Cohere has a variety of models that cover many different use cases. If you need more customization, you can train a model to tune it to your specific use case.


Command is Cohere's default generation model that takes a user instruction (or command) and generates text following the instruction. Our Command models also have conversational capabilities which means that they are well-suited for chat applications.

Latest ModelDescriptionMax TokensEndpoints
command-lightA smaller, faster version of command. Almost as capable, but a lot faster.4096Co.generate()
commandAn instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.4096Co.generate()


This model generates natural language that can be used for used for interactive autocomplete, augmenting human writing processes, summarization, text rephrasing, and other text-to-text tasks in non-sensitive domains.

Latest ModelDescriptionMax TokensEndpoints
base-lightA smaller, faster version of base. Almost as capable, but a lot faster.2048Co.generate()
baseA model that performs generative language tasks.2048Co.generate()


These models can be used to generate embeddings from text or classify it based on various parameters. Embeddings can be used for estimating semantic similarity between two sentences, choosing a sentence which is most likely to follow another sentence, or categorizing user feedback, while outputs from the Classify endpoint can be used for any classification or analysis task. The Representation model comes with a variety of helper functions, like detecting the language of an input, or tokenizing/detokenizing an input.

Latest ModelDescriptionMax TokensEndpoints
embed-english-light-v2.0A smaller, faster version of embed-english-v2.0. Almost as capable, but a lot faster. English only.512Co.Classify(), Co.Embed(), Co.Detect_language(), Co.Tokenize(), Co.Detokenize()
embed-english-v2.0A model that allows for text to be classified or turned into embeddings. English only.512Co.Classify(), Co.Embed(), Co.Detect_language(), Co.Tokenize(), Co.Detokenize()
embed-multilingual-v2.0Provides multilingual classification and embedding support. See supported languages here.512[Co.Classify(), Co.Embed(), Co.Detect_language(), Co.Tokenize(), Co.Detokenize()

Rerank (Beta)

The Rerank model can improve created models by re-organizing their results based on certain parameters. This can be used to improve search algorithms.

Latest ModelDescriptionMax TokensEndpoints
rerank-english-v2.0A model that allows for re-ranking English language documents.N/ACo.rerank()
rerank-multilingual-v2.0A model for documents that are not in English. Supports the same languages as embed-multilingual-v2.0.N/ACo.rerank()


Rerank accepts full strings rather than tokens, so the token limit does not apply. See our best practice guide for more info about formatting documents for the Rerank endpoint.

Summarize (Beta)

This model generates a succinct version of a provided text. This summary relays the most important messages of the text, and a user can configure the results with a variety of parameters to support unique use cases.

Latest ModelDescriptionMax TokensEndpoints
summarize-mediumA smaller, faster version of summarize-xlarge. Almost as capable, but a lot faster.2048Co.summarize()
summarize-xlargeA model that takes a piece of text and generates a summary.2048Co.summarize()