Aya Vision 32B
Open multilingual vision model for OCR, visual reasoning, and image question answering
CohereTextPromo
Aya Vision 32B
Open multilingual vision model for OCR, visual reasoning, and image question answering
c4ai-aya-vision-32b- Type
- Text
- Quality
- 10 · Top 90% on the LMArena Vision
- Context window
- 16,000 tokens
- Max output
- 4,000 tokens
- Input price
- —
- Output price
- —
- Cache read
- —
- Cache write
- —
- Parameters
- 33B (33,137,896,688)
- Downloads
- 270 in the last 30 days
- Likes
- 230
- Access to weights
- Accept the license on Hugging Face first
- Released
- Mar 4, 2025
- Knowledge cutoff
- —
- Takes in
- Text, Image
- Puts out
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- File attachments
- Yes
- Access
- Open weights
- License
- CC BY-NC 4.0
- Rarity
- Promo
- Set number
- 509/1044
License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: docs.cohere.com.