Understand this story
On November 4, 2026, Cohere announced that its retrieval models Embed 5 and Rerank 5 are now available on OpenRouter. According to information published on Cohere's product and research blog the same day, users can call both models through a single API with unified billing, without the need for an additional SDK. Embed 5 Pro and Fast share the same embedding space, allowing Pro to be used for indexing and Fast for queries to reduce latency; Rerank 5's scores are calibrated, so the same relevance threshold can filter weak context across queries and domains. Embed 5 supports 256 to 2048-dimensional Matryoshka vectors, defaults to 2048 dimensions, and handles up to 128k tokens per request. Currently, this news has only one source, Cohere's official blog, and there have been no follow-up reports.
AI-generated from public reports
Latest development · Report
Cohere Retrieval Models Embed 5 and Rerank 5 Now Available on OpenRouterDevelopments
1 confirmed developments
Cohere's Embed 5 and Rerank 5 are now available on OpenRouter
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 4
Cohere Product and Research BlogFirst-party
Cohere Retrieval Models Embed 5 and Rerank 5 Now Available on OpenRouter
Cohere's Embed 5 and Rerank 5 retrieval models are now available on OpenRouter, accessible through a single API call with unified billing and no additional SDK required. Embed 5 Pro and Fast share the same embedding space, so you can index with Pro and query with Fast to reduce latency; Rerank 5's scores are calibrated, allowing the same relevance threshold to filter weak context across queries and domains. Embed 5 supports 256 to 2048-dimensional Matryoshka vectors, defaults to 2048 dimensions, and handles up to 128k tokens per request.