Cohere models
All 10 Cohere models on OpenDunes, priced in Algerian Dinars.
10 models
Rerank 4 Fast takes a search question and a list of candidate documents and returns them ordered by relevance, reading up to about 32 pages per document, question included, in more than 100 languages. It is the lighter of the two Rerank 4 models, suited to quick replies and heavy traffic, so use it where many searches arrive at once.
You send Rerank 4 Pro a search question and a list of candidate documents, and it returns them ordered by relevance. Each document, question included, can run to about 32 pages, in more than 100 languages, and data records are accepted alongside text. Use it as a second pass after a keyword search or a search by meaning, for hard questions and long documents where result quality counts most. Rerank 4 Fast is the lighter version for quick replies; Rerank v3.5 reads only about 4 pages per document.
Cohere's earlier reranker, from before Rerank 4, reordering semantic or keyword search results by relevance and handling multi-aspect and semi-structured data across more than 100 languages
This model accepts text and pictures as input to generate numerical representations of the content. It can process up to 120 pages of material simultaneously. Its design focuses on being a fast and economical option for content representation tasks. The model is limited to processing and outputting these representations and cannot perform tasks requiring complex reasoning or generating new written material.
This model accepts text and pictures as input and outputs numerical representations of the content. It can process up to 120 pages of material at once and generate up to 110 pages of output. It is designed to be a higher accuracy tier within its family of models. This model is limited to processing and outputting these representations and cannot perform tasks requiring complex reasoning.
Command A+ is Cohere's flagship for business agents. It reads text and images, replies with text up to about 64 pages, uses your connected tools following the exact form you set, fills in tables as specified, and can think before answering. Use it to read a scanned form or screenshot and act on it, or to run a multi-step workflow. Command A is the text-only sibling that keeps about 256 pages in mind and replies up to about 8; pick that when you need to pack in more reading and have no images.
Command R7B is the small, fast model of the Command R line, updated in December 2024. It answers from documents you supply, uses connected tools and handles agent steps that need some reasoning, keeping about 128 pages in mind and replying up to about 4 pages. Use it as a quick worker behind a larger agent, or for high-volume question answering over your documents.
Command R (08-2024) answers questions from documents you supply, uses your connected tools, and works across many languages, keeping about 128 pages in mind and replying up to about 4 pages. Compared with the first Command R, maths, code and reasoning improved. Pick it for support bots and knowledge-base search that answer from retrieved passages. Command R+ is the choice for harder multi-step tool use, and Command R7B when speed matters most.
Command A is a Cohere model that you can download and run yourself, for text in and text out, keeping about 256 pages in mind and replying up to about 8 pages. It is built for agents that use connected tools, for answering from documents you supply, and for work in many languages. Use it when you need long source material in one request or want to run it yourself.
Command R+ (08-2024) answers from documents you supply and uses several connected tools in a row, keeping about 128 pages in mind and replying up to about 4 pages. Cohere reports about 50% more work done in the same time and 25% faster replies than the earlier R+ on the same hardware.