Models Directory

Aya Expanse is a highly performant 32B multilingual model, designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages.

Aya Expanse is a highly performant 8B multilingual model, designed to rival monolingual performance through innovations in instruction tuning with data arbitrage, preference training, and model merging. Serves 23 languages.

Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. Serves 23 languages. This 32 billion parameter variant is focused on state-of-art multilingual performance.

Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. This 8 billion parameter variant is focused on low latency and best-in-class performance.

ChatGPT-4o points to the GPT-4o snapshot currently used in ChatGPT. We recommend using an API model like GPT-5 or GPT-4o for most API integrations, but feel free to use this ChatGPT-4o model to test our latest improvements for chat use cases.

Claude 3 Opus

Claude 3.5 Sonnet

Claude 3.5 Sonnet v2

Our cutting-edge language model for coding with the first version released May 2024

Our cutting-edge language model for coding with the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more on our blog post

Our cutting-edge language model for coding released in January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more in our blog post

Our cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more in our blog post

Our state-of-the-art semantic for extracting representation of code extracts

Our first mamba 2 open source model released July 2024. Learn more on our blog post

An instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.

Command A is our most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.

A smaller, faster version of command. Almost as capable, but a lot faster.

To reduce the time between major releases, we put out nightly versions of command models. For command-light, that is command-light-nightly. Be advised that command-light-nightly is the latest, most experimental, and (possibly) unstable version of its default counterpart. Nightly releases are updated regularly, without warning, and are not recommended for production use.