aya vision 8b
CohereLabs/aya-vision-8b
Open Source · chat · open-weights
Open
Alert me on changes
Context
16K
Max output
4K
Weights
Open
API $/1M
—
Modalities
text · image
Released
02 Mar 2025
License: cc-by-nc-4.0 · CohereLabs/aya-vision-8b
AI summary
● machine-written
Cohere releases Aya Vision 8B multilingual vision-language model
Aya Vision 8B is a compact, open-weight 8-billion-parameter multimodal model from Cohere supporting 23 languages for image and text understanding tasks. It processes text and image inputs with a 16K token context window and up to 4K output tokens, designed for OCR and visual question answering use cases.
What's new
- Supports 23 languages including English, Mandarin, Arabic, Japanese, and others
- 16K context window with 4K maximum output tokens
- Available under CC-BY-NC-4.0 open-weight license
Best for
Optical character recognition (OCR) on documents and screenshotsVisual question answering tasksMultilingual image content analysis