{
  "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,
  "sources": [
    {
      "url": "https://docs.cohere.com/docs/models",
      "accessed_at": "2026-07-20T01:30:00Z",
      "fields": [
        "model_id",
        "status",
        "modalities",
        "context_window_tokens",
        "max_output_tokens"
      ],
      "quote": "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"
    },
    {
      "url": "https://docs.cohere.com/docs/aya-vision",
      "accessed_at": "2026-07-25T12:20:00Z",
      "fields": [
        "modalities"
      ],
      "quote": "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",
  "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"
}