OpenRouter in Pro and Fast tiers
cohere · x · 2026-11-04
Cohere's Embed 5 and Rerank 5 families are now available on OpenRouter via a single API with unified billing.
- Embed 5 Pro: a 2.4B-parameter multimodal embedding model that embeds text, images, and interleaved content into one vector space; 128K context, 100+ languages, selectable output dimensions (256–2048), priced at $0.12/M tokens. It shares its embedding space with Embed 5 Fast, enabling an index-with-Pro, query-with-Fast pattern.
- Rerank 5 Pro: built for ranking-quality-critical retrieval pipelines (complex queries, long/domain-specific docs, RAG), with relevance scores calibrated to a 0–1 range for consistent thresholds; priced at $0.05/M tokens with 33K context. A lower-latency Rerank 5 Fast targets high-volume search and agent loops.
Related event: Cohere Embed 5 and Rerank 5 land on OpenRouter(4 posts)→
More from Models
- AI semiotics: models are swayed by visual symbols without recognizing it in their chains-of-thought — emollick · 2026-11-05
- vLLM ships day-0 support for Kimi K3.1 across NVIDIA, AMD and TPUs — vllm_project · 2026-11-05
- Kimi K3.1 Pro hits 61.2% on long-horizon code bench, up from 55.95% — vllm_project · 2026-11-05
- Liquid AI: vision encoders can burn more compute than the LLM on large images and video — JosephJacks_ · 2026-11-05
- Baseten explains how to make flash models faster: kernel fusion, PDL, and host loop cuts — baseten · 2026-11-05
- Moonshot AI open-sources Kimi K3.1 Pro: 2.8T-param MoE with 1M-token context — Kimi_Moonshot · 2026-11-05