cohere
Aya Vision 32B
c4ai-aya-vision-32b
Fields
| provider | "cohere" |
|---|---|
| model_id | "c4ai-aya-vision-32b" |
| display_name | "Aya Vision 32B" |
| status | "ga" |
| release_date | null |
| deprecation_date | null |
| retirement_date | null |
| pricing | {"input_per_mtok": null, "output_per_mtok": null, "cached_input_per_mtok": null, "batch_discount_pct": null} |
| context_window_tokens | 16000 |
| context_window_notation | "16k" |
| max_output_tokens | 4000 |
| modalities | {"input": ["text", "image"], "output": ["text"]} |
| knowledge_cutoff | null |
| verified_at | "2026-07-20T01:30:00Z" |
| notes | "Cohere model page confirms live API availability and limits; public token price was not found in the collected primary pricing page." |
| permalink | "/models/cohere/c4ai-aya-vision-32b.html" |
Sources
https://docs.cohere.com/docs/models
Accessed: 2026-07-20T01:30:00Z
Fields: model_id, status, modalities, context_window_tokens, max_output_tokens
c4ai-aya-vision-32b Live Aya Vision is a state-of-the-art multimodal model excelling at a variety of critical benchmarks for language, text, and image capabilities. Serves 23 languages. Text, Images 16k 4k Chat
https://docs.cohere.com/docs/aya-vision
Accessed: 2026-07-25T12:20:00Z
Fields: modalities
Aya Vision’s multimodal capabilities enable it to understand content across different media types, including text and images as input.
Verified At
2026-07-20T01:30:00Z
Changelog History
- 2026-07-20 v0.8: cohere/c4ai-aya-vision-32b added