Aya Vision 8B
by Cohere · listed Mar 2025VW
Compact open multilingual vision model for OCR and visual question answering
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
c4ai-aya-vision-8b- Context window
- 16K tokens
- Max output
- 4K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-03-04
- Last updated
- 2025-05-14
- Provider docs
- docs.cohere.com/docs/models