Cohere Makes Embed 5 and Rerank 5 Available on OpenRouter
Cohere announced on November 4, 2026 that Embed 5 and Rerank 5 are available on OpenRouter. Existing OpenRouter users can call them with the same API key and credits, without separate SDKs, accounts or bills.
Cohere announced on November 4, 2026 that its Embed 5 and Rerank 5 retrieval models are available on OpenRouter. Existing OpenRouter users can call them with the same API key and credits they use for other models, without separate SDKs, accounts or bills, according to the report from Unite.AI.
Where the models fit in a RAG pipeline
The two models cover the retrieval stages of a retrieval-augmented generation (RAG) pipeline:
- Embed 5 converts documents and queries into vectors.
- Rerank 5 rescores candidate results against the query.
- Generation of the final answer can be handled by any chat model available on OpenRouter.
This means a full RAG workflow can run through a single OpenRouter integration, with Cohere handling retrieval and a chat model of the user's choice handling the answer.
What this means
The change is about access, not a new model launch. Teams already routing chat models through OpenRouter can add embedding and reranking to the same setup, using the same key, credits and billing. Retrieval and generation can then sit behind one API rather than being split across separate vendor accounts and SDKs.
Related Articles
NVIDIA publishes NVFP4 DeepSeek-V4.1-Flash-1017 checkpoint at about 400 GiB for Blackwell GPUs
NVIDIA released an NVFP4 quantized checkpoint of DeepSeek AI's DeepSeek-V4.1-Flash-1017 on Hugging Face on 10/30/2026. The checkpoint is about 400 GiB, targets NVIDIA Blackwell GPUs, and matches the MXFP4 source closely on six benchmarks, according to NVIDIA's evaluation.
Baidu unveils Apollo World, a world model that generates up to 100,000 km of simulated driving per day
Baidu unveiled Apollo World on November 3, a world model that simulates interactive road environments to train and test autonomous vehicles. The company says it can generate up to 100,000 kilometers of simulated driving per day and already supports Apollo Go's global robotaxi development.
Ant Group's LingBot Robot Models Pass 2.2 Million Downloads as Pharmacy Robots Run in Shanghai Stores
Ant Group's embodied AI unit says its open-source LingBot robot foundation models have passed 2.2 million downloads and 33,000 GitHub stars in nine months. It also presented a 2.0 lineup and a robotic pharmacy already operating in several Guoda Pharmacy stores in Shanghai.
Google Antigravity gets Cheminformatics Skills; agent runs drug design workflow in an hour, DeepMind says
Google DeepMind has released Cheminformatics Skills for Google Antigravity, pairing a language model agent with RDKit and connectors to ChEMBL and PubChem. In a lung cancer case study, DeepMind says the agent went from literature search to proposed macrocycles with synthetic routes in an hour, versus multiple days for a typical iteration.
Comments
Loading...