Aya Vision 8B
Cohere's Aya Vision 8B is a multilingual chat model optimized for vision-language use cases, including OCR, captioning, and question answering, with capabilities in 23 languages. It is genuinely best at handling a variety of tasks that require both text and image inputs, such as visual reasoning and summarization.
Input
Output
Context
16K
Max Output
4K
Parameters
8.6B
Technical Specifications
Model TypeChat
Context Window16,000 tokens
Max Output Tokens4,000 tokens
Parameters8.6B
Release DateMar 2, 2025
Training CutoffNot available
Licensecc-by-nc-4.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Aya Vision 8B
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.