docsCohere 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.
Cohere models are currently available on the following platforms:
At the end of each major section below, you’ll find technical details about how to call a given model on a particular platform.
In this section, we’ll provide some high-level context on Cohere’s offerings, and what the strengths of each are.
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, meaning they are well-suited for chat applications, and Command A Vision can interact with image inputs.
In this table, we provide some important context for using Cohere Command models on Amazon Bedrock, Amazon SageMaker, and more.
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. The Representation model comes with a variety of helper functions, such as for detecting the language of an input.
In this table, we provide some important context for using Cohere Embed models on Amazon Bedrock, Amazon SageMaker, and more.
The Rerank model can improve created models by re-organizing their results based on certain parameters. This can be used to improve search algorithms.
In this table, we provide some important context for using Cohere Rerank models on Amazon Bedrock, SageMaker, and more.
Rerank accepts full strings rather than tokens, so the token limit works a little differently. Rerank will automatically chunk documents longer than 510 tokens, and there is therefore no explicit limit to how long a document can be when using rerank. See our best practice guide for more info about formatting documents for the Rerank endpoint.
Cohere Transcribe is our dedicated model for audio-in, text-out automatic speech recognition (ASR) workloads.
Cohere Transcribe isn’t available on other platforms.
Aya is a family of multilingual large language models designed to expand the number of languages covered by generative AI for purposes of research and to better-serve minority linguistic communities.
The 32-billion parameter Aya Expanse offering is optimized to perform well in these 23 languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese.
The 32-billion parameter Aya Vision model is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities.
Tiny Aya is a compact 3.35B-parameter multilingual model supporting 70 languages. Its instruction-tuned variants are available on the Cohere API via the Chat endpoint and as open-weight models on Hugging Face.
