News
ReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior ReleaseReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior Release
EveryLLM
imgAya Vision

Aya Vision

Open-weights multilingual multimodal vision model from Cohere For AI

Aya Vision is a multilingual, multimodal model with open weights, released by Cohere For AI as a foundation for AI that can see and communicate across languages. Cohere presents it as a vision model supporting multilingual and multimodal communication globally.

Share on WhatsApp

  • Open-weights vision model from Cohere For AI
  • Multilingual and multimodal, handling images and text
  • Positioned as a base for global AI communication
  • Part of the Aya family of multilingual models

What it is

Aya Vision is an open-weights model that combines vision with language, built by Cohere For AI. The company describes it as a foundation for AI-enabled communication that works across many languages and handles images as well as text. It sits within the Aya line of multilingual models. Cohere positions it as a vision model aimed at global use rather than English-only settings, giving developers a base they can build multilingual and multimodal applications on.

How to use it

The weights are released openly. Cohere describes the model as open-weights, meaning the trained parameters can be downloaded and used rather than only reached through a service.

Questions people ask about Aya Vision

What is Aya Vision?

It is a multimodal model from Cohere For AI that works with images and text across many languages. The company released it with open weights so developers can build on it directly, and describes it as a foundation for multilingual, multimodal AI communication.

Who makes it?

Cohere For AI, the research arm associated with Cohere. The company presents the model as part of its work on open science and multilingual AI, and released it under the Aya name used for its multilingual model family.

Is it open?

Yes. Cohere describes Aya Vision as an open-weights model, which means the trained parameters are published for download and use, rather than being available only through a hosted API or app.

What makes it different from English-focused models?

Cohere says the model is built for multilingual and multimodal use globally, so it is aimed at communication across languages rather than English alone, with vision capabilities alongside text.

Good reading and sources

    Where this page comes from

    There is no English Wikipedia article on Aya Vision yet, so the facts on this page come from the sources listed above: cohere.com/blog/aya-vision. Some are the subject's own pages, so its claims about itself are reported as its claims. EveryLLM wrote the text in its own words, with AI assistance, and compares it with the sources to make sure no passage is copied.

    It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

    The weekly digest

    Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.